Skip to content

Files

Latest commit

 

History

History
14 lines (14 loc) · 187 KB

CLUSTERS_INFO.csv

File metadata and controls

14 lines (14 loc) · 187 KB
1
 CountPercentageOur_labelBertopic_nameRepresentationkeywords_(1,1)keywords_(1,2)bigramstrigramsNOUNSVERBSADJimpact_ofrole_ofkeywords_count_vectorizer
2
08590.105emissions_substances_materials0_emissions_carbon_air_co2['emissions', 'carbon', 'air', 'co2', 'learning', 'waste', 'based', 'machine', 'emission', 'energy', 'machine learning', 'pollution', 'using', 'environmental', 'prediction', 'environment', 'used', 'quality', 'air quality', 'development', 'gas', 'global', 'climate', 'neural', 'time', 'sustainable', 'performance', 'air pollution', 'high', 'concrete'][('predicting', 0.394), ('forecasting', 0.3939), ('renewables', 0.3755), ('autoregressivemodel', 0.3751), ('predictors', 0.3732), ('emissions', 0.3629), ('machinelearning', 0.3628), ('econometrics', 0.3622), ('econometric', 0.357), ('boosting', 0.3547), ('autoregressive', 0.3481), ('regressors', 0.3469), ('polluting', 0.3462), ('bioenergy', 0.3452), ('predictive', 0.3451), ('classifiers', 0.3449), ('autoregression', 0.3331), ('forecasts', 0.3321), ('causation', 0.3272), ('regressing', 0.3237), ('causalities', 0.322), ('pollutions', 0.3201), ('causality', 0.3199), ('glm', 0.3196), ('backpropagation', 0.3187), ('regression', 0.3186), ('predictor', 0.3183), ('coal', 0.3162), ('perceptrons', 0.315), ('biofuels', 0.3095), ('climate', 0.3084), ('lstms', 0.3078), ('hydroelectricity', 0.306), ('co2influences', 0.3041), ('forecasters', 0.303), ('lstm', 0.3023), ('forecaster', 0.3023), ('polluters', 0.3023), ('regressor', 0.3016), ('regularization', 0.3007), ('prediction', 0.2995), ('predicts', 0.2991), ('pollution', 0.2981), ('svm', 0.297), ('datasets', 0.2932), ('ai', 0.2925), ('polluter', 0.2903), ('pollutants', 0.2895), ('autocorrelation', 0.2894), ('pollute', 0.2868)][('emissions forecasting', 0.6081), ('pollutant prediction', 0.6014), ('predicting pollutants', 0.5992), ('emissions prediction', 0.5991), ('forecasting carbon', 0.5782), ('pollution prediction', 0.5778), ('environmental prediction', 0.5748), ('emission forecasting', 0.5688), ('predict pollution', 0.5648), ('forecasting pollution', 0.5583), ('emissions predictors', 0.5558), ('pollution forecasting', 0.5464), ('predicted pollutants', 0.5453), ('pollution predict', 0.5449), ('predicting environmental', 0.5444), ('environmental forecasting', 0.5436), ('predict pollutant', 0.5424), ('emissions forecasted', 0.5384), ('pollutants predictions', 0.537), ('emissions forecasts', 0.5357), ('predicting renewable', 0.5355), ('forecast emissions', 0.5339), ('forecasting energy', 0.5309), ('emissions ai', 0.529), ('forecasting emission', 0.5256), ('forecasts carbon', 0.5244), ('predicting co2', 0.5235), ('sustainable predictive', 0.5211), ('forecasting coal', 0.5168), ('emissions predicted', 0.5155), ('econometrics carbon', 0.5154), ('predict environmental', 0.5073), ('predicting pm2', 0.5072), ('predictive sustainable', 0.5064), ('environment forecasting', 0.4997), ('co2 prediction', 0.4977), ('forecasting renewable', 0.4973), ('forecasting co2', 0.4967), ('predicts co2', 0.4958), ('emissions future', 0.4948), ('sustainable predicting', 0.4942), ('predicting carbon', 0.4941), ('pm2 forecasting', 0.4914), ('future emissions', 0.4909), ('pm2 prediction', 0.4898), ('forecasting pm2', 0.4893), ('emissions climate', 0.4885), ('pollution modeling', 0.4857), ('pollutant modeling', 0.4841), ('emissions 2022', 0.483)]machine learning: 782, climate change: 406, air quality: 273, deep learning: 267, neural network: 257, artificial intelligence: 242, air pollution: 238, global warming: 188, carbon dioxide: 178, co2 emissions: 166, carbon emissions: 149, random forest: 126, carbon emission: 118, energy consumption: 116, sustainable development: 108, artificial neural: 106, neural networks: 105, compressive strength: 98, greenhouse gas: 97, real time: 92, short term: 89, waste management: 89, renewable energy: 88, support vector: 87, using machine: 82, learning algorithms: 81, square error: 76, dioxide emissions: 74, human health: 74, term memory: 74, economic growth: 70, covid 19: 69, gas emissions: 66, long term: 65, time series: 65, ghg emissions: 63, learning ml: 63, co2 emission: 61, learning based: 61, learning techniques: 61, particulate matter: 59, learning approach: 58, solid waste: 57, low carbon: 54, economic development: 53, emission reduction: 53, convolutional neural: 52, gradient boosting: 52, absolute error: 51, fossil fuels: 51, fuel consumption: 51, intelligence ai: 51, linear regression: 51, vector machine: 49, global climate: 47, air pollutants: 46, carbon price: 46, error rmse: 42, fossil fuel: 41, greenhouse gases: 41, decision tree: 40, memory lstm: 40, decision making: 39, dioxide co2: 39, environmental sustainability: 39, natural gas: 39, network ann: 39, fly ash: 37, recent years: 37, energy sources: 36, forest rf: 35, decision support: 34, energy efficiency: 34, united states: 34, carbon capture: 33, co2 capture: 32, error mae: 32, formula presented: 32, public health: 31, real world: 31, using deep: 31, waste classification: 31, cross validation: 30, low cost: 30, plastic waste: 30, vector regression: 30, environmental impact: 29, extreme gradient: 29, large scale: 29, paper proposes: 29, sustainable environment: 29, carbon footprint: 28, mechanical properties: 28, quality index: 28, carbon neutrality: 27, learning algorithm: 27, using artificial: 27, deep neural: 26, dioxide emission: 26, geopolymer concrete: 26using machine learning: 81, short term memory: 74, artificial neural network: 70, carbon dioxide emissions: 67, machine learning algorithms: 65, machine learning ml: 63, greenhouse gas emissions: 53, machine learning techniques: 53, artificial intelligence ai: 51, support vector machine: 49, machine learning approach: 42, term memory lstm: 40, carbon dioxide co2: 39, neural network ann: 38, artificial neural networks: 36, random forest rf: 35, square error rmse: 35, convolutional neural network: 34, absolute error mae: 31, deep learning based: 30, global climate change: 30, machine learning based: 29, support vector regression: 29, air quality index: 28, using deep learning: 28, extreme gradient boosting: 27, carbon dioxide emission: 26, global warming potential: 24, sustainable development goals: 24, extreme learning machine: 23, carbon emission reduction: 21, machine learning approaches: 21, absolute percentage error: 20, covid 19 pandemic: 20, deep neural network: 20, greenhouse gas ghg: 20, using artificial intelligence: 20, renewable energy sources: 19, convolutional neural networks: 18, gross domestic product: 18, climate change mitigation: 17, carbon price prediction: 16, gas ghg emissions: 16, low carbon economic: 16, municipal solid waste: 16, neural network cnn: 16, artificial intelligence based: 15, dioxide co2 emissions: 15, machine learning algorithm: 15, multiple linear regression: 15, real time monitoring: 15, solid waste management: 15, vector machine svm: 15, air quality prediction: 14, beijing tianjin hebei: 14, particle swarm optimization: 14, quality index aqi: 14, air quality monitoring: 13, fold cross validation: 13, formula presented emissions: 13, gradient boosting machine: 13, particulate matter pm: 13, aerosol optical depth: 12, artificial intelligence techniques: 12, deep learning approach: 12, machine learning technique: 12, multi objective optimization: 12, random forest algorithm: 12, supervised machine learning: 12, vector regression svr: 12, based machine learning: 11, carbon economic development: 11, deep learning dl: 11, empirical mode decomposition: 11, fine particulate matter: 11, percentage error mape: 11, radial basis function: 11, response surface methodology: 11, self organizing map: 11, air pollution levels: 10, bp neural network: 10, carbon dioxide capture: 10, co2 emissions prediction: 10, deep learning algorithms: 10, different machine learning: 10, land use regression: 10, low carbon economy: 10, near real time: 10, reduce carbon emissions: 10, self powered sensors: 10, square error mse: 10, tianjin hebei region: 10, air pollution monitoring: 9, climate change scenarios: 9, combat climate change: 9, deep learning framework: 9, domestic product gdp: 9, hybrid deep learning: 9, life cycle assessment: 9, nitrogen dioxide no2: 9[('model', 1175), ('data', 1035), ('machine', 904), ('carbon', 867), ('emissions', 861), ('learning', 829), ('energy', 799), ('%', 734), ('models', 701), ('air', 672), ('study', 610), ('climate', 598), ('results', 554), ('prediction', 525), ('emission', 518), ('co2', 495), ('waste', 488), ('environment', 467), ('pollution', 465), ('change', 455), ('development', 449), ('system', 448), ('time', 418), ('analysis', 397), ('performance', 394), ('quality', 383), ('network', 344), ('method', 340), ('paper', 335), ('approach', 310), ('accuracy', 300), ('gas', 291), ('process', 281), ('consumption', 280), ('research', 279), ('intelligence', 274), ('error', 269), ('methods', 259), ('regression', 252), ('efficiency', 243), ('production', 230), ('power', 225), ('health', 225), ('impact', 223), ('techniques', 220), ('management', 219), ('factors', 214), ('fuel', 212), ('algorithms', 207), ('reduction', 204), ('dioxide', 204), ('optimization', 201), ('use', 197), ('-', 196), ('parameters', 196), ('warming', 193), ('level', 191), ('materials', 183), ('oil', 182), ('conditions', 181), ('work', 180), ('sustainability', 178), ('effects', 176), ('sources', 175), ('monitoring', 174), ('temperature', 171), ('systems', 170), ('design', 170), ('growth', 169), ('concentration', 168), ('technology', 167), ('ozone', 164), ('concentrations', 164), ('strength', 162), ('co', 162), ('term', 161), ('decision', 161), ('classification', 158), ('values', 157), ('cities', 157), ('greenhouse', 154), ('forecasting', 154), ('forest', 153), ('networks', 151), ('application', 151), ('potential', 150), ('framework', 150), ('variables', 149), ('cost', 149), ('properties', 148), ('countries', 145), ('effect', 143), ('pollutants', 142), ('information', 140), ('value', 137), ('concrete', 137), ('world', 134), ('input', 130), ('water', 122), ('years', 119)][('use', 1417), ('base', 969), ('predict', 536), ('propose', 448), ('develop', 429), ('show', 426), ('learn', 372), ('provide', 352), ('have', 346), ('reduce', 316), ('increase', 283), ('improve', 280), ('compare', 268), ('include', 241), ('apply', 234), ('achieve', 220), ('make', 219), ('present', 184), ('find', 176), ('estimate', 172), ('obtain', 170), ('consider', 168), ('evaluate', 160), ('identify', 157), ('require', 151), ('drive', 141), ('produce', 139), ('perform', 138), ('affect', 135), ('become', 134), ('demonstrate', 133), ('forecast', 133), ('combine', 131), ('help', 131), ('generate', 124), ('indicate', 122), ('relate', 122), ('be', 119), ('lead', 118), ('employ', 118), ('analyze', 118), ('investigate', 116), ('enhance', 116), ('contribute', 116), ('utilize', 115), ('train', 111), ('implement', 110), ('support', 109), ('cause', 109), ('optimize', 108), ('integrate', 107), ('exist', 105), ('assess', 105), ('determine', 104), ('focus', 102), ('build', 102), ('need', 100), ('result', 99), ('model', 98), ('take', 97), ('collect', 96), ('reveal', 95), ('give', 95), ('aim', 93), ('monitor', 92), ('design', 91), ('conduct', 89), ('explore', 88), ('mean', 87), ('study', 86), ('address', 84), ('suggest', 83), ('select', 83), ('enable', 81), ('discuss', 79), ('promote', 79), ('boost', 77), ('introduce', 76), ('follow', 75), ('decrease', 73), ('measure', 73), ('influence', 71), ('understand', 70), ('observe', 68), ('mitigate', 68), ('create', 68), ('calculate', 67), ('associate', 66), ('play', 65), ('establish', 64), ('validate', 64), ('highlight', 63), ('allow', 63), ('control', 62), ('ensure', 59), ('capture', 59), ('classify', 59), ('construct', 57), ('test', 56), ('contain', 56)][('environmental', 511), ('global', 437), ('sustainable', 411), ('high', 382), ('artificial', 368), ('neural', 367), ('such', 359), ('-', 358), ('deep', 347), ('different', 344), ('economic', 299), ('other', 241), ('new', 230), ('important', 205), ('low', 204), ('various', 197), ('human', 187), ('green', 180), ('long', 176), ('significant', 173), ('real', 167), ('urban', 166), ('effective', 152), ('random', 152), ('accurate', 150), ('future', 147), ('industrial', 142), ('large', 141), ('experimental', 138), ('efficient', 134), ('renewable', 133), ('higher', 126), ('natural', 126), ('short', 126), ('novel', 125), ('more', 119), ('current', 116), ('multi', 115), ('many', 113), ('meteorological', 112), ('better', 110), ('major', 110), ('main', 110), ('atmospheric', 109), ('recent', 104), ('key', 104), ('non', 102), ('best', 102), ('optimal', 102), ('spatial', 101), ('several', 100), ('compressive', 100), ('predictive', 99), ('smart', 98), ('statistical', 94), ('concrete', 93), ('co2', 92), ('absolute', 90), ('first', 89), ('average', 89), ('total', 88), ('square', 87), ('multiple', 87), ('potential', 86), ('comprehensive', 84), ('hybrid', 81), ('critical', 80), ('linear', 80), ('intelligent', 80), ('complex', 79), ('extreme', 77), ('solid', 76), ('ensemble', 73), ('available', 72), ('traditional', 72), ('regional', 72), ('computational', 71), ('specific', 71), ('most', 70), ('empirical', 69), ('mean', 69), ('lower', 69), ('overall', 67), ('present', 67), ('highest', 66), ('local', 66), ('pollutant', 66), ('ecological', 65), ('negative', 64), ('temporal', 64), ('possible', 64), ('mechanical', 64), ('conventional', 63), ('daily', 63), ('single', 63), ('essential', 61), ('physical', 59), ('great', 59), ('good', 58), ('social', 57)]{'air': 5, 'carbon': 5, 'co2': 3, 'climate': 3, 'industrial': 3, 'renewable': 2, 'global': 2, 'ai': 2, 'various': 2, 'meteorology': 2, 'economic': 2, 'income': 2, 'covid': 2, 'human': 2, 'brickfields': 2, 'biomass': 1, 'changes': 1, 'plastic': 1, 'gas': 1, 'indias': 1, 'transportation': 1, 'different': 1, 'dust': 1, 'lockdown': 1, 'ict': 1, 'mps': 1, 'residents': 1, 'microplastics': 1, 'computational': 1, 'fixed': 1, 'environmental': 1, 'certain': 1, 'energy': 1, 'r': 1, 'innovation': 1, 'regional': 1, 'inequality': 1, 'excessive': 1, 'silicon': 1, 'digital': 1, 'eggshell': 1, 'leachate': 1, 'natural': 1, 'using': 1, 'financial': 1, 'materials': 1, 'genetic': 1, 'cement': 1, 'ml': 1, 'determinants': 1, 'land': 1, 'short': 1, 'oil': 1, 'dms': 1, 'pricing': 1, 'rising': 1, 'local': 1, 'haze': 1, 'industrialization': 1}{'renewable': 2, 'green': 2, 'specific': 1, 'electric': 1, 'policy': 1, 'climatic': 1, 'sulfidation': 1, 'meteorology': 1, 'plants': 1, 'conflicts': 1, 'force': 1, 'silicon': 1, 'cities': 1, 'ai': 1, 'mechanistic': 1, 'spe': 1}[('machine learning models air pollution', 0.6681), ('machine learning climate change', 0.6614), ('forecasting carbon emissions', 0.629), ('accurate carbon emission forecasting', 0.6194), ('accurate pollutant prediction', 0.6127), ('carbon emission prediction', 0.6113), ('future carbon emission prediction research', 0.6101), ('carbon emissions prediction base', 0.6077), ('carbon emissions forecasting', 0.6054), ('machine learning algorithms carbon dioxide', 0.6047), ('pollutant prediction', 0.6014), ('carbon emissions prediction model', 0.5997), ('emissions prediction', 0.5991), ('co2 emissions prediction methods', 0.5989), ('accurate carbon emission prediction models', 0.5987), ('co2 emissions prediction model', 0.5979), ('artificial intelligence algorithms greenhouse gases', 0.597), ('co2 emissions prediction', 0.5955), ('co2 emission forecasting', 0.5905), ('carbon emission prediction model', 0.5887), ('carbon dioxide emissions forecasting', 0.5824), ('air pollution prediction', 0.5823), ('carbon dioxide emission forecasting', 0.5793), ('accurate co2 emissions forecasting model', 0.5792), ('environmental prediction', 0.5748), ('hybrid deep learning architecture air pollution prediction', 0.5743), ('probabilistic carbon price forecasting carbon price prediction', 0.5722), ('co2 emission prediction model', 0.5717), ('carbon emissions data analysis', 0.5714), ('emission forecasting', 0.5688), ('greenhouse gas emission prediction', 0.5687), ('carbon emission forecasting models', 0.5683), ('short term carbon dioxide emissions forecasting', 0.568), ('multivariate time series co2 emissions forecasting challenges', 0.5642), ('noticeable co2 emission forecasting accuracy', 0.5622), ('air pollution prediction model', 0.5566), ('carbon dioxide emission prediction', 0.5558), ('artificial intelligent techniques air pollution', 0.5505), ('sustainable environment prediction', 0.5504), ('ghg emissions prediction', 0.5475), ('pollution forecasting', 0.5464), ('stable carbon emissions forecasting', 0.5437), ('environmental forecasting', 0.5436), ('effective air quality prediction', 0.5428), ('carbon market forecasting', 0.5419), ('carbon emissions forecasting accuracy', 0.5406), ('daily carbon emission prediction model', 0.5383), ('climate change prediction challenging', 0.5377), ('accurate carbon price forecasting', 0.535), ('daily co2 emissions prediction', 0.5341)]
3
16740.082risk_management1_water_flood_decision_management['water', 'flood', 'decision', 'management', 'climate', 'support', 'risk', 'change', 'based', 'decision support', 'climate change', 'areas', 'use', 'information', 'development', 'land', 'systems', 'using', 'assessment', 'dss', 'learning', 'urban', 'used', 'paper', 'resources', 'disaster', 'planning', 'flooding', 'natural', 'machine'][('hydroclimatology', 0.4695), ('floodplain', 0.4419), ('floodplains', 0.4335), ('geostatistics', 0.4318), ('hydrology', 0.4067), ('hydrological', 0.4051), ('hydrogeology', 0.3884), ('flooding', 0.3839), ('hydroclimatic', 0.3783), ('hydrologically', 0.3711), ('flood', 0.3698), ('hydrologic', 0.3644), ('floods', 0.3588), ('climatological', 0.3515), ('flooded', 0.3381), ('dams', 0.3368), ('geoengineering', 0.3361), ('geostatistical', 0.3358), ('climatology', 0.3328), ('catchments', 0.3328), ('floodwaters', 0.3314), ('bioclimatic', 0.3304), ('geosciences', 0.329), ('floodwater', 0.3284), ('rainfalls', 0.3283), ('hydroclimate', 0.3267), ('biogeographic', 0.3234), ('hydrograph', 0.3232), ('droughts', 0.3221), ('geoinformatics', 0.321), ('floodnet', 0.3186), ('runoff', 0.3172), ('biogeography', 0.3139), ('geomorphology', 0.3133), ('irrigations', 0.3126), ('modelling', 0.3125), ('ecologic', 0.3116), ('reservoirs', 0.3098), ('forecasting', 0.3091), ('irrigation', 0.3083), ('levees', 0.3082), ('geohydrological', 0.3071), ('topography', 0.305), ('geoscience', 0.3039), ('catchment', 0.3021), ('hydrographical', 0.2993), ('runoffs', 0.2984), ('climates', 0.2984), ('hydrologists', 0.2954), ('hydrogeological', 0.2951)][('hydrological modelling', 0.6344), ('hydrological modeling', 0.6329), ('hydrology modeling', 0.6226), ('floodplain mapping', 0.5989), ('flood modelling', 0.5945), ('flood prediction', 0.582), ('flood forecasting', 0.5781), ('flood modeling', 0.5774), ('flood mapping', 0.5745), ('predicting floods', 0.5732), ('floods prediction', 0.5727), ('forecasting flood', 0.5701), ('predicting flood', 0.569), ('flood assessment', 0.5673), ('watershed modelling', 0.567), ('flooding prediction', 0.5662), ('forecasting floods', 0.5658), ('forecasting flooding', 0.5655), ('hydrological forecasting', 0.5624), ('estimating flood', 0.5608), ('predict floods', 0.5571), ('predicting flooding', 0.5546), ('flood map', 0.5534), ('floodplain management', 0.5527), ('modeling flood', 0.5493), ('flood maps', 0.5477), ('predict flood', 0.5468), ('mapping floods', 0.5465), ('flood predict', 0.5464), ('hydrological simulations', 0.5432), ('flood predictive', 0.5431), ('catchment modelling', 0.5413), ('hydroclimate modeling', 0.5383), ('hydrological dynamics', 0.535), ('mapping flood', 0.534), ('watershed modeling', 0.534), ('predicts flooding', 0.5336), ('predict flooding', 0.5333), ('flood planning', 0.5295), ('scenarios hydrological', 0.5288), ('forecast floods', 0.526), ('flooding climate', 0.5251), ('floods analyzed', 0.525), ('forecasting water', 0.5249), ('floods adapting', 0.5242), ('hydroclimatology driven', 0.524), ('scenarios hydrologic', 0.5232), ('mapping flooding', 0.522), ('prediction floods', 0.5192), ('flood scenarios', 0.5172)]climate change: 593, decision support: 386, machine learning: 358, land use: 169, decision making: 167, water resources: 164, artificial intelligence: 120, flood risk: 110, real time: 102, deep learning: 100, water supply: 90, decision makers: 88, remote sensing: 87, water management: 81, random forest: 77, river basin: 76, flood susceptibility: 74, natural disasters: 74, sustainable development: 73, support systems: 68, water quality: 65, neural network: 62, long term: 60, risk assessment: 59, learning algorithms: 57, water resource: 54, socio economic: 53, landslide susceptibility: 51, urban flood: 49, risk management: 47, resources management: 46, water level: 46, global climate: 44, global warming: 44, support vector: 44, resource management: 43, urban areas: 42, large scale: 41, flood events: 40, paper presents: 40, multi criteria: 39, using machine: 39, geographic information: 37, early warning: 35, land cover: 35, recent years: 35, surface water: 35, water demand: 35, gis based: 34, vector machine: 34, change scenarios: 33, flash flood: 33, sea level: 33, spatial decision: 33, learning techniques: 32, neural networks: 32, flood forecasting: 31, natural hazards: 31, coastal areas: 30, flood disaster: 30, future climate: 30, intelligence ai: 30, artificial neural: 29, climate changes: 29, extreme weather: 29, high resolution: 29, susceptibility mapping: 29, web based: 29, criteria decision: 27, forest rf: 27, learning ml: 27, risk reduction: 27, based decision: 26, disaster risk: 26, emergency management: 26, sustainable management: 26, urban water: 26, level rise: 25, making process: 25, natural disaster: 25, weather conditions: 25, change impacts: 24, developing countries: 24, disaster management: 24, gradient boosting: 24, sustainable water: 24, debris flow: 23, decision tree: 23, end users: 23, hierarchy process: 23, learning based: 22, water related: 22, cultural heritage: 21, extreme events: 21, flood detection: 21, multi objective: 21, support decision: 21, use changes: 21, water use: 21, adaptation measures: 20decision support systems: 68, machine learning algorithms: 48, water resources management: 43, global climate change: 37, using machine learning: 37, support vector machine: 34, climate change scenarios: 33, artificial intelligence ai: 30, spatial decision support: 30, water resource management: 28, machine learning ml: 27, machine learning techniques: 27, random forest rf: 27, multi criteria decision: 25, sea level rise: 25, climate change impacts: 24, decision making process: 24, based decision support: 23, artificial neural network: 20, land use changes: 20, vector machine svm: 20, land use planning: 19, decision support tools: 18, land use change: 18, synthetic aperture radar: 18, land use land: 17, flood risk assessment: 16, use land cover: 16, analytic hierarchy process: 14, future climate change: 14, receiver operating characteristic: 14, sustainable development goals: 14, climate change adaptation: 13, disaster risk reduction: 13, flood risk management: 13, machine learning approach: 13, criteria decision making: 12, decision support tool: 12, extreme gradient boosting: 12, water resources planning: 12, water supply systems: 12, aperture radar sar: 11, decision making processes: 11, extreme weather events: 11, machine learning approaches: 11, machine learning based: 11, regional risk assessment: 11, support decision making: 11, agricultural land use: 10, deep learning based: 10, flood prone areas: 10, flood susceptibility mapping: 10, hierarchy process ahp: 10, sustainable water resources: 10, analytical hierarchy process: 9, artificial neural networks: 9, combining double low: 9, convolutional neural network: 9, convolutional neural networks: 9, deep neural network: 9, development goals sdgs: 9, double low line: 9, future flood risk: 9, information systems gis: 9, integrated water resources: 9, support systems dss: 9, using artificial intelligence: 9, agricultural heritage digitalized: 8, best management practices: 8, climate change effects: 8, climate change impact: 8, gis based decision: 8, gradient boosting xgboost: 8, heritage digitalized conservation: 8, landslide susceptibility assessment: 8, machine learning algorithm: 8, managed aquifer recharge: 8, operating characteristic roc: 8, particle swarm optimization: 8, representative concentration pathway: 8, science business media: 8, springer science business: 8, support decision makers: 8, urban flood risk: 8, using deep learning: 8, coastal zone management: 7, deep learning algorithm: 7, deep learning algorithms: 7, different machine learning: 7, extreme weather conditions: 7, flash flood susceptibility: 7, geographic information systems: 7, integrated water resource: 7, landslide rainfall threshold: 7, landslide susceptibility mapping: 7, management decision support: 7, near real time: 7, radial basis function: 7, socio economic development: 7, square error rmse: 7[('water', 1439), ('data', 939), ('climate', 929), ('flood', 885), ('system', 796), ('management', 758), ('decision', 753), ('change', 683), ('model', 663), ('study', 527), ('risk', 481), ('support', 457), ('models', 449), ('development', 411), ('results', 405), ('machine', 401), ('information', 400), ('areas', 392), ('systems', 382), ('land', 380), ('use', 372), ('%', 366), ('analysis', 364), ('learning', 344), ('paper', 329), ('assessment', 308), ('approach', 304), ('research', 280), ('resources', 278), ('framework', 266), ('area', 264), ('time', 262), ('planning', 226), ('environment', 223), ('scenarios', 222), ('dss', 219), ('prediction', 212), ('method', 202), ('process', 202), ('methods', 199), ('disaster', 196), ('level', 187), ('susceptibility', 182), ('flooding', 182), ('events', 180), ('network', 177), ('floods', 176), ('rainfall', 176), ('impact', 173), ('factors', 172), ('landslide', 168), ('impacts', 166), ('disasters', 163), ('changes', 161), ('monitoring', 160), ('tools', 160), ('knowledge', 160), ('evaluation', 157), ('conditions', 157), ('case', 156), ('river', 156), ('weather', 156), ('application', 155), ('performance', 155), ('infrastructure', 155), ('quality', 151), ('techniques', 146), ('damage', 145), ('-', 145), ('resilience', 142), ('intelligence', 141), ('scale', 137), ('project', 136), ('tool', 135), ('region', 129), ('supply', 129), ('basin', 128), ('technology', 127), ('gis', 126), ('detection', 126), ('years', 125), ('design', 125), ('strategies', 124), ('forest', 124), ('technologies', 122), ('effects', 117), ('measures', 115), ('networks', 114), ('adaptation', 114), ('demand', 113), ('methodology', 112), ('accuracy', 112), ('algorithms', 111), ('resource', 110), ('studies', 110), ('regions', 109), ('world', 107), ('order', 107), ('stakeholders', 107), ('simulation', 105)][('use', 1002), ('base', 719), ('develop', 413), ('provide', 363), ('propose', 317), ('increase', 275), ('include', 258), ('make', 236), ('show', 234), ('integrate', 228), ('have', 222), ('predict', 207), ('support', 205), ('consider', 196), ('learn', 193), ('present', 189), ('apply', 186), ('identify', 183), ('improve', 175), ('evaluate', 166), ('assess', 154), ('relate', 147), ('cause', 143), ('reduce', 124), ('require', 123), ('achieve', 119), ('affect', 117), ('address', 115), ('build', 112), ('allow', 109), ('demonstrate', 108), ('implement', 107), ('combine', 103), ('analyze', 101), ('exist', 100), ('compare', 99), ('aim', 98), ('take', 95), ('help', 95), ('determine', 94), ('become', 94), ('need', 93), ('focus', 93), ('indicate', 92), ('enhance', 92), ('result', 90), ('perform', 90), ('design', 90), ('obtain', 88), ('lead', 88), ('select', 84), ('manage', 83), ('be', 82), ('enable', 82), ('establish', 81), ('drive', 79), ('find', 78), ('generate', 78), ('describe', 77), ('represent', 77), ('occur', 77), ('model', 74), ('follow', 74), ('change', 73), ('give', 73), ('estimate', 71), ('produce', 70), ('face', 69), ('discuss', 67), ('expect', 67), ('contribute', 66), ('involve', 65), ('collect', 65), ('conduct', 64), ('detect', 63), ('create', 63), ('simulate', 62), ('utilize', 61), ('monitor', 61), ('mitigate', 58), ('investigate', 57), ('test', 56), ('associate', 56), ('employ', 55), ('ensure', 54), ('optimize', 54), ('classify', 54), ('understand', 50), ('introduce', 50), ('accord', 49), ('flood', 48), ('grow', 48), ('adopt', 47), ('plan', 47), ('facilitate', 46), ('induce', 46), ('suggest', 46), ('locate', 45), ('construct', 44), ('incorporate', 44)][('-', 343), ('urban', 325), ('such', 302), ('sustainable', 301), ('environmental', 300), ('different', 275), ('high', 271), ('natural', 251), ('economic', 237), ('future', 210), ('global', 208), ('spatial', 195), ('new', 188), ('coastal', 184), ('multi', 180), ('other', 173), ('artificial', 158), ('real', 147), ('deep', 146), ('various', 138), ('social', 138), ('agricultural', 133), ('current', 127), ('human', 123), ('effective', 123), ('important', 122), ('extreme', 117), ('large', 115), ('local', 114), ('several', 110), ('many', 103), ('complex', 103), ('regional', 102), ('significant', 100), ('remote', 100), ('low', 98), ('available', 95), ('potential', 95), ('neural', 94), ('major', 91), ('recent', 90), ('main', 89), ('critical', 89), ('ecological', 88), ('hydrological', 87), ('best', 85), ('random', 85), ('smart', 82), ('multiple', 81), ('key', 81), ('specific', 76), ('long', 76), ('efficient', 72), ('optimal', 72), ('fuzzy', 68), ('suitable', 67), ('more', 66), ('novel', 66), ('public', 66), ('national', 65), ('possible', 65), ('non', 64), ('accurate', 63), ('essential', 63), ('geographic', 63), ('better', 62), ('early', 61), ('rapid', 60), ('present', 59), ('first', 58), ('digital', 57), ('big', 57), ('total', 55), ('useful', 54), ('dynamic', 53), ('operational', 53), ('climatic', 52), ('scientific', 52), ('historical', 52), ('reliable', 52), ('temporal', 52), ('open', 52), ('necessary', 52), ('great', 51), ('appropriate', 51), ('statistical', 49), ('physical', 48), ('robust', 47), ('comprehensive', 47), ('particular', 46), ('cultural', 46), ('overall', 45), ('relevant', 45), ('highest', 44), ('higher', 44), ('geospatial', 44), ('vulnerable', 44), ('good', 44), ('intelligent', 43), ('severe', 42)]{'climate': 18, 'flood': 5, 'natural': 2, 'urban': 2, 'various': 2, 'heips': 2, 'temperature': 2, 'flooding': 2, 'higher': 1, 'agriculture': 1, 'water': 1, 'unconventional': 1, 'applying': 1, 'anthropogenic': 1, 'livestock': 1, 'hurricanes': 1, 'balancing': 1, 'global': 1, 'different': 1, 'future': 1, 'seasonal': 1, 'computational': 1, 'hazards': 1, 'floods': 1, 'high': 1, 'losses': 1, 'technology': 1, 'weather': 1, 'agricultural': 1, 'measures': 1, 'ice': 1, 'point': 1}{'state': 1, 'peoples': 1, 'spatial': 1, 'dss': 1, 'experts': 1, 'hydrological': 1, 'decision': 1, 'smart': 1, 'land': 1, 'cross': 1}[('flood water level prediction models', 0.6452), ('flood assessment model', 0.6404), ('hydrological modelling', 0.6344), ('hydrological modeling', 0.6329), ('flooding prediction model', 0.6195), ('flood prediction model', 0.6187), ('flood water level forecasting', 0.6076), ('agricultural flood assessment', 0.6032), ('flood prediction models', 0.596), ('flood risk assessment', 0.5954), ('analyses flood risks', 0.5951), ('flood modelling', 0.5945), ('large scale flood risk analyses', 0.5931), ('watershed modelling system', 0.5928), ('flood risk prediction', 0.5918), ('future flood risk mapping', 0.5916), ('accurate flood model forecasting', 0.5873), ('mapping flood susceptibility', 0.5862), ('flood susceptibility prediction', 0.5861), ('stormwater flood forecasting', 0.5855), ('pluvial flood risk mapping', 0.5849), ('flood forecasting flooding', 0.5838), ('flood risk models', 0.5822), ('flood prediction', 0.582), ('flood risk assessment map', 0.5802), ('flood forecasting', 0.5781), ('pluvial flood risk prediction', 0.5775), ('flood risk management information system', 0.5774), ('global flood risk modeling framework', 0.5774), ('flood modeling', 0.5774), ('flood risk dynamics', 0.575), ('flood prediction system', 0.5749), ('flood mapping', 0.5745), ('mapping flood hazards', 0.5741), ('flood map generation', 0.5736), ('physical hydrology modeling', 0.5734), ('most flood risk analysis', 0.5716), ('regional flood susceptibility mapping', 0.5716), ('flood severity prediction', 0.5711), ('flood forecasting models', 0.5709), ('flood trend studies', 0.5686), ('flood condition maps', 0.5681), ('flood assessment', 0.5673), ('flood hazard assessment', 0.5672), ('flood risk classification', 0.5671), ('intelligent flood models', 0.5665), ('pluvial flood prediction', 0.5663), ('stormwater flood forecasting system', 0.5663), ('forecasting floods', 0.5658), ('hydrological models', 0.5651)]
4
25950.073energy_power_electricity2_energy_power_solar_wind['energy', 'power', 'solar', 'wind', 'renewable', 'electricity', 'pv', 'based', 'renewable energy', 'generation', 'learning', 'systems', 'consumption', 'using', 'forecasting', 'grid', 'demand', 'photovoltaic', 'proposed', 'load', 'smart', 'optimization', 'electric', 'paper', 'sources', 'machine', 'prediction', 'control', 'deep', 'used'][('timeseries', 0.4339), ('smartgenerators', 0.3673), ('boosting', 0.3645), ('lstms', 0.3561), ('lstm', 0.3539), ('forecasting', 0.3486), ('classifiers', 0.3384), ('svms', 0.3378), ('predicting', 0.3309), ('svm', 0.3289), ('energyhubs', 0.3281), ('kriging', 0.3278), ('sensors', 0.3237), ('detecting', 0.3225), ('ecognition', 0.3192), ('classifier', 0.3136), ('clstm', 0.3091), ('detect', 0.3065), ('energyplus', 0.3043), ('forecasts', 0.3029), ('predictive', 0.3029), ('autoregressive', 0.2999), ('sensing', 0.2937), ('electrify', 0.2921), ('hydroelectricity', 0.2879), ('hydropower', 0.2835), ('timelags', 0.2799), ('adaboost', 0.279), ('hydrogen', 0.2788), ('smartgrids', 0.2772), ('prediction', 0.2769), ('autoencoders', 0.2769), ('indicators', 0.2762), ('clusters', 0.2751), ('nonstationary', 0.2739), ('backpropagation', 0.2725), ('regularization', 0.2714), ('turbines', 0.2708), ('deepcomp', 0.2699), ('classifying', 0.2693), ('clustering', 0.2686), ('autoencoder', 0.2686), ('segmentation', 0.2659), ('detection', 0.2653), ('kalman', 0.2625), ('forecaster', 0.2616), ('monitoring', 0.261), ('bioenergy', 0.2608), ('forecast', 0.2604), ('dlstm', 0.2602)][('energy forecasting', 0.5673), ('forecasting energy', 0.532), ('predicting changes', 0.5258), ('detect change', 0.5187), ('forecasting energetics', 0.5177), ('energy trending', 0.5074), ('energy forecasts', 0.5042), ('forecasts energy', 0.5008), ('energy disaggregation', 0.4986), ('forecast energy', 0.4906), ('change detection', 0.4795), ('time series', 0.4619), ('intelligent energy', 0.4601), ('energy monitoring', 0.4546), ('sustainable predictive', 0.4487), ('detection change', 0.4484), ('generation forecasting', 0.4479), ('automated energy', 0.4451), ('predictive energy', 0.4419), ('energy detection', 0.441), ('detect gradual', 0.4356), ('energy indicators', 0.4355), ('electricity forecasting', 0.4354), ('smart energy', 0.4347), ('timeseries', 0.4339), ('trend energy', 0.4308), ('technologies predicting', 0.4304), ('predictions sensors', 0.4287), ('state prediction', 0.4283), ('identify changes', 0.4259), ('intelligent thermodynamic', 0.4245), ('predicts energy', 0.4239), ('advanced forecasting', 0.4236), ('learning forecast', 0.4217), ('energy smart', 0.4213), ('temporal ensemble', 0.4212), ('prediction detection', 0.4211), ('dataset electricity', 0.4201), ('energy intelligent', 0.4187), ('energy hotspots', 0.418), ('power forecasting', 0.4176), ('energy prediction', 0.4171), ('emission smart', 0.4171), ('ml drift', 0.4166), ('predicting energy', 0.4163), ('emissions forecasting', 0.4156), ('predict dynamic', 0.413), ('intelligent forecasting', 0.4111), ('electricity prediction', 0.4104), ('influential sensors', 0.4089)]machine learning: 370, renewable energy: 353, climate change: 255, deep learning: 189, energy consumption: 181, artificial intelligence: 171, wind power: 165, neural network: 155, power generation: 155, global warming: 151, solar energy: 142, energy sources: 135, energy management: 119, short term: 116, energy systems: 108, wind speed: 106, reinforcement learning: 93, neural networks: 90, time series: 80, wind energy: 77, decision support: 76, artificial neural: 72, smart grid: 69, electric vehicles: 67, electricity consumption: 67, term memory: 67, energy resources: 66, solar power: 66, fossil fuels: 62, energy production: 61, sustainable energy: 59, long term: 58, real time: 58, deep reinforcement: 57, energy demand: 56, learning based: 55, sustainable development: 55, carbon dioxide: 54, power systems: 51, solar radiation: 51, decision making: 50, learning algorithms: 50, learning techniques: 50, energy generation: 49, photovoltaic pv: 49, energy efficiency: 47, greenhouse gas: 44, paper presents: 43, power grid: 43, wind turbines: 43, solar pv: 42, multi objective: 41, using machine: 40, electric vehicle: 39, pv power: 39, support vector: 39, energy storage: 37, paper proposes: 37, solar photovoltaic: 37, solar irradiance: 36, square error: 36, gas emissions: 35, learning algorithm: 34, pv systems: 34, random forest: 34, energy sector: 33, dioxide emissions: 31, load forecasting: 31, memory lstm: 31, solar panels: 31, wind turbine: 31, genetic algorithm: 30, intelligence ai: 30, power consumption: 30, electricity demand: 29, fossil fuel: 29, large scale: 29, power plants: 29, fault diagnosis: 28, learning ml: 28, power plant: 28, recent years: 28, distributed energy: 27, real world: 27, electric power: 26, electrical energy: 26, energy saving: 26, smart city: 26, deep neural: 25, energy forecasting: 25, grid connected: 25, clean energy: 24, energy source: 24, energy usage: 24, feature selection: 24, maximum power: 24, convolutional neural: 23, demand response: 23, learning approach: 23, photovoltaic power: 23renewable energy sources: 91, short term memory: 67, deep reinforcement learning: 57, artificial neural network: 46, machine learning algorithms: 41, using machine learning: 40, machine learning techniques: 36, wind power generation: 36, greenhouse gas emissions: 34, carbon dioxide emissions: 31, term memory lstm: 31, artificial intelligence ai: 30, machine learning ml: 28, artificial neural networks: 26, machine learning based: 25, renewable energy resources: 24, neural network ann: 21, renewable energy systems: 21, convolutional neural network: 20, machine learning algorithm: 19, absolute percentage error: 18, electric vehicle charging: 18, gated recurrent unit: 17, deep neural networks: 16, support vector machine: 16, hybrid renewable energy: 15, multi objective optimization: 15, renewable energy generation: 15, based decision support: 14, deep learning based: 14, distributed energy resources: 14, maximum power point: 14, particle swarm optimization: 14, sustainable development goals: 14, global climate change: 13, percentage error mape: 13, recurrent neural network: 13, using artificial intelligence: 13, wind power forecasting: 13, ant colony optimization: 12, artificial intelligence techniques: 12, carbon dioxide emission: 12, deep deterministic policy: 12, deterministic policy gradient: 12, energy management systems: 12, machine learning technique: 12, reinforcement learning drl: 12, square error rmse: 12, wind speed prediction: 12, global warming potential: 11, neural network cnn: 11, power point tracking: 11, reinforcement learning based: 11, renewable energy technologies: 11, short term wind: 11, solar photovoltaic pv: 11, support vector regression: 11, artificial intelligence based: 10, based deep learning: 10, decision support tool: 10, energy management strategy: 10, intrusive load monitoring: 10, mitigate climate change: 10, non intrusive load: 10, pv output power: 10, pv power generation: 10, renewable energy source: 10, solar energy generation: 10, solar power generation: 10, using deep learning: 10, vector machine svm: 10, absolute error mae: 9, deep learning dl: 9, electric vehicles evs: 9, energy storage systems: 9, fossil fuel based: 9, lithium ion battery: 9, photovoltaic pv systems: 9, recurrent unit gru: 9, reduce greenhouse gas: 9, short term load: 9, solar power plant: 9, support vector machines: 9, wind speed forecasting: 9, climate change impacts: 8, climate change mitigation: 8, deep learning techniques: 8, deep neural network: 8, different machine learning: 8, electric vehicles ev: 8, energy consumption prediction: 8, load monitoring nilm: 8, machine learning approach: 8, machine learning approaches: 8, neural networks ann: 8, nonintrusive load monitoring: 8, pv energy production: 8, recurrent neural networks: 8, reduce global warming: 8, using artificial neural: 8[('energy', 2270), ('power', 1100), ('system', 838), ('model', 654), ('data', 643), ('wind', 579), ('learning', 545), ('systems', 461), ('machine', 416), ('climate', 385), ('models', 383), ('results', 376), ('electricity', 369), ('consumption', 366), ('generation', 362), ('prediction', 333), ('paper', 325), ('study', 313), ('forecasting', 306), ('performance', 291), ('%', 290), ('change', 289), ('time', 288), ('demand', 288), ('optimization', 245), ('management', 244), ('network', 238), ('sources', 237), ('grid', 233), ('analysis', 225), ('load', 224), ('control', 223), ('development', 220), ('method', 219), ('environment', 218), ('approach', 216), ('decision', 210), ('methods', 207), ('use', 186), ('term', 184), ('techniques', 183), ('intelligence', 181), ('accuracy', 178), ('carbon', 173), ('research', 172), ('cost', 169), ('efficiency', 166), ('production', 164), ('warming', 154), ('error', 151), ('networks', 149), ('problem', 149), ('algorithms', 148), ('operation', 147), ('speed', 141), ('resources', 140), ('emissions', 136), ('temperature', 134), ('technologies', 129), ('process', 126), ('design', 126), ('conditions', 125), ('work', 124), ('information', 123), ('technology', 121), ('world', 119), ('framework', 118), ('battery', 116), ('support', 114), ('gas', 112), ('distribution', 111), ('order', 111), ('output', 111), ('heat', 108), ('impact', 107), ('regression', 107), ('state', 106), ('potential', 104), ('weather', 104), ('strategy', 101), ('parameters', 99), ('simulation', 99), ('application', 97), ('emission', 97), ('vehicles', 96), ('reinforcement', 95), ('storage', 93), ('source', 93), ('challenges', 91), ('fuel', 91), ('case', 90), ('solution', 90), ('-', 89), ('technique', 88), ('building', 86), ('usage', 86), ('sector', 86), ('series', 85), ('supply', 83), ('sustainability', 83)][('use', 1016), ('base', 720), ('propose', 488), ('predict', 246), ('develop', 242), ('reduce', 227), ('increase', 224), ('learn', 223), ('show', 219), ('provide', 214), ('compare', 198), ('have', 195), ('improve', 179), ('make', 167), ('consider', 165), ('present', 154), ('apply', 134), ('generate', 121), ('include', 117), ('integrate', 117), ('obtain', 113), ('require', 110), ('charge', 109), ('become', 103), ('achieve', 102), ('drive', 100), ('find', 96), ('forecast', 93), ('optimize', 92), ('evaluate', 91), ('produce', 89), ('lead', 88), ('demonstrate', 88), ('help', 86), ('analyze', 85), ('design', 85), ('combine', 84), ('identify', 82), ('train', 81), ('estimate', 80), ('need', 79), ('exist', 76), ('distribute', 76), ('solve', 75), ('build', 73), ('enable', 73), ('perform', 72), ('address', 71), ('support', 70), ('relate', 69), ('test', 69), ('give', 69), ('be', 69), ('take', 67), ('implement', 64), ('utilize', 63), ('aim', 61), ('determine', 61), ('investigate', 60), ('collect', 60), ('introduce', 59), ('ensure', 59), ('result', 58), ('focus', 57), ('create', 57), ('contribute', 56), ('grow', 56), ('allow', 56), ('employ', 56), ('conduct', 54), ('accord', 54), ('play', 53), ('cause', 52), ('mean', 52), ('enhance', 51), ('assess', 50), ('model', 49), ('minimize', 49), ('establish', 48), ('validate', 46), ('control', 46), ('affect', 46), ('meet', 45), ('select', 44), ('connect', 44), ('indicate', 43), ('operate', 43), ('mitigate', 42), ('monitor', 42), ('manage', 42), ('carry', 42), ('promote', 41), ('discuss', 41), ('set', 41), ('study', 40), ('overcome', 38), ('depend', 38), ('outperform', 37), ('face', 37), ('examine', 36)][('solar', 579), ('renewable', 481), ('deep', 308), ('global', 282), ('-', 282), ('smart', 275), ('different', 275), ('such', 267), ('sustainable', 267), ('artificial', 266), ('neural', 250), ('environmental', 202), ('electric', 194), ('high', 174), ('new', 172), ('hybrid', 160), ('optimal', 149), ('other', 143), ('long', 139), ('multi', 137), ('short', 133), ('real', 133), ('economic', 131), ('various', 131), ('efficient', 127), ('electrical', 121), ('accurate', 115), ('important', 111), ('future', 110), ('photovoltaic', 109), ('large', 98), ('novel', 96), ('effective', 91), ('low', 90), ('many', 89), ('non', 80), ('current', 79), ('significant', 78), ('best', 78), ('several', 77), ('thermal', 77), ('intelligent', 73), ('multiple', 70), ('conventional', 70), ('better', 69), ('urban', 68), ('complex', 68), ('objective', 67), ('more', 66), ('main', 66), ('residential', 66), ('critical', 65), ('recent', 64), ('available', 59), ('present', 56), ('key', 55), ('major', 55), ('green', 55), ('predictive', 54), ('reliable', 54), ('maximum', 54), ('random', 53), ('potential', 53), ('statistical', 53), ('total', 52), ('essential', 52), ('traditional', 52), ('local', 52), ('computational', 51), ('higher', 50), ('fuzzy', 50), ('average', 49), ('experimental', 49), ('clean', 49), ('square', 48), ('fossil', 48), ('meteorological', 47), ('technical', 46), ('single', 46), ('necessary', 45), ('promising', 45), ('specific', 44), ('dynamic', 44), ('first', 44), ('industrial', 44), ('able', 44), ('daily', 43), ('friendly', 43), ('linear', 42), ('absolute', 42), ('human', 41), ('possible', 41), ('advanced', 41), ('small', 41), ('robust', 40), ('crucial', 40), ('overall', 39), ('climatic', 39), ('genetic', 39), ('fast', 38)]{'climate': 5, 'global': 2, 'fossil': 2, 'climatic': 2, 'power': 1, 'refrigeration': 1, 'using': 1, 'renewable': 1, 'greenhouse': 1, 'energy': 1, 'online': 1, 'errors': 1, 'machine': 1, 'users': 1, 'weather': 1, 'overload': 1, 'operation': 1, 'kpis': 1, 'geopolitical': 1, 'ict': 1, 'extreme': 1, 'low': 1, 'artificial': 1, 'advance': 1}{'artificial': 2, 'asymmetric': 2, 'fusion': 1, 'energy': 1, 'machine': 1, 'natural': 1, 'strategic': 1, 'electricity': 1}[('time series change point detection change points', 0.6344), ('energy forecasting', 0.5673), ('reference energy disaggregation dataset', 0.563), ('energy forecasting systems', 0.5527), ('probabilistic energy time series forecasts', 0.5386), ('energy data analysis', 0.5013), ('energy disaggregation', 0.4986), ('energy forecasting techniques', 0.4958), ('renewable energy prediction ability', 0.494), ('machine learning algorithms climate change', 0.4924), ('time series energy consumption data', 0.4904), ('intelligent smart energy', 0.4882), ('consumption energy forecasting', 0.4859), ('energy theft detection', 0.4826), ('energy demand prediction', 0.4822), ('climate change detection', 0.479), ('energy consumption forecasting', 0.474), ('smart energy meters', 0.471), ('energy production prediction', 0.4684), ('tentative energy hotspots', 0.468), ('energy consumption structure forecasting', 0.4656), ('energy demand prediction models', 0.4633), ('time series', 0.4619), ('individual energy usage pattern analysis', 0.4603), ('intelligent energy', 0.4601), ('intelligent energy management strategies', 0.4592), ('energy consumption prediction data', 0.4581), ('smart energy systems', 0.4568), ('indian energy exchange dataset', 0.4556), ('energy monitoring', 0.4546), ('intelligent energy industry', 0.4534), ('accurate renewable energy forecasting', 0.4513), ('wide energy demand prediction', 0.4496), ('energy consumption prediction system', 0.4492), ('generation forecasting', 0.4479), ('energy consumption pattern analysis service', 0.4464), ('smart energy portfolio', 0.446), ('time energy monitoring', 0.4458), ('energy load forecasting', 0.4457), ('machine learning climate change mitigation', 0.4438), ('energy society task force', 0.443), ('energy consumption prediction', 0.4429), ('energy forecasting problems', 0.4429), ('green deep learning climate change', 0.4426), ('good energy prediction', 0.4423), ('accurate power generation prediction', 0.4413), ('energy data', 0.4406), ('energy prediction model', 0.4386), ('deep neural networks climate change', 0.4385), ('intelligent energy management', 0.4371)]
5
31770.022health3_health_disease_climate_risk['health', 'disease', 'climate', 'risk', 'covid', 'covid 19', '19', 'cases', 'learning', 'diseases', 'based', 'transmission', 'incidence', 'machine', 'factors', 'change', 'machine learning', 'patients', 'virus', 'using', 'climate change', 'distribution', 'medical', 'temperature', 'infection', 'prediction', 'vector', 'surveillance', 'areas', 'used'][('climate', 0.353), ('climatology', 0.3524), ('preterm', 0.331), ('climatological', 0.3308), ('regressions', 0.3289), ('glm', 0.325), ('climatic', 0.3178), ('epidemiology', 0.3109), ('temperature', 0.3108), ('climates', 0.3012), ('microclimates', 0.2999), ('climatically', 0.2968), ('bioclimatic', 0.2964), ('forecasts', 0.2952), ('forecaster', 0.2923), ('pregnancy', 0.2918), ('temperatures', 0.2905), ('forecasting', 0.2849), ('geostatistical', 0.2748), ('weather', 0.2737), ('gestational', 0.2701), ('forecast', 0.2682), ('temperate', 0.2656), ('warming', 0.2653), ('epidemiologists', 0.2612), ('socioenvironmental', 0.2591), ('predictors', 0.2589), ('heatstroke', 0.2584), ('epidemiologic', 0.2582), ('neonatal', 0.2573), ('regression', 0.256), ('h1n1', 0.2548), ('predicting', 0.2544), ('warmer', 0.249), ('epidemiological', 0.2462), ('covariates', 0.2426), ('acclimatization', 0.2412), ('socioeconomics', 0.2338), ('birth', 0.226), ('prediction', 0.2257), ('epidemics', 0.2239), ('hyperparameters', 0.2229), ('subtropical', 0.2227), ('fever', 0.2208), ('meteorological', 0.2201), ('correlates', 0.2185), ('predictor', 0.2173), ('anticipatory', 0.2161), ('pollution', 0.2157), ('forecasted', 0.2153)][('temperature preterm', 0.5469), ('temperatures preterm', 0.5418), ('epidemiological climate', 0.5276), ('climatic predictors', 0.5163), ('climate health', 0.5093), ('climatic correlates', 0.4957), ('environmental predictors', 0.4922), ('climate predictors', 0.4766), ('human climate', 0.4605), ('risk preterm', 0.4497), ('climate contributes', 0.4472), ('spatial epidemiology', 0.447), ('climate socioeconomic', 0.4466), ('temperature risk', 0.4432), ('temperatures late', 0.4416), ('climate modeling', 0.4405), ('correlations climate', 0.4402), ('bioclimatic predictor', 0.4388), ('environmental prediction', 0.4379), ('pandemic climate', 0.4356), ('risk temperature', 0.4349), ('predictor climate', 0.4334), ('climate incidence', 0.4332), ('climatic correlated', 0.4323), ('pollution predictors', 0.4322), ('disease climate', 0.432), ('climatic socioeconomic', 0.4299), ('diseases climate', 0.4296), ('predict climate', 0.4278), ('climatic socioenvironmental', 0.426), ('swedish pregnancy', 0.4255), ('climate effects', 0.4249), ('forecasting health', 0.4244), ('fever prediction', 0.4234), ('climate evaluating', 0.4221), ('climate affect', 0.4208), ('anthropogenic climate', 0.4205), ('using climate', 0.4201), ('climate forecasting', 0.4196), ('socioeconomic climatic', 0.4184), ('climate factors', 0.4179), ('temperature impacts', 0.4178), ('temperature mortality', 0.4164), ('climate disease', 0.4158), ('preterm births', 0.415), ('climatic predict', 0.4135), ('climate indicators', 0.4133), ('climate relationships', 0.4131), ('assess climate', 0.4127), ('disease forecasting', 0.4118)]machine learning: 161, climate change: 145, covid 19: 102, artificial intelligence: 59, public health: 45, deep learning: 44, random forest: 41, health care: 30, vector borne: 22, neural network: 21, 19 pandemic: 19, time series: 19, artificial neural: 18, high risk: 18, short term: 18, dengue fever: 17, future climate: 16, global warming: 16, intelligence ai: 16, risk areas: 16, using machine: 16, decision making: 15, dengue cases: 15, heat related: 15, human health: 15, infectious diseases: 15, learning ml: 15, ae aegypti: 14, change scenarios: 14, learning approach: 14, long term: 14, sars cov: 14, support vector: 14, wind speed: 14, environmental factors: 13, learning algorithms: 13, real time: 13, real world: 13, west nile: 13, ae albopictus: 12, ecological niche: 12, infectious disease: 12, learning techniques: 12, vector control: 12, 19 cases: 11, borne diseases: 11, dengue outbreak: 11, disease outbreaks: 11, disease surveillance: 11, geographical distribution: 11, global health: 11, heat waves: 11, neural networks: 11, nile virus: 11, preterm birth: 11, relative humidity: 11, rough set: 11, tnb individuals: 11, climate conditions: 10, climate factors: 10, climatic conditions: 10, digital health: 10, logistic regression: 10, term memory: 10, borne disease: 9, climate changes: 9, climatic factors: 9, early warning: 9, forest rf: 9, spatial distribution: 9, street view: 9, sustainable development: 9, adult ae: 8, decision tree: 8, european countries: 8, land use: 8, learning based: 8, lstm att: 8, remote sensing: 8, spatio temporal: 8, surface temperature: 8, united states: 8, vector machine: 8, view images: 8, weather conditions: 8, weekly dengue: 8, yangtze river: 8, added value: 7, aegypti abundance: 7, ai applications: 7, case counts: 7, climate dynamics: 7, climate hfrs: 7, confirmed cases: 7, dengue risk: 7, global climate: 7, habitat suitability: 7, learning algorithm: 7, malaria incidence: 7, maximum temperature: 7covid 19 pandemic: 19, artificial intelligence ai: 16, using machine learning: 16, artificial neural network: 15, machine learning ml: 15, machine learning algorithms: 12, machine learning approach: 12, climate change scenarios: 11, covid 19 cases: 11, west nile virus: 11, machine learning techniques: 10, short term memory: 10, random forest rf: 9, vector borne diseases: 9, adult ae aegypti: 8, street view images: 8, support vector machine: 8, ae aegypti abundance: 7, machine learning algorithm: 7, machine learning based: 7, nile virus wnv: 7, term memory lstm: 7, torres strait islander: 7, vector borne disease: 7, female adult ae: 6, future climate change: 6, heat related mortality: 6, high risk areas: 6, post covid 19: 6, rough set based: 6, supervised machine learning: 6, based deep learning: 5, climate hfrs association: 5, early warning systems: 5, ecological niche modeling: 5, electronic health records: 5, future climate scenarios: 5, granulation rough set: 5, heat related ambulance: 5, land surface temperature: 5, positive covid 19: 5, random forest regression: 5, time series forecasting: 5, ubiquitous clinic recommendation: 5, used machine learning: 5, world health organization: 5, ai enabled tools: 4, central highland regions: 4, covid 19 transmission: 4, deep learning dl: 4, dengue fever df: 4, ecg myocardial infarction: 4, fine grained intra: 4, grained intra urban: 4, machine learning classifier: 4, multi criteria decision: 4, multi granulation rough: 4, myocardial infarction detection: 4, neural network ann: 4, poyang lake region: 4, random forest classifier: 4, related ambulance calls: 4, sustainable development goals: 4, vector machine svm: 4, ae albopictus distribution: 3, ai driven technologies: 3, artificial intelligence based: 3, artificial intelligence health: 3, artificial neural networks: 3, based machine learning: 3, batrachochytrium dendrobatidis bd: 3, boosted regression trees: 3, borne infectious disease: 3, climate change background: 3, climate change scenario: 3, clinical public health: 3, convolutional neural network: 3, convolutional neural networks: 3, coronavirus disease 2019: 3, covid 19 risk: 3, daily diarrhoea cases: 3, dengue fever outbreaks: 3, dengue risk prediction: 3, effective early warning: 3, evolutionary parameter optimization: 3, extreme climate events: 3, extremely preterm birth: 3, facilitating fine grained: 3, forest machine learning: 3, gaussian process based: 3, global change scenarios: 3, global climate dynamics: 3, health care environment: 3, health care systems: 3, health enabling technologies: 3, health records ehr: 3, health technology assessment: 3, heat health relationships: 3, heat wave hazard: 3, human rna viruses: 3[('data', 346), ('climate', 324), ('health', 299), ('model', 238), ('models', 225), ('disease', 183), ('machine', 175), ('study', 164), ('change', 161), ('risk', 151), ('%', 150), ('learning', 145), ('results', 125), ('factors', 120), ('prediction', 118), ('temperature', 113), ('distribution', 102), ('analysis', 100), ('diseases', 98), ('cases', 97), ('methods', 96), ('areas', 94), ('time', 89), ('dengue', 84), ('vector', 81), ('transmission', 77), ('approach', 75), ('research', 75), ('variables', 73), ('accuracy', 72), ('intelligence', 71), ('performance', 69), ('incidence', 69), ('regression', 67), ('patients', 67), ('conditions', 65), ('approaches', 61), ('heat', 61), ('system', 61), ('population', 60), ('surveillance', 60), ('information', 59), ('weather', 57), ('impact', 56), ('infection', 56), ('regions', 55), ('-', 54), ('control', 53), ('method', 51), ('care', 50), ('virus', 50), ('number', 50), ('outbreaks', 49), ('environment', 49), ('paper', 47), ('systems', 43), ('forest', 43), ('case', 42), ('techniques', 42), ('world', 42), ('framework', 41), ('changes', 41), ('management', 40), ('healthcare', 40), ('classification', 40), ('countries', 39), ('development', 39), ('species', 39), ('outbreak', 39), ('forecasting', 38), ('use', 37), ('malaria', 37), ('area', 36), ('years', 36), ('studies', 35), ('term', 35), ('scenarios', 35), ('humidity', 35), ('precipitation', 35), ('findings', 35), ('temperatures', 34), ('decision', 34), ('range', 33), ('background', 32), ('effects', 32), ('future', 31), ('region', 31), ('measures', 30), ('level', 30), ('challenges', 30), ('mortality', 30), ('conclusions', 28), ('association', 28), ('correlation', 28), ('technologies', 28), ('tools', 28), ('period', 28), ('suitability', 28), ('spread', 28), ('parameters', 28)][('use', 306), ('base', 189), ('predict', 160), ('show', 89), ('learn', 88), ('propose', 86), ('include', 82), ('have', 78), ('increase', 71), ('develop', 70), ('identify', 65), ('improve', 61), ('compare', 60), ('relate', 60), ('provide', 55), ('model', 47), ('apply', 46), ('drive', 45), ('find', 43), ('evaluate', 42), ('be', 40), ('consider', 38), ('investigate', 35), ('estimate', 35), ('suggest', 35), ('support', 35), ('aim', 34), ('affect', 34), ('make', 33), ('exist', 32), ('forecast', 31), ('help', 30), ('bear', 30), ('cause', 29), ('reduce', 29), ('integrate', 28), ('mean', 28), ('assess', 28), ('require', 27), ('explore', 26), ('generate', 26), ('obtain', 25), ('collect', 25), ('change', 25), ('take', 24), ('contribute', 24), ('understand', 24), ('follow', 24), ('need', 24), ('perform', 24), ('select', 24), ('influence', 24), ('present', 24), ('indicate', 23), ('correlate', 23), ('ensure', 23), ('associate', 23), ('build', 22), ('determine', 22), ('analyze', 22), ('demonstrate', 21), ('remain', 21), ('implement', 21), ('result', 20), ('emerge', 20), ('focus', 20)][('such', 93), ('global', 90), ('environmental', 89), ('-', 81), ('high', 79), ('artificial', 77), ('human', 71), ('future', 68), ('other', 68), ('medical', 63), ('climatic', 63), ('public', 61), ('different', 60), ('predictive', 55), ('spatial', 54), ('current', 54), ('new', 52), ('important', 50), ('pandemic', 48), ('random', 46), ('potential', 44), ('deep', 44), ('sustainable', 44), ('various', 42), ('digital', 39), ('clinical', 37), ('effective', 37), ('significant', 36), ('average', 33), ('local', 33), ('urban', 33), ('geographical', 32), ('neural', 32), ('meteorological', 32), ('infectious', 32), ('ecological', 31), ('more', 31), ('extreme', 31), ('real', 30), ('long', 30), ('specific', 29), ('monthly', 29), ('non', 29), ('statistical', 28), ('many', 28), ('early', 28), ('higher', 27), ('major', 27), ('social', 27), ('big', 27), ('daily', 27), ('short', 25), ('low', 25), ('several', 25), ('complex', 25), ('seasonal', 24), ('large', 22), ('positive', 22), ('northern', 22), ('geographic', 22), ('economic', 22), ('best', 22), ('southern', 21), ('main', 20), ('scientific', 20), ('national', 20), ('temporal', 20)]{'climate': 10, 'temperature': 2, 'seasonality': 2, 'different': 2, 'heatwaves': 2, 'relevance': 2, 'sensitivity': 1, 'climatic': 1, 'factors': 1, 'ai': 1, 'vrvs': 1, 'proposed': 1, 'various': 1}{'climatic': 2, 'meteorological': 1, 'climate': 1, 'certain': 1, 'digital': 1, 'ecological': 1, 'official': 1, 'machine': 1, 'scientific': 1}[('momentous climate change health impacts', 0.5406), ('communicable diseases climate changes', 0.5252), ('climatic predictors', 0.5163), ('important environmental predictors', 0.5074), ('climatic correlates', 0.4957), ('temperature mortality rates', 0.4932), ('environmental predictors', 0.4922), ('preterm birth risk', 0.4883), ('key environmental predictors', 0.4832), ('climate predictors', 0.4766), ('correlational study climate change', 0.469), ('heat illness risk', 0.4685), ('monthly heat wave risk maps', 0.4525), ('different climatic variables', 0.4519), ('climatic variables', 0.4475), ('spatial epidemiology', 0.447), ('influential climate variables', 0.447), ('vulnerable population climate change', 0.4466), ('climate modeling', 0.4405), ('risk temperature', 0.4349), ('different climate factors', 0.4346), ('effective population health services climate change', 0.4314), ('climate variables', 0.4298), ('machine learning approach climate change', 0.4291), ('relevant climate indicators', 0.4265), ('air pollution predictors', 0.4254), ('urban heat environment', 0.4218), ('machine learning perspective climate change', 0.4206), ('climate factors', 0.4179), ('temperature impacts', 0.4178), ('monthly heat wave hazard', 0.4176), ('preterm births', 0.415), ('heat risk assessment', 0.4144), ('uncertain pandemic climate', 0.4132), ('climate relationships', 0.4131), ('climate model', 0.4096), ('simple urban climate model', 0.408), ('healthcare prediction', 0.4064), ('climate change variables', 0.4064), ('climate projections', 0.4052), ('climatic sensitivity', 0.4049), ('big climate data', 0.4049), ('spatial climate', 0.4044), ('predictive meteorological factors', 0.4037), ('climatic factors', 0.4018), ('environmental temperatures', 0.4014), ('covid risk prediction', 0.4014), ('heat illness prevention', 0.4011), ('overall warmer temperatures', 0.4006), ('swedish pregnancy register', 0.3999)]
6
412000.147vegetation_ecosystems4_forest_species_soil_climate['forest', 'species', 'soil', 'climate', 'change', 'land', 'learning', 'carbon', 'using', 'vegetation', 'machine', 'climate change', 'machine learning', 'based', 'cover', 'used', 'distribution', 'classification', 'spatial', 'remote', 'sensing', 'remote sensing', 'area', 'forests', 'tree', 'use', 'high', 'areas', 'global', 'changes'][('soilgrids', 0.4734), ('soilgrids250m', 0.4718), ('soils', 0.4327), ('soil', 0.43), ('geosciences', 0.4047), ('soilcastor', 0.4018), ('geostatistics', 0.4016), ('biogeography', 0.3792), ('topsoil', 0.3771), ('geoscience', 0.3758), ('topsoils', 0.3749), ('geomorphology', 0.3679), ('sediments', 0.3654), ('biogeographic', 0.3437), ('geolearn', 0.338), ('terrains', 0.3306), ('geoclimatic', 0.3286), ('peatlands', 0.3283), ('landsat', 0.3234), ('topographic', 0.3233), ('vegetation', 0.3213), ('landforms', 0.3199), ('vegetations', 0.3194), ('desertification', 0.318), ('geostatistical', 0.3165), ('classifiers', 0.3158), ('stratigraphy', 0.3148), ('geomorphological', 0.3138), ('peatland', 0.3106), ('topography', 0.3081), ('landcover', 0.3055), ('predictors', 0.3046), ('biodiversitymonitoring', 0.3043), ('mineralogy', 0.3035), ('ecosystems15', 0.3026), ('climates', 0.3019), ('topographical', 0.3003), ('biogeographical', 0.2997), ('imagenet', 0.2983), ('agroecosystems', 0.2978), ('landform', 0.2977), ('terrain', 0.2967), ('forests', 0.2965), ('glaciology', 0.2958), ('为了探明利用机器学习方法对表层土壤氢氧稳定同位素组成', 0.295), ('geotechnical', 0.2947), ('geomorphologic', 0.294), ('biogeochemistry', 0.293), ('densenet18', 0.2922), ('agroforestry', 0.2915)][('soil predictors', 0.7052), ('soil predictor', 0.6848), ('predictive soil', 0.6812), ('predicting soil', 0.6666), ('dataset soil', 0.6627), ('predict soil', 0.6571), ('soil dataset', 0.6482), ('soil datasets', 0.6444), ('prediction soil', 0.6345), ('soil estimating', 0.6341), ('estimating soil', 0.6291), ('predicted soil', 0.6285), ('soil databases', 0.6274), ('soil mapping', 0.6264), ('soil database', 0.6251), ('predictors soil', 0.6221), ('mapping soil', 0.6205), ('predicted soils', 0.6203), ('predictor soil', 0.6189), ('accurate soil', 0.6162), ('forecasting soil', 0.6103), ('soils estimating', 0.6069), ('soil accurate', 0.6009), ('soil maps', 0.5952), ('landform predictors', 0.5929), ('modelling soil', 0.5847), ('soils database', 0.5841), ('globalsoilmap soil', 0.5836), ('map soil', 0.5829), ('quantifying soil', 0.5823), ('modeling soil', 0.5823), ('mapping soils', 0.5816), ('mapping soilgrids250m', 0.58), ('quantitative soil', 0.5785), ('soil information', 0.5773), ('landsat8 soil', 0.5761), ('soil map', 0.5755), ('soil sensing', 0.5754), ('soil classification', 0.5744), ('forecasts soil', 0.5742), ('soil survey', 0.5727), ('predictions soil', 0.5709), ('soil features', 0.5677), ('soil profiles', 0.5671), ('soil surveys', 0.5667), ('understanding soil', 0.5661), ('determining soil', 0.566), ('soil soc100', 0.5658), ('prediction topsoil', 0.5642), ('soil radiometric', 0.5626)]climate change: 1220, machine learning: 1149, remote sensing: 599, random forest: 446, land cover: 428, deep learning: 395, land use: 360, neural network: 191, support vector: 183, learning algorithms: 172, organic carbon: 170, high resolution: 168, long term: 163, soil organic: 157, forest rf: 150, species distribution: 134, tree species: 134, large scale: 130, vector machine: 128, using machine: 120, spatial distribution: 118, neural networks: 117, time series: 115, convolutional neural: 110, learning algorithm: 106, spatial resolution: 104, forest management: 102, learning techniques: 102, future climate: 98, satellite images: 96, mg ha: 94, carbon stocks: 92, soil carbon: 91, global climate: 89, google earth: 88, vegetation index: 87, aboveground biomass: 86, soc stock: 86, sustainable development: 85, artificial intelligence: 83, carbon sequestration: 83, global warming: 83, learning based: 81, carbon storage: 77, earth engine: 77, satellite imagery: 76, ecosystem services: 75, machine svm: 75, remotely sensed: 75, soc stocks: 75, carbon cycle: 74, semi arid: 73, square error: 72, learning approach: 71, soil properties: 71, habitat suitability: 70, cover change: 68, environmental factors: 67, human activities: 67, change mitigation: 65, artificial neural: 64, carbon soc: 64, change detection: 64, plant species: 63, error rmse: 61, gradient boosting: 59, learning ml: 58, soil erosion: 58, change scenarios: 57, cross validation: 57, image classification: 57, use land: 57, global carbon: 56, normalized difference: 54, soil moisture: 54, cover classification: 53, potential distribution: 53, terrestrial ecosystems: 53, climate changes: 52, biomass agb: 51, carbon stock: 50, decision support: 50, forest ecosystems: 50, forest cover: 49, learning approaches: 49, linear regression: 49, protected areas: 48, multi source: 47, united states: 46, difference vegetation: 45, sensing images: 45, spatially explicit: 45, suitable habitat: 45, tibetan plateau: 45, vegetation indices: 45, decision making: 44, semantic segmentation: 44, carbon sink: 43, climatic conditions: 43, land surface: 43machine learning algorithms: 158, random forest rf: 150, soil organic carbon: 128, support vector machine: 128, using machine learning: 119, machine learning algorithm: 91, machine learning techniques: 82, google earth engine: 77, vector machine svm: 75, global climate change: 67, climate change mitigation: 65, organic carbon soc: 63, convolutional neural network: 62, land use land: 57, machine learning ml: 57, use land cover: 55, climate change scenarios: 53, square error rmse: 50, land cover change: 48, convolutional neural networks: 47, machine learning approach: 47, remote sensing images: 45, difference vegetation index: 44, land cover classification: 44, artificial neural network: 43, machine learning based: 42, normalized difference vegetation: 42, future climate change: 41, machine learning approaches: 40, land use change: 38, using deep learning: 37, using random forest: 36, vegetation index ndvi: 36, qinghai tibet plateau: 34, synthetic aperture radar: 34, deep learning based: 33, global carbon cycle: 33, land use cover: 33, satellite remote sensing: 33, support vector machines: 33, aboveground biomass agb: 32, climate change impacts: 32, land cover mapping: 32, using remote sensing: 31, digital soil mapping: 30, resolution remote sensing: 30, forest machine learning: 28, extreme gradient boosting: 27, random forest algorithm: 27, random forest machine: 27, high spatial resolution: 26, neural network cnn: 26, remote sensing imagery: 26, sustainable forest management: 26, gross primary productivity: 25, land cover lulc: 25, soil organic matter: 25, fold cross validation: 24, multiple linear regression: 24, neural network ann: 24, used machine learning: 24, earth engine gee: 23, land cover classes: 23, remote sensing image: 23, forest aboveground biomass: 22, land cover changes: 22, absolute error mae: 21, artificial neural networks: 21, deep neural network: 20, different machine learning: 20, high resolution remote: 20, semi arid regions: 20, soil carbon stocks: 20, land cover maps: 19, machine learning classifiers: 19, sea level rise: 19, support vector regression: 19, boosted regression trees: 18, ground biomass agb: 18, leaf area index: 18, maximum entropy maxent: 18, tree species classification: 18, aperture radar sar: 17, deep learning dl: 17, global land cover: 17, linear regression mlr: 17, mitigating climate change: 17, random forest regression: 17, land cover types: 16, remote sensing technology: 16, based machine learning: 15, breast height dbh: 15, carbon sequestration capacity: 15, climate change effects: 15, climate change scenario: 15, deep learning techniques: 15, future climate scenarios: 15, greenhouse gas emissions: 15, gross primary production: 15, learning ml algorithms: 15[('climate', 2061), ('data', 1957), ('forest', 1886), ('change', 1647), ('%', 1539), ('model', 1510), ('soil', 1371), ('machine', 1319), ('species', 1254), ('models', 1245), ('land', 1187), ('learning', 1166), ('study', 1117), ('carbon', 1087), ('results', 986), ('vegetation', 832), ('classification', 736), ('accuracy', 718), ('distribution', 705), ('area', 664), ('cover', 656), ('areas', 628), ('use', 619), ('changes', 574), ('methods', 560), ('management', 559), ('variables', 548), ('tree', 539), ('method', 538), ('soc', 525), ('approach', 516), ('images', 506), ('forests', 501), ('time', 490), ('information', 485), ('mapping', 470), ('analysis', 468), ('scale', 456), ('resolution', 438), ('performance', 436), ('satellite', 423), ('temperature', 423), ('factors', 419), ('prediction', 377), ('ecosystem', 358), ('research', 339), ('algorithms', 334), ('sensing', 331), ('regression', 325), ('water', 321), ('development', 320), ('biomass', 319), ('monitoring', 311), ('image', 305), ('c', 304), ('maps', 303), ('region', 299), ('network', 297), ('field', 294), ('techniques', 292), ('habitat', 291), ('conditions', 291), ('ecosystems', 289), ('conservation', 287), ('-', 279), ('growth', 279), ('regions', 274), ('trees', 269), ('detection', 269), ('scenarios', 265), ('imagery', 261), ('plant', 260), ('dynamics', 258), ('effects', 252), ('index', 247), ('years', 246), ('environment', 246), ('system', 243), ('biodiversity', 243), ('approaches', 241), ('estimation', 240), ('features', 237), ('precipitation', 231), ('studies', 224), ('loss', 222), ('range', 221), ('types', 220), ('dataset', 219), ('stocks', 218), ('level', 218), ('training', 216), ('importance', 215), ('modeling', 214), ('landscape', 212), ('error', 212), ('patterns', 210), ('term', 207), ('paper', 205), ('potential', 203), ('impacts', 201)][('use', 2621), ('base', 1256), ('show', 767), ('predict', 739), ('provide', 616), ('learn', 578), ('have', 558), ('increase', 516), ('estimate', 415), ('propose', 412), ('compare', 411), ('develop', 401), ('improve', 379), ('include', 367), ('sense', 357), ('apply', 340), ('evaluate', 310), ('identify', 308), ('assess', 303), ('model', 290), ('find', 262), ('combine', 259), ('support', 245), ('reduce', 239), ('obtain', 233), ('affect', 224), ('indicate', 222), ('understand', 218), ('derive', 212), ('demonstrate', 209), ('monitor', 208), ('consider', 205), ('achieve', 196), ('train', 191), ('analyze', 184), ('present', 183), ('suggest', 182), ('perform', 180), ('require', 171), ('drive', 169), ('determine', 169), ('generate', 168), ('produce', 167), ('relate', 165), ('make', 164), ('change', 163), ('integrate', 158), ('decrease', 157), ('classify', 157), ('investigate', 156), ('result', 150), ('map', 150), ('extract', 149), ('build', 148), ('reveal', 145), ('detect', 144), ('test', 136), ('quantify', 136), ('select', 136), ('be', 133), ('collect', 133), ('exist', 131), ('become', 130), ('explore', 130), ('aim', 130), ('follow', 130), ('remain', 129), ('help', 126), ('cause', 125), ('give', 120), ('project', 120), ('lead', 117), ('protect', 116), ('represent', 115), ('range', 114), ('contribute', 112), ('associate', 112), ('need', 111), ('measure', 110), ('mean', 109), ('take', 107), ('grow', 107), ('observe', 107), ('boost', 106), ('allow', 105), ('vary', 104), ('cover', 102), ('play', 102), ('influence', 102), ('enhance', 101), ('address', 101), ('study', 98), ('simulate', 96), ('employ', 95), ('focus', 91), ('create', 90), ('outperform', 90), ('occur', 90), ('highlight', 88), ('explain', 87)][('-', 808), ('spatial', 761), ('high', 693), ('global', 663), ('remote', 616), ('different', 543), ('random', 534), ('environmental', 530), ('important', 498), ('deep', 498), ('future', 481), ('such', 449), ('large', 422), ('ecological', 362), ('other', 354), ('current', 320), ('neural', 306), ('potential', 290), ('urban', 283), ('temporal', 283), ('sustainable', 278), ('multi', 274), ('new', 273), ('human', 256), ('significant', 256), ('natural', 247), ('overall', 245), ('organic', 244), ('climatic', 240), ('accurate', 235), ('spectral', 229), ('annual', 223), ('suitable', 218), ('higher', 212), ('low', 212), ('regional', 204), ('long', 200), ('rf', 200), ('many', 193), ('local', 183), ('effective', 182), ('total', 180), ('best', 175), ('average', 171), ('agricultural', 169), ('various', 167), ('key', 166), ('artificial', 166), ('terrestrial', 165), ('recent', 164), ('tropical', 164), ('available', 162), ('multiple', 160), ('complex', 152), ('more', 149), ('highest', 146), ('critical', 145), ('digital', 145), ('main', 143), ('better', 142), ('major', 139), ('most', 136), ('first', 135), ('essential', 135), ('ensemble', 134), ('specific', 131), ('mean', 131), ('net', 128), ('traditional', 126), ('convolutional', 125), ('national', 124), ('present', 123), ('anthropogenic', 123), ('predictive', 123), ('non', 121), ('agb', 120), ('northern', 118), ('arid', 117), ('aboveground', 117), ('linear', 109), ('extreme', 109), ('coastal', 108), ('several', 107), ('semi', 106), ('statistical', 105), ('similar', 103), ('phenological', 103), ('great', 101), ('maximum', 100), ('single', 99), ('novel', 97), ('optical', 96), ('crucial', 95), ('small', 93), ('relative', 92), ('same', 92), ('dry', 92), ('southern', 91), ('square', 91), ('central', 90)]{'climate': 23, 'human': 4, 'global': 4, 'land': 3, 'different': 3, 'environmental': 3, 'drought': 2, 'eastern': 2, 'tillage': 2, 'topographic': 2, 'potential': 1, 'vegetation': 1, 'physiological': 1, 'dense': 1, 'insect': 1, 'urban': 1, 'deforestation': 1, 'local': 1, 'disturbances': 1, 'late': 1, 'slm': 1, 'stratification': 1, 'urbanization': 1, 'enlarging': 1, 'pre': 1, 'training': 1, 'forest': 1, 'predicted': 1, 'redcedar': 1, 'lianas': 1, 'storm': 1, 'conservative': 1, 'rainfall': 1, 'multiple': 1, 'large': 1, 'drivers': 1, 'management': 1, 'uncertainties': 1, 'future': 1, 'climatic': 1, 'isolation': 1, 'network': 1, 'interspecific': 1, 'agricultural': 1, 'external': 1, 'unsustainable': 1, 'awc': 1, 'pretraining': 1, 'changing': 1}{'forests': 3, 'precipitation': 2, 'information': 2, 'climatic': 2, 'land': 1, 'time': 1, 'remote': 1, 'minimum': 1, 'semi': 1, 'anthropogenic': 1, 'gpp': 1, 'coastal': 1, 'bio': 1, 'anthropogeomorphology': 1, 'human': 1, 'multiple': 1, 'different': 1, 'lai': 1, 'industry': 1, 'glacial': 1, 'weather': 1, 'cue': 1, 'tussocks': 1, 'carbon': 1, 'climate': 1, 'maximum': 1, 'ecological': 1, 'varying': 1, 'elevation': 1, 'functionally': 1, 'forest': 1}[('harmonized world soil database', 0.7115), ('soil predictors', 0.7052), ('consistent global soil information', 0.6898), ('accurate spatial soil information', 0.6829), ('predictive soil mapping', 0.6797), ('national soil information grids', 0.6692), ('accurate soil data', 0.6574), ('current digital soil mapping framework', 0.6486), ('legacy soil datasets', 0.6483), ('soil classification data', 0.6478), ('accurate soil maps', 0.6459), ('machine learning models soil erosion', 0.6455), ('soil data sets', 0.645), ('soil datasets', 0.6444), ('predictive soil mapping paradigm', 0.6416), ('soil texture class prediction', 0.6377), ('new digital soil mapping framework', 0.6373), ('detailed spatial soil information', 0.6368), ('global gridded soil information', 0.6313), ('soil property prediction', 0.6275), ('soil data', 0.6268), ('machine learning tools land degradation', 0.6264), ('soil mapping', 0.6264), ('soil database', 0.6251), ('artificial neural networks soil', 0.6221), ('mapping soil', 0.6205), ('representative soil profiles', 0.6163), ('accurate soil', 0.6162), ('digital soil mapping framework', 0.6146), ('many tropical soil databases', 0.6135), ('single regional soils database', 0.6117), ('deep learning approach soil', 0.6108), ('digital soil maps', 0.6084), ('soil survey data', 0.6079), ('soil texture classification', 0.6074), ('digital soil mapping', 0.6061), ('detailed soil information', 0.605), ('conventional soil mapping', 0.6043), ('soil profiles representative', 0.6024), ('soil information system', 0.6018), ('depth soil predictor', 0.5982), ('rainforest accurate soil', 0.5962), ('soil maps', 0.5952), ('legacy soil data', 0.5947), ('global land cover data underpins research', 0.593), ('novel soil texture maps', 0.593), ('landform predictors', 0.5929), ('traditional soil mapping approaches', 0.588), ('soil properties inference', 0.5874), ('recent national soil survey', 0.5863)]
7
58350.102agriculture5_crop_yield_agriculture_climate['crop', 'yield', 'agriculture', 'climate', 'agricultural', 'production', 'food', 'learning', 'using', 'based', 'crops', 'machine', 'change', 'machine learning', 'farmers', 'climate change', 'plant', 'yields', 'prediction', 'used', 'rice', 'irrigation', 'soil', 'farming', 'water', 'management', 'crop yield', 'disease', 'different', 'time'][('smartagriculture', 0.4398), ('climateprojections', 0.3943), ('agroecology', 0.3859), ('agronomics', 0.3783), ('agronomical', 0.3704), ('landsat', 0.3693), ('agroclimate', 0.3689), ('agroecologies', 0.3664), ('agroclimatic', 0.3648), ('crops', 0.3609), ('permaculture', 0.3587), ('agriculture', 0.3573), ('agroforestry', 0.3506), ('agroeconomic', 0.3492), ('agrotechnology', 0.3478), ('climates', 0.3434), ('agroecosystem', 0.3424), ('climate', 0.3411), ('agricultural', 0.3368), ('agroecosystems', 0.3368), ('orchards', 0.3363), ('agronomically', 0.3356), ('desertification', 0.3342), ('agriculturists', 0.3303), ('classifiers', 0.3272), ('ecoregions', 0.3267), ('agroecological', 0.3248), ('multispectral', 0.3247), ('croplands', 0.3243), ('predicting', 0.3237), ('agricultures', 0.3229), ('climatological', 0.3224), ('agriculturalists', 0.3217), ('meteorology', 0.3212), ('agrobiodiversity', 0.3204), ('vegetation', 0.3201), ('agriculturally', 0.3196), ('cropland', 0.3168), ('predictors', 0.316), ('deforestation', 0.3132), ('agronomic', 0.3123), ('agronomy', 0.3106), ('glm', 0.3086), ('farmland', 0.308), ('forests', 0.3077), ('forestry', 0.3043), ('phenology', 0.2984), ('forecasting', 0.2982), ('smartcropplanting', 0.2976), ('climatically', 0.2972)][('agriculture predictive', 0.5985), ('predictive agriculture', 0.5937), ('agricultural prediction', 0.5798), ('classifiers agriculture', 0.5577), ('predicting agricultural', 0.5558), ('agriculture prediction', 0.552), ('predictive agronomic', 0.5496), ('prediction agriculture', 0.5476), ('crops predicting', 0.5451), ('agricultural predictions', 0.5418), ('forecasting agriculture', 0.5354), ('agriculture forecasting', 0.5308), ('precision agriculture', 0.5304), ('agricultural forecasting', 0.5294), ('forecasting crops', 0.528), ('crop prediction', 0.5278), ('prediction agricultural', 0.5275), ('climate agronomic', 0.5275), ('predict agricultural', 0.5248), ('crop meteorological', 0.522), ('predict crops', 0.5214), ('climate agricultural', 0.5182), ('crops estimating', 0.5181), ('predicting crop', 0.5181), ('predict cropland', 0.5179), ('agriculture estimating', 0.5172), ('crops predict', 0.5161), ('agriculture dataset', 0.5155), ('sensing agricultural', 0.5148), ('agricultural dataset', 0.5137), ('climate prediction', 0.5111), ('sensed cropland', 0.5104), ('climate crop', 0.5103), ('prediction agrotourism', 0.5102), ('agriculture climate', 0.5087), ('crop adaptation', 0.5077), ('foresee climates', 0.5076), ('crops climate', 0.5075), ('climate agriculture', 0.5074), ('forecast crops', 0.5065), ('crop climate', 0.5061), ('agriculture precision', 0.5044), ('forecasting agricultural', 0.5042), ('predicting vegetation', 0.5035), ('predicted crops', 0.5033), ('forecasting crop', 0.5012), ('climate forecasting', 0.5006), ('predicts crop', 0.497), ('agricultural precision', 0.4968), ('remote sensing', 0.4956)]machine learning: 745, climate change: 709, deep learning: 270, crop yield: 262, artificial intelligence: 238, food security: 191, neural network: 171, random forest: 166, yield prediction: 149, decision support: 135, crop yields: 128, remote sensing: 126, crop production: 125, real time: 91, support vector: 91, winter wheat: 91, learning algorithms: 90, neural networks: 89, using machine: 89, agricultural production: 88, global warming: 78, decision making: 76, learning techniques: 72, precision agriculture: 69, learning based: 68, time series: 67, long term: 66, vector machine: 63, future climate: 62, smart agriculture: 62, convolutional neural: 59, disease detection: 59, smart farming: 59, plant disease: 58, soil moisture: 57, short term: 55, food production: 54, intelligence ai: 54, sustainable agriculture: 54, kg ha: 52, large scale: 52, things iot: 52, climate changes: 50, forest rf: 50, learning approach: 50, maize yield: 50, plant diseases: 49, learning ml: 48, rice yield: 48, sustainable development: 48, water resources: 48, wheat yield: 48, artificial neural: 47, life cycle: 47, climatic conditions: 46, agricultural sector: 45, grain yield: 44, management practices: 44, learning algorithm: 43, linear regression: 43, crop growth: 41, food supply: 41, process based: 41, term memory: 40, gradient boosting: 39, irrigation water: 39, climate conditions: 38, computer vision: 36, crop management: 36, growing season: 36, leaf disease: 36, image processing: 35, transfer learning: 35, global food: 34, land use: 34, recent years: 34, weather conditions: 34, cotton yield: 33, environmental impacts: 33, machine svm: 33, rice yields: 33, square error: 33, using deep: 33, paper presents: 32, supply chain: 32, use efficiency: 32, water use: 32, climate variability: 31, deep neural: 30, agricultural systems: 29, air temperature: 29, environmental conditions: 29, extreme weather: 29, human health: 29, iot based: 29, environmental factors: 28, learning approaches: 28, rice production: 28, agrotechnology transfer: 27, digital technologies: 27using machine learning: 88, machine learning algorithms: 82, crop yield prediction: 70, support vector machine: 62, artificial intelligence ai: 54, machine learning techniques: 51, random forest rf: 50, machine learning ml: 48, convolutional neural network: 42, short term memory: 40, machine learning approach: 39, machine learning based: 38, vector machine svm: 33, machine learning algorithm: 30, deep learning based: 27, artificial neural networks: 25, deep neural network: 24, using deep learning: 24, plant disease detection: 23, artificial neural network: 22, machine learning approaches: 22, future climate change: 21, agrotechnology transfer dssat: 20, climate change impacts: 20, deep learning techniques: 20, global food security: 20, neural network cnn: 20, cold dew wind: 19, term memory lstm: 19, convolutional neural networks: 17, decision support systems: 17, multiple linear regression: 17, deep learning dl: 16, leaf disease detection: 16, machine learning technique: 16, support vector regression: 16, using artificial intelligence: 16, climate change adaptation: 15, extreme weather events: 15, global climate change: 15, seed cotton yield: 15, square error rmse: 15, winter wheat yield: 15, climate change scenarios: 14, yield prediction using: 14, climate change impact: 13, cycle environmental impacts: 13, life cycle assessment: 13, life cycle environmental: 13, neural network ann: 12, recurrent neural network: 12, remote sensing technology: 12, sustainable development goals: 12, unmanned aerial vehicles: 12, water use efficiency: 12, convolution neural network: 11, deep transfer learning: 11, extreme gradient boosting: 11, plant disease identification: 11, radial basis function: 11, supervised machine learning: 11, artificial intelligence based: 10, different machine learning: 10, food supply chain: 10, future climate conditions: 10, google earth engine: 10, predict crop yield: 10, process based crop: 10, random forest algorithm: 10, remote sensing monitoring: 10, representative concentration pathways: 10, rice growth stages: 10, soil organic carbon: 10, unmanned aerial vehicle: 10, wireless sensor network: 10, dssat decision support: 9, future climate scenarios: 9, gradient boosting regression: 9, high throughput phenotyping: 9, near real time: 9, north china plain: 9, remote sensing images: 9, soil water content: 9, using random forest: 9, various machine learning: 9, climate change scenario: 8, cycle global warming: 8, deep learning algorithm: 8, deep learning algorithms: 8, difference vegetation index: 8, disease detection using: 8, explicit life cycle: 8, extreme weather conditions: 8, forest machine learning: 8, gradient boosting machine: 8, hybrid deep learning: 8, land use change: 8, life cycle global: 8, plant leaf disease: 8, predicting crop yields: 8[('crop', 1387), ('climate', 1363), ('data', 1292), ('yield', 1097), ('model', 939), ('machine', 847), ('%', 813), ('change', 786), ('learning', 783), ('production', 748), ('agriculture', 742), ('models', 651), ('food', 618), ('study', 594), ('system', 557), ('prediction', 549), ('results', 512), ('water', 500), ('management', 457), ('soil', 451), ('crops', 448), ('time', 416), ('farmers', 395), ('plant', 379), ('accuracy', 372), ('research', 356), ('irrigation', 332), ('yields', 325), ('systems', 322), ('conditions', 320), ('methods', 319), ('temperature', 316), ('rice', 314), ('growth', 311), ('use', 302), ('wheat', 301), ('information', 298), ('approach', 296), ('disease', 295), ('paper', 292), ('weather', 291), ('factors', 283), ('development', 281), ('farming', 275), ('environment', 274), ('decision', 274), ('analysis', 269), ('performance', 269), ('detection', 269), ('method', 268), ('field', 264), ('intelligence', 256), ('classification', 256), ('technologies', 251), ('network', 246), ('diseases', 243), ('techniques', 235), ('application', 226), ('impact', 225), ('changes', 219), ('security', 216), ('support', 212), ('maize', 211), ('technology', 210), ('quality', 203), ('land', 201), ('area', 201), ('productivity', 200), ('impacts', 195), ('images', 195), ('algorithms', 191), ('regression', 190), ('variables', 186), ('forest', 174), ('years', 173), ('level', 172), ('precision', 171), ('scale', 169), ('areas', 163), ('efficiency', 159), ('monitoring', 155), ('population', 154), ('plants', 153), ('effects', 152), ('process', 152), ('challenges', 152), ('resources', 151), ('parameters', 147), ('approaches', 146), ('farm', 146), ('regions', 145), ('scenarios', 144), ('control', 144), ('work', 139), ('dataset', 139), ('image', 137), ('leaf', 133), ('world', 132), ('networks', 130), ('practices', 128)][('use', 1641), ('base', 920), ('predict', 441), ('increase', 421), ('show', 386), ('develop', 380), ('learn', 375), ('propose', 375), ('provide', 356), ('have', 321), ('improve', 315), ('identify', 261), ('include', 236), ('compare', 233), ('grow', 231), ('make', 225), ('reduce', 218), ('apply', 203), ('achieve', 195), ('evaluate', 180), ('affect', 171), ('support', 168), ('present', 161), ('help', 157), ('consider', 149), ('find', 147), ('estimate', 144), ('assess', 142), ('obtain', 141), ('collect', 139), ('require', 139), ('become', 126), ('integrate', 125), ('detect', 124), ('combine', 122), ('be', 122), ('implement', 120), ('analyze', 119), ('relate', 119), ('take', 118), ('perform', 117), ('determine', 115), ('need', 111), ('drive', 111), ('train', 110), ('monitor', 108), ('produce', 108), ('cause', 106), ('exist', 101), ('enable', 101), ('yield', 100), ('test', 99), ('select', 99), ('indicate', 99), ('lead', 99), ('simulate', 98), ('demonstrate', 96), ('change', 96), ('give', 95), ('create', 94), ('address', 94), ('suggest', 91), ('model', 86), ('contribute', 86), ('generate', 85), ('build', 84), ('optimize', 84), ('employ', 83), ('aim', 82), ('investigate', 82), ('result', 81), ('project', 79), ('focus', 79), ('sense', 77), ('explore', 77), ('utilize', 77), ('classify', 77), ('enhance', 76), ('control', 76), ('allow', 75), ('forecast', 75), ('decrease', 75), ('ensure', 71), ('design', 71), ('understand', 70), ('play', 70), ('conduct', 69), ('face', 68), ('observe', 66), ('automate', 65), ('derive', 64), ('extract', 64), ('discuss', 64), ('associate', 63), ('accord', 62), ('boost', 61), ('assist', 60), ('do', 60), ('follow', 59), ('expect', 59)][('agricultural', 758), ('different', 414), ('such', 392), ('environmental', 367), ('deep', 365), ('sustainable', 326), ('-', 318), ('high', 301), ('artificial', 296), ('future', 277), ('neural', 261), ('global', 259), ('smart', 257), ('other', 249), ('new', 224), ('important', 220), ('various', 189), ('random', 184), ('climatic', 183), ('current', 170), ('large', 169), ('economic', 166), ('significant', 151), ('remote', 149), ('major', 140), ('real', 140), ('higher', 132), ('long', 131), ('spatial', 131), ('accurate', 129), ('main', 128), ('many', 128), ('best', 127), ('specific', 121), ('efficient', 120), ('effective', 120), ('human', 119), ('low', 119), ('available', 113), ('digital', 111), ('suitable', 108), ('more', 106), ('intelligent', 105), ('optimal', 104), ('big', 103), ('early', 103), ('extreme', 101), ('key', 100), ('average', 100), ('recent', 96), ('several', 95), ('multi', 95), ('better', 91), ('complex', 90), ('multiple', 90), ('essential', 90), ('traditional', 86), ('local', 84), ('potential', 83), ('meteorological', 83), ('predictive', 83), ('overall', 83), ('novel', 82), ('most', 81), ('statistical', 80), ('regional', 79), ('linear', 79), ('natural', 77), ('temporal', 77), ('short', 76), ('ecological', 76), ('critical', 71), ('present', 70), ('experimental', 70), ('crucial', 69), ('non', 69), ('genetic', 67), ('maximum', 67), ('highest', 66), ('relative', 65), ('able', 65), ('first', 64), ('convolutional', 63), ('possible', 62), ('total', 62), ('small', 61), ('annual', 61), ('appropriate', 59), ('mobile', 59), ('adaptive', 57), ('historical', 57), ('good', 57), ('technological', 57), ('negative', 56), ('conventional', 56), ('advanced', 55), ('agronomic', 52), ('social', 52), ('daily', 51), ('rapid', 50)]{'climate': 44, 'environmental': 4, 'weather': 3, 'farming': 2, 'using': 2, 'different': 2, 'adverse': 2, 'greenhouse': 1, 'extreme': 1, 'temperature': 1, 'past': 1, 'nitrogen': 1, 'rainfall': 1, 'fruit': 1, 'fvw': 1, 'future': 1, 'irrigation': 1, 'projected': 1, 'pests': 1, 'water': 1, 'low': 1, 'excess': 1, 'environment': 1, 'participating': 1, 'crop': 1, 'dr': 1, 'inter': 1, 'changing': 1, 'higher': 1, 'conversion': 1, 'meteorological': 1, 'price': 1, 'minimum': 1, 'biodiversity': 1, 'cattle': 1, 'climatic': 1, 'external': 1, 'carbon': 1}{'government': 2, 'ai': 2, 'remote': 1, 'climate': 1, 'projected': 1, 'organic': 1, 'water': 1, 'rainfed': 1, 'innovation': 1, 'hydro': 1, 'consumers': 1, 'particulate': 1, 'average': 1, 'weather': 1, 'learning': 1, 'socio': 1, 'co2': 1, 'technology': 1, 'sa': 1, 'smart': 1, 'iot': 1, 'various': 1, 'seed': 1, 'geospatial': 1}[('crop yield prediction climate change', 0.6067), ('predictive agriculture', 0.5937), ('arid environments crop yield prediction', 0.5866), ('future climate scenarios crop yield modeling', 0.5782), ('crop prediction models', 0.5745), ('satellite data track crop growth condition', 0.565), ('statistical crop modeling', 0.5616), ('machine learning methods agriculture', 0.5582), ('classifiers agriculture', 0.5577), ('crop yield prediction studies', 0.5552), ('agricultural crop yield prediction', 0.555), ('rapid climate change crop', 0.5511), ('agricultural prediction values', 0.5497), ('agricultural climate change', 0.5488), ('agrometeorological big data climate change', 0.5473), ('effective crop yield prediction', 0.5465), ('crop yield prediction models', 0.5464), ('crop yield prediction environment', 0.5423), ('agricultural predictions', 0.5418), ('crop prediction model', 0.54), ('crop adaptation measures', 0.5354), ('better crop yield prediction', 0.5349), ('accurate crop yield prediction', 0.5323), ('accurate crop classification', 0.5321), ('agricultural yield prediction', 0.5321), ('crop yield dataset', 0.5319), ('complete crop yield prediction framework', 0.5318), ('machine learning approach climate change', 0.5314), ('statistical crop models', 0.5309), ('precision agriculture', 0.5304), ('accurate phenological predictions', 0.5301), ('multispectral imagery food demand', 0.5293), ('crop prediction system', 0.5292), ('crop prediction', 0.5278), ('accurate crop prediction results', 0.5273), ('crop yield prediction', 0.5258), ('agricultural decision support applications', 0.522), ('climate changes agriculture', 0.5202), ('crop type prediction', 0.5194), ('scale crop yield prediction', 0.519), ('deep learning crop yield estimates', 0.5167), ('uav agricultural remote sensing', 0.516), ('machine learning approach farmers', 0.5158), ('agricultural big data', 0.5149), ('agricultural dataset', 0.5137), ('farming futures climate change research program', 0.5134), ('efficient crop yield prediction', 0.5129), ('climate prediction', 0.5111), ('many remote sensing applications', 0.5109), ('regional crop data', 0.5106)]
8
68920.109infrastructure_industry6_energy_building_smart_based['energy', 'building', 'smart', 'based', 'environment', 'learning', 'sustainable', 'design', 'buildings', 'iot', 'systems', 'paper', 'proposed', 'performance', 'cities', 'consumption', 'traffic', 'urban', 'using', 'development', 'intelligence', 'city', 'energy consumption', 'network', 'machine', 'sustainability', 'decision', 'artificial', 'time', 'machine learning'][('smartwork', 0.4416), ('metaheuristics', 0.4075), ('heuristics', 0.4071), ('metaheuristic', 0.379), ('blueprinting', 0.3459), ('optimizing', 0.3428), ('optimising', 0.3341), ('hvac', 0.3248), ('smartpls', 0.3233), ('utilities', 0.3213), ('optimizer', 0.3137), ('building', 0.313), ('optimisations', 0.3122), ('renovation', 0.3105), ('automation', 0.3102), ('optimization', 0.3099), ('architectural', 0.3063), ('algorithms', 0.3052), ('industrial', 0.3022), ('heuristic', 0.3019), ('renovate', 0.3012), ('optimise', 0.3004), ('optimass', 0.3003), ('optimize', 0.3002), ('sustainability', 0.2993), ('architecture', 0.2978), ('architect', 0.2916), ('efficacity', 0.2904), ('optimizations', 0.2903), ('annealing', 0.2902), ('optimises', 0.2858), ('optimisation', 0.2841), ('architectures', 0.2828), ('architects', 0.2808), ('designbuilder', 0.28), ('construction', 0.2795), ('workflows', 0.2793), ('renovations', 0.2785), ('retrofitting', 0.2783), ('robots', 0.2778), ('energyplus', 0.2756), ('fuzzysets', 0.2755), ('iot', 0.2742), ('ai', 0.2736), ('algorithm', 0.2724), ('zigbee', 0.2722), ('buildings', 0.2706), ('informatics', 0.2685), ('optimum', 0.2677), ('dbms', 0.2664)][('intelligent building', 0.5606), ('building automation', 0.5404), ('smart building', 0.5329), ('smart industrial', 0.5102), ('intelligent manufacturing', 0.5093), ('buildings smart', 0.5091), ('sustainable renovation', 0.5089), ('sustainability optimization', 0.5019), ('intelligent buildings', 0.5008), ('smart buildings', 0.497), ('buildings optimization', 0.4865), ('environmental optimization', 0.4857), ('smart manufacturing', 0.485), ('smartwork designing', 0.4828), ('intelligent environment', 0.4813), ('architecture intelligently', 0.481), ('building optimisation', 0.4801), ('manufacturing smart', 0.4799), ('architecture sustainability', 0.4797), ('renovation energy', 0.4757), ('algorithms industrial', 0.4755), ('optimization buildings', 0.4753), ('industrial smart', 0.4748), ('sustainability intelligent', 0.4745), ('efficient buildings', 0.4733), ('sustainability buildings', 0.473), ('smart environment', 0.4707), ('sustainability building', 0.47), ('optimizing building', 0.469), ('smart construction', 0.4689), ('sustainability ai', 0.4659), ('sustainable building', 0.4639), ('design sustainability', 0.4635), ('buildings sustainable', 0.4625), ('sustainability construction', 0.4609), ('automation sustainability', 0.4605), ('optimised building', 0.46), ('buildings eco', 0.459), ('sustainability industrial', 0.4587), ('smart industries', 0.4584), ('industrial automation', 0.4577), ('intelligent optimization', 0.457), ('smart environments', 0.4562), ('energy optimisation', 0.455), ('optimized building', 0.4549), ('building sustainable', 0.4547), ('sustainable operations', 0.4542), ('smart ecologies', 0.4541), ('smart industry', 0.4539), ('smartwork project', 0.4534)]machine learning: 484, artificial intelligence: 332, energy consumption: 326, climate change: 214, deep learning: 211, smart cities: 203, smart city: 162, building energy: 147, decision support: 147, real time: 142, sustainable development: 141, reinforcement learning: 137, decision making: 136, energy efficiency: 136, things iot: 103, learning based: 101, neural network: 101, energy efficient: 89, intelligence ai: 89, global warming: 79, thermal comfort: 78, learning algorithms: 69, cloud computing: 65, energy use: 62, iot devices: 61, energy performance: 60, built environment: 58, deep reinforcement: 56, paper presents: 56, neural networks: 52, long term: 49, life cycle: 48, learning techniques: 47, large scale: 46, paper proposes: 46, learning ml: 45, traffic congestion: 44, air quality: 43, sustainable urban: 43, carbon dioxide: 42, artificial neural: 41, edge computing: 40, recent years: 40, intrusion detection: 39, multi agent: 39, wireless sensor: 39, energy management: 38, renewable energy: 38, short term: 38, air conditioning: 37, energy harvesting: 37, energy demand: 36, real world: 36, residential buildings: 36, sustainable smart: 36, energy saving: 35, power consumption: 35, proposed approach: 35, building design: 34, support vector: 34, using machine: 34, ai based: 32, greenhouse gas: 32, learning approach: 32, proposed framework: 32, smart buildings: 32, air pollution: 31, based approach: 31, decision makers: 31, digital twin: 31, federated learning: 31, multi objective: 31, cooling energy: 30, random forest: 30, sustainable cities: 30, learning algorithm: 29, urban development: 29, carbon emissions: 28, traffic flow: 28, waste management: 28, carbon footprint: 27, transfer learning: 27, energy savings: 26, sensor networks: 26, support systems: 26, transportation systems: 26, convolutional neural: 25, cyber physical: 25, green building: 25, low cost: 25, sensor network: 25, using deep: 25, covid 19: 24, low carbon: 24, urban environment: 24, autonomous vehicles: 23, communication technologies: 23, decision tree: 23, energy usage: 23, gas emissions: 23artificial intelligence ai: 88, deep reinforcement learning: 56, machine learning algorithms: 48, machine learning ml: 45, machine learning based: 39, building energy consumption: 36, using machine learning: 34, deep learning based: 32, machine learning techniques: 30, sustainable smart cities: 24, artificial neural network: 23, carbon dioxide emissions: 22, greenhouse gas emissions: 22, short term memory: 22, decision support systems: 20, wireless sensor networks: 20, sustainable development goals: 19, multi objective optimization: 18, ant colony optimization: 17, artificial neural networks: 17, building energy performance: 17, sustainable urban development: 17, convolutional neural network: 16, reinforcement learning rl: 16, using deep learning: 16, wireless sensor network: 16, artificial intelligence based: 15, multi criteria decision: 15, reduce energy consumption: 15, support vector machine: 15, air conditioning hvac: 13, energy consumption prediction: 13, term memory lstm: 13, building energy simulation: 12, cooling energy consumption: 12, cyber physical systems: 12, deep learning dl: 12, machine learning algorithm: 12, reinforcement learning based: 12, smart city applications: 12, smart city environment: 12, support vector regression: 12, using artificial intelligence: 12, criteria decision making: 11, decision making process: 11, deep learning techniques: 11, global warming impact: 11, learning based approach: 11, machine learning approach: 11, real time monitoring: 11, reinforcement learning drl: 11, renewable energy sources: 11, traffic flow prediction: 11, unmanned aerial vehicles: 11, agent reinforcement learning: 10, artificial intelligence techniques: 10, bp neural network: 10, building energy use: 10, building information modeling: 10, carbon dioxide emission: 10, cloud computing environment: 10, deep learning algorithms: 10, deep neural network: 10, early design stage: 10, intelligent transportation systems: 10, multi agent reinforcement: 10, neural network cnn: 10, based decision support: 9, convolutional neural networks: 9, decision support tool: 9, deep neural networks: 9, ecological carrying capacity: 9, life cycle assessment: 9, machine learning technique: 9, real time traffic: 9, sdn based cloud: 9, sustainable building design: 9, vector machine svm: 9, building energy efficiency: 8, coal pillar stagger: 8, design methodology approach: 8, energy harvesting eh: 8, future smart cities: 8, green intelligent ports: 8, high rise buildings: 8, life cycle cost: 8, machine learning approaches: 8, total energy consumption: 8, using reinforcement learning: 8, absolute percentage error: 7, aerial vehicles uavs: 7, air conditioning systems: 7, analytic hierarchy process: 7, building energy management: 7, covid 19 pandemic: 7, cycle assessment lca: 7, deep learning algorithm: 7, deep transfer learning: 7, federated learning fl: 7, government ecological audit: 7[('energy', 1636), ('data', 1268), ('system', 901), ('environment', 822), ('learning', 777), ('model', 777), ('systems', 575), ('paper', 566), ('building', 544), ('machine', 540), ('performance', 528), ('design', 520), ('development', 499), ('%', 470), ('buildings', 451), ('intelligence', 437), ('study', 434), ('time', 432), ('network', 429), ('results', 424), ('research', 424), ('consumption', 412), ('analysis', 398), ('cities', 397), ('decision', 394), ('approach', 382), ('climate', 368), ('information', 361), ('management', 360), ('models', 357), ('sustainability', 353), ('city', 334), ('traffic', 333), ('technologies', 308), ('framework', 305), ('method', 291), ('technology', 290), ('detection', 285), ('efficiency', 278), ('internet', 276), ('control', 275), ('use', 269), ('prediction', 267), ('applications', 258), ('devices', 253), ('networks', 246), ('change', 245), ('things', 239), ('methods', 236), ('algorithms', 230), ('techniques', 228), ('process', 224), ('environments', 222), ('support', 219), ('security', 206), ('challenges', 206), ('accuracy', 205), ('optimization', 203), ('quality', 199), ('impact', 199), ('application', 197), ('work', 197), ('solutions', 196), ('carbon', 195), ('power', 185), ('air', 183), ('construction', 183), ('case', 182), ('-', 182), ('cost', 180), ('simulation', 178), ('communication', 177), ('life', 176), ('emissions', 173), ('infrastructure', 173), ('services', 164), ('sensor', 161), ('order', 161), ('level', 161), ('cloud', 160), ('resources', 158), ('monitoring', 157), ('computing', 153), ('conditions', 152), ('factors', 152), ('comfort', 152), ('problem', 150), ('architecture', 148), ('temperature', 147), ('solution', 144), ('sensors', 144), ('evaluation', 143), ('transportation', 141), ('reinforcement', 140), ('demand', 138), ('number', 137), ('vehicles', 137), ('world', 134), ('knowledge', 131), ('health', 131)][('use', 1204), ('base', 1083), ('propose', 772), ('build', 419), ('provide', 416), ('develop', 370), ('improve', 339), ('learn', 336), ('make', 330), ('show', 304), ('reduce', 296), ('present', 272), ('have', 261), ('increase', 243), ('achieve', 234), ('predict', 220), ('include', 217), ('exist', 210), ('apply', 203), ('consider', 198), ('evaluate', 197), ('integrate', 190), ('enable', 189), ('compare', 189), ('identify', 168), ('enhance', 165), ('support', 156), ('address', 155), ('design', 152), ('drive', 151), ('optimize', 150), ('analyze', 149), ('require', 148), ('perform', 142), ('demonstrate', 142), ('become', 142), ('generate', 142), ('create', 139), ('implement', 136), ('aim', 134), ('focus', 134), ('help', 133), ('relate', 131), ('collect', 131), ('introduce', 128), ('need', 127), ('take', 120), ('discuss', 114), ('combine', 108), ('lead', 106), ('detect', 103), ('cool', 101), ('be', 100), ('find', 100), ('train', 99), ('assess', 98), ('monitor', 97), ('select', 96), ('obtain', 96), ('explore', 93), ('allow', 92), ('utilize', 91), ('ensure', 91), ('give', 87), ('test', 85), ('result', 84), ('contribute', 80), ('conduct', 77), ('offer', 76), ('estimate', 76), ('solve', 76), ('distribute', 75), ('investigate', 75), ('determine', 74), ('establish', 72), ('involve', 71), ('emerge', 71), ('connect', 71), ('promote', 71), ('call', 70), ('manage', 69), ('deploy', 69), ('define', 68), ('accord', 66), ('indicate', 65), ('change', 64), ('cause', 64), ('model', 61), ('maintain', 61), ('adopt', 59), ('grow', 58), ('study', 58), ('affect', 58), ('minimize', 58), ('consume', 57), ('play', 57), ('leverage', 55), ('know', 55), ('save', 55), ('reveal', 54)][('smart', 838), ('sustainable', 710), ('urban', 459), ('artificial', 406), ('environmental', 388), ('such', 375), ('-', 367), ('deep', 340), ('new', 308), ('different', 297), ('real', 263), ('intelligent', 261), ('efficient', 242), ('various', 223), ('human', 208), ('high', 206), ('other', 203), ('multi', 201), ('global', 187), ('economic', 187), ('future', 172), ('thermal', 164), ('green', 159), ('neural', 157), ('social', 153), ('optimal', 150), ('many', 149), ('large', 149), ('effective', 145), ('dynamic', 142), ('low', 139), ('significant', 135), ('digital', 132), ('important', 132), ('current', 131), ('indoor', 128), ('key', 126), ('industrial', 123), ('wireless', 120), ('more', 119), ('public', 117), ('better', 116), ('novel', 114), ('multiple', 111), ('physical', 108), ('recent', 104), ('several', 104), ('main', 98), ('autonomous', 98), ('critical', 97), ('mobile', 96), ('computational', 95), ('long', 95), ('residential', 95), ('big', 93), ('complex', 92), ('major', 92), ('experimental', 86), ('traditional', 83), ('overall', 82), ('non', 82), ('potential', 81), ('available', 81), ('iot', 80), ('possible', 79), ('natural', 79), ('spatial', 76), ('local', 76), ('ecological', 76), ('accurate', 75), ('advanced', 72), ('adaptive', 71), ('secure', 69), ('average', 68), ('reliable', 64), ('comprehensive', 64), ('rapid', 64), ('regional', 63), ('hybrid', 62), ('single', 62), ('essential', 62), ('specific', 62), ('solar', 62), ('same', 62), ('best', 61), ('predictive', 61), ('higher', 61), ('virtual', 61), ('modern', 61), ('able', 60), ('first', 60), ('cloud', 60), ('small', 60), ('particular', 60), ('operational', 60), ('total', 59), ('innovative', 57), ('necessary', 56), ('short', 55), ('most', 55)]{'climate': 12, 'policy': 3, 'pavement': 2, 'alternative': 2, 'aviation': 2, 'building': 2, 'thermostat': 2, 'design': 1, '24': 1, 'municipal': 1, 'transporting': 1, 'social': 1, 'ai': 1, 'outdoor': 1, 'u': 1, 'larger': 1, 'supplanting': 1, 'generating': 1, 'local': 1, 'future': 1, 'resource': 1, 'iot': 1, 'living': 1, '3d': 1, 'enterprise': 1, 'jin': 1, 'residential': 1, 'predicted': 1, 'certain': 1, 'spatial': 1, 'investment': 1, 'green': 1, 'machine': 1, 'various': 1, 'technology': 1, 'buildings': 1, 'clustering': 1, 'influenceable': 1, 'setpoint': 1, 'mobility': 1}{'building': 2, 'artificial': 2, 'enabling': 1, 'behavioural': 1, 'various': 1, 'dynamic': 1, 'spatial': 1, 'users': 1, 'government': 1, 'infrastructure': 1, 'microalloying': 1, 'alloying': 1, 'ai': 1, 'ml': 1, 'sustainable': 1, 'machine': 1, 'supervisory': 1, 'landscape': 1, 'sms': 1, 'imaging': 1, 'strategic': 1, 'information': 1}[('dynamic intelligent building decision', 0.5712), ('intelligent building platform', 0.5662), ('building energy optimization system', 0.5613), ('intelligent building', 0.5606), ('energy efficiency automation', 0.5446), ('smart building', 0.5329), ('smart green building', 0.5305), ('sustainable office building renovation', 0.5278), ('residential building optimisation', 0.5276), ('evolutionary building placement optimization system', 0.521), ('dynamic intelligent building retrofit decision', 0.52), ('intelligent sustainable systems', 0.5187), ('intelligent building energy management system research project', 0.5152), ('intelligent building environments', 0.5148), ('sustainable building renovation', 0.5106), ('smart building management', 0.5094), ('intelligent manufacturing', 0.5093), ('intelligent autonomic smart buildings', 0.5036), ('energy optimization software', 0.5028), ('sustainable renovation strategies', 0.5028), ('intelligent buildings', 0.5008), ('smart environment systems', 0.4995), ('artificial intelligence construction projects', 0.4992), ('energy efficiency projects', 0.499), ('sustainable renovation actions', 0.4971), ('smart buildings', 0.497), ('efficient building design selection', 0.4931), ('smart building systems', 0.4928), ('green smart environments', 0.4923), ('smart city buildings', 0.4917), ('true smart building', 0.4913), ('sustainable building renovation processes', 0.4912), ('energy efficiency goals', 0.4898), ('smart building system', 0.4879), ('smart system projects', 0.4877), ('building automation system', 0.4875), ('modern smart building', 0.4865), ('sustainable decision support system', 0.4865), ('energy decision support system', 0.4858), ('smart manufacturing systems', 0.485), ('smart manufacturing', 0.485), ('efficient building energy management systems', 0.4837), ('whole building life cycle assessment', 0.4823), ('intelligent environment', 0.4813), ('intelligent building sites management', 0.4808), ('intelligent environmental plan', 0.4805), ('harmonious smart environment', 0.4791), ('smart building energy management', 0.4787), ('energy consumption optimisation', 0.4762), ('optimise building energy performance', 0.4757)]
9
72440.03landuse_urban_planning7_urban_built_land_environment['urban', 'built', 'land', 'environment', 'cities', 'spatial', 'sustainable', 'city', 'learning', 'heat', 'built environment', 'development', 'landscape', 'street', 'areas', 'based', 'machine', 'machine learning', 'using', 'planning', 'lst', 'urbanization', 'area', 'temperature', 'climate', 'use', 'surface', 'high', 'ecological', 'used'][('landsat', 0.405), ('urbanization', 0.3801), ('urbanizing', 0.3794), ('urbanisation', 0.3654), ('lidar', 0.3584), ('classifiers', 0.3527), ('openstreetmap', 0.3518), ('slummificationand', 0.3457), ('urbanity', 0.3448), ('climate', 0.3315), ('geostatistical', 0.3283), ('desertification', 0.3225), ('meteorology', 0.3222), ('climates', 0.3217), ('streetscapes', 0.3215), ('gis', 0.3191), ('urbanism', 0.3152), ('urbanized', 0.3123), ('urbanists', 0.309), ('svm', 0.3033), ('cities', 0.3018), ('classifier', 0.3015), ('land', 0.3007), ('datasets', 0.2977), ('convolutional', 0.2928), ('landcover', 0.2908), ('landforms', 0.2884), ('geographers', 0.2876), ('classification', 0.2825), ('urban', 0.2817), ('streetscape', 0.2806), ('geodata', 0.278), ('maps', 0.2772), ('predicting', 0.2767), ('roofscapes', 0.2764), ('forecasting', 0.2762), ('geographical', 0.275), ('imageries', 0.2747), ('vegetation', 0.2742), ('clustering', 0.2726), ('mapping', 0.2724), ('neighbourhoods', 0.2719), ('hyperspectral', 0.2718), ('meteorological', 0.2717), ('subtropical', 0.2716), ('cnns', 0.2704), ('neighborhoods', 0.2689), ('city', 0.2685), ('forests', 0.2677), ('geospatial', 0.2676)][('classifying urban', 0.5284), ('urbanization classification', 0.5218), ('forecasting urban', 0.5205), ('urbanisation climate', 0.5201), ('calculated urbanization', 0.5135), ('climate urban', 0.5116), ('meteorological urban', 0.5116), ('urban climate', 0.5081), ('predicting land', 0.5034), ('predicting urban', 0.503), ('urban climates', 0.4972), ('urban landcover', 0.497), ('mapping urban', 0.4964), ('estimating urban', 0.495), ('urban detection', 0.4923), ('urbanization sustainable', 0.4895), ('cities climate', 0.4881), ('ndvi urbanization', 0.4874), ('predicting climate', 0.4853), ('urbanization temperature', 0.4843), ('urbanization climate', 0.4839), ('urban ecologicalization', 0.4832), ('environment classification', 0.4794), ('urbanization accelerating', 0.4762), ('detecting urban', 0.4753), ('landsat city', 0.4749), ('urban sustainability', 0.474), ('sustainable urban', 0.4731), ('urbanization sustainability', 0.4727), ('phenotyping urban', 0.4709), ('urbanization using', 0.4698), ('analysing climate', 0.4688), ('modelling urban', 0.4683), ('urbanization area', 0.4675), ('analyzing urban', 0.4671), ('urbanization land', 0.4669), ('vegetation urban', 0.4665), ('urbanized land', 0.4658), ('urbanizing tropical', 0.4656), ('urban mapping', 0.4654), ('urban land', 0.4646), ('classification urban', 0.4646), ('urban biophysical', 0.4641), ('urbanization roofpedia', 0.463), ('environment urbanization', 0.4625), ('classification streetscape', 0.4622), ('urbanized lands', 0.4618), ('urban sustainable', 0.4616), ('assessments urbanization', 0.4609), ('land dataset', 0.4608)]machine learning: 209, built environment: 115, climate change: 99, land use: 85, sustainable development: 72, deep learning: 70, surface temperature: 59, urban heat: 58, land cover: 57, urban planning: 57, remote sensing: 53, land surface: 50, urban areas: 49, heat island: 46, street view: 45, random forest: 42, sustainable urban: 42, urban environment: 36, urban growth: 36, artificial intelligence: 35, air temperature: 32, high resolution: 27, urban expansion: 27, urban form: 27, large scale: 26, neural network: 25, urban landscape: 25, using machine: 24, view images: 24, urban development: 22, urban morphology: 22, ecosystem services: 21, socio economic: 21, temperature lst: 21, urban thermal: 20, ecological environment: 19, urban area: 19, urban climate: 19, use land: 19, decision making: 18, rapid urbanization: 18, thermal environment: 18, time series: 18, urban land: 18, urban planners: 18, yellow river: 18, learning algorithms: 17, linear regression: 17, thermal comfort: 17, urban environments: 17, urban vitality: 17, cellular automata: 16, decision makers: 16, energy consumption: 16, high density: 16, artificial neural: 15, global climate: 15, human activities: 15, learning ml: 15, local climate: 15, street greenery: 15, uhi effect: 15, carbon emissions: 14, geographic information: 14, learning based: 14, river basin: 14, sustainable cities: 14, urban mobility: 14, forest rf: 13, high spatial: 13, island uhi: 13, learning techniques: 13, normalized difference: 13, spatial distribution: 13, spatial resolution: 13, spatio temporal: 13, united states: 13, urban built: 13, urban ecological: 13, vegetation index: 13, ecological security: 12, green spaces: 12, landscape design: 12, learning approach: 12, water bodies: 12, active travel: 11, computer vision: 11, decision support: 11, global warming: 11, land fragmentation: 11, long term: 11, low carbon: 11, multiple linear: 11, satellite images: 11, spatial patterns: 11, surface urban: 11, urban design: 11, using deep: 11, water conservation: 11, water yield: 11land surface temperature: 45, urban heat island: 45, street view images: 24, using machine learning: 24, surface temperature lst: 21, land use land: 19, use land cover: 19, sustainable urban development: 17, machine learning algorithms: 15, machine learning ml: 15, artificial neural network: 13, heat island uhi: 13, random forest rf: 13, urban ecological environment: 12, yellow river basin: 12, multiple linear regression: 11, surface urban heat: 11, using deep learning: 11, difference vegetation index: 10, normalized difference vegetation: 10, sustainable urban planning: 10, vegetation land fragmentation: 10, global climate change: 9, heat island effect: 9, land cover lulc: 9, machine learning based: 9, machine learning techniques: 9, urban built environment: 9, urban land use: 9, carbon sequestration potential: 8, high spatial resolution: 8, machine learning approach: 8, urban thermal environment: 8, vegetation index ndvi: 8, land use cover: 7, local climate zone: 7, neural network ann: 7, new york city: 7, rural landscape elements: 7, sustainable development goals: 7, urban heat islands: 7, absolute error mae: 6, cellular automata ca: 6, climate change mitigation: 6, heat related health: 6, hourly air temperature: 6, local climate zones: 6, machine learning algorithm: 6, machine learning solutions: 6, mass real estate: 6, outdoor thermal comfort: 6, real estate valuation: 6, remote sensing images: 6, square error rmse: 6, urban landscape design: 6, urban surface temperature: 6, air temperature mapping: 5, artificial intelligence ai: 5, based machine learning: 5, built settlement extents: 5, deep learning based: 5, dimensional built environment: 5, extreme temperature indices: 5, field variance index: 5, google street view: 5, greenhouse gas emissions: 5, high density cities: 5, level built environment: 5, pro social behavior: 5, ridesplitting adoption rate: 5, significant positive effect: 5, street view imagery: 5, thermal field variance: 5, urban form interventions: 5, urban landscape dynamics: 5, urban thermal field: 5, using random forest: 5, using street view: 5, artificial intelligence based: 4, built environment stock: 4, carbon dioxide emissions: 4, convolutional neural network: 4, criteria spatial decision: 4, deep learning techniques: 4, ecosystem service value: 4, gradient boosting decision: 4, gradient boosting machine: 4, high resolution satellite: 4, international horticultural exposition: 4, island uhi effect: 4, land cover maps: 4, large spatial scales: 4, learning ml algorithms: 4, main urban area: 4, multi criteria spatial: 4, potential tod areas: 4, residential land growth: 4, shared socioeconomic pathways: 4, socio economic indicators: 4, southeastern united states: 4[('data', 448), ('environment', 289), ('land', 271), ('study', 269), ('machine', 221), ('learning', 221), ('model', 217), ('cities', 210), ('climate', 207), ('development', 202), ('areas', 169), ('results', 165), ('%', 164), ('analysis', 157), ('city', 147), ('temperature', 143), ('change', 143), ('heat', 136), ('landscape', 133), ('area', 131), ('use', 124), ('planning', 121), ('research', 116), ('method', 113), ('surface', 107), ('population', 106), ('models', 99), ('scale', 98), ('street', 98), ('time', 96), ('methods', 94), ('factors', 94), ('approach', 93), ('urbanization', 91), ('water', 91), ('vegetation', 88), ('lst', 87), ('level', 87), ('growth', 84), ('effects', 83), ('studies', 83), ('cover', 79), ('information', 79), ('framework', 75), ('images', 74), ('effect', 73), ('health', 73), ('resolution', 70), ('variables', 67), ('sustainability', 67), ('design', 67), ('quality', 67), ('patterns', 65), ('carbon', 64), ('density', 64), ('characteristics', 64), ('features', 63), ('changes', 63), ('energy', 60), ('paper', 60), ('emissions', 60), ('impact', 60), ('network', 59), ('mobility', 59), ('index', 58), ('decision', 57), ('travel', 57), ('impacts', 57), ('air', 57), ('regression', 55), ('transportation', 55), ('view', 55), ('environments', 53), ('system', 53), ('mapping', 53), ('accuracy', 53), ('ecosystem', 51), ('forest', 50), ('classification', 49), ('c', 49), ('relationship', 49), ('indicators', 49), ('transport', 48), ('pattern', 47), ('space', 46), ('management', 46), ('case', 45), ('expansion', 45), ('strategies', 44), ('assessment', 43), ('potential', 43), ('maps', 41), ('prediction', 41), ('intelligence', 41), ('distribution', 41), ('world', 41), ('datasets', 41), ('people', 39), ('buildings', 38), ('cycling', 38)][('use', 389), ('build', 251), ('base', 235), ('provide', 142), ('show', 135), ('have', 125), ('propose', 101), ('develop', 100), ('learn', 91), ('increase', 86), ('predict', 78), ('identify', 73), ('relate', 66), ('include', 63), ('improve', 63), ('contribute', 61), ('analyze', 61), ('apply', 60), ('understand', 58), ('explore', 58), ('make', 58), ('find', 54), ('demonstrate', 51), ('reduce', 51), ('affect', 50), ('model', 49), ('assess', 48), ('combine', 47), ('evaluate', 47), ('help', 46), ('become', 46), ('achieve', 45), ('exist', 44), ('compare', 43), ('estimate', 42), ('reveal', 42), ('support', 41), ('indicate', 41), ('consider', 40), ('need', 40), ('examine', 39), ('present', 38), ('integrate', 38), ('create', 36), ('require', 35), ('investigate', 35), ('associate', 34), ('aim', 34), ('measure', 33), ('be', 33), ('quantify', 32), ('promote', 32), ('address', 31), ('conduct', 31), ('lead', 31), ('extract', 31), ('mitigate', 30), ('generate', 30), ('enhance', 30), ('capture', 30), ('influence', 29), ('drive', 29), ('suggest', 28), ('take', 28), ('sense', 28), ('focus', 28), ('change', 28), ('perform', 28), ('obtain', 28), ('study', 27), ('determine', 27), ('select', 25), ('represent', 24), ('establish', 24), ('derive', 24), ('employ', 23), ('give', 22), ('result', 22), ('grow', 22), ('decrease', 22), ('remain', 21), ('carry', 21), ('facilitate', 21), ('share', 20), ('map', 20), ('construct', 20), ('plan', 20)][('urban', 946), ('sustainable', 233), ('spatial', 210), ('high', 119), ('such', 113), ('-', 111), ('environmental', 108), ('global', 102), ('ecological', 96), ('different', 90), ('human', 90), ('new', 77), ('deep', 76), ('significant', 70), ('future', 68), ('important', 67), ('local', 67), ('thermal', 66), ('economic', 66), ('temporal', 60), ('green', 58), ('social', 56), ('other', 55), ('large', 54), ('artificial', 54), ('remote', 53), ('multi', 51), ('uhi', 50), ('big', 50), ('random', 49), ('open', 48), ('natural', 46), ('low', 44), ('public', 44), ('higher', 41), ('multiple', 40), ('effective', 39), ('rapid', 38), ('rural', 38), ('more', 35), ('current', 35), ('main', 35), ('negative', 35), ('statistical', 34), ('neural', 32), ('regional', 32), ('various', 32), ('geographic', 31), ('key', 31), ('overall', 31), ('physical', 31), ('visual', 31), ('many', 29), ('several', 29), ('real', 29), ('active', 29), ('novel', 28), ('recent', 28), ('major', 28), ('comprehensive', 28), ('complex', 27), ('essential', 27), ('socioeconomic', 27), ('average', 26), ('mean', 26), ('efficient', 25), ('geospatial', 25), ('available', 24), ('linear', 24), ('specific', 24), ('residential', 23), ('critical', 23), ('potential', 23), ('crucial', 22), ('quantitative', 22), ('positive', 22), ('spatiotemporal', 22), ('traditional', 22), ('smart', 21), ('possible', 21), ('cultural', 21), ('common', 20), ('extreme', 20), ('same', 20)]{'urban': 4, 'built': 2, 'climate': 2, 'construction': 2, 'regional': 1, 'spatiotemporal': 1, 'land': 1, 'active': 1, 'pairwise': 1, 'fractional': 1, 'lu': 1, 'trees': 1, 'similar': 1, 'spatially': 1}{'cycling': 2, 'urban': 2, 'nonmotorized': 1, 'remote': 1, 'background': 1, 'ridesourcing': 1, 'forestry': 1, 'centrality': 1, 'greenery': 1}[('new urban environment classification method', 0.6273), ('urban surface temperature prediction', 0.6005), ('urban planning machine learning models', 0.5922), ('urban climate assessments', 0.5917), ('spatiotemporal land use regression', 0.5911), ('machine learning models climate change', 0.589), ('urban land surface temperature', 0.586), ('urban land surface temperatures', 0.5856), ('new urban surface temperature prediction model', 0.5826), ('urban climate change', 0.5809), ('urban land cover characteristics', 0.5804), ('urban local climate zones classification', 0.5778), ('urban climate data', 0.5774), ('urban thermal environment data', 0.5605), ('such urban climate datasets', 0.5552), ('daytime ndvi data urbanization', 0.5493), ('high resolution land use', 0.5493), ('urban growth prediction', 0.5465), ('urban land use', 0.5461), ('urban data science', 0.5441), ('urban development classification models', 0.5425), ('urban land use growth scenarios', 0.5358), ('urban climate change factors', 0.5325), ('land use classification', 0.532), ('urban microclimate analysis', 0.5239), ('new dynamic urban thermal exposure index', 0.5232), ('dynamic urban thermal exposure index', 0.5207), ('urban climate research areas', 0.5181), ('land use analysis', 0.5122), ('urban big geospatial data', 0.5111), ('urban thermal environment research', 0.5089), ('urban climate', 0.5081), ('global urban sustainability science', 0.5076), ('urban land use planning', 0.5035), ('urban land surface models', 0.5029), ('urban surface temperature', 0.5017), ('urban landscape dynamics', 0.4993), ('global urban areas', 0.4983), ('urban pattern analysis', 0.498), ('global surface urban heat islands', 0.498), ('urban climates', 0.4972), ('urban landcover', 0.497), ('urban thermal characteristics', 0.497), ('accurate urban extent datasets', 0.4939), ('urban surface temperature sensitivity', 0.4938), ('sustainable urban growth', 0.4929), ('urban detection', 0.4923), ('urban environmental variables', 0.4899), ('urban biophysical indices', 0.4874), ('urban spatial pattern metrics', 0.4871)]
10
85400.066water_marine_envs8_sea_ice_ocean_learning['sea', 'ice', 'ocean', 'learning', 'water', 'climate', 'marine', 'machine', 'based', 'using', 'coastal', 'change', 'machine learning', 'sea ice', 'deep', 'surface', 'high', 'global', 'climate change', 'snow', 'temperature', 'images', 'resolution', 'coral', 'deep learning', 'satellite', 'permafrost', 'arctic', 'used', 'spatial'][('oceanography', 0.4102), ('climatologies', 0.4095), ('biogeochemistry', 0.3594), ('oceanographic', 0.3511), ('climatological', 0.3165), ('climatology', 0.3129), ('oceanographers', 0.3117), ('phytoplankton', 0.3045), ('ecoregions', 0.3043), ('kriging', 0.3032), ('ecoregionalization', 0.3015), ('bioregionalization', 0.3012), ('predicting', 0.2998), ('predictive', 0.2956), ('classifiers', 0.2917), ('rmses', 0.2887), ('meroplankton', 0.2792), ('biogeographic', 0.2775), ('bioregions', 0.2763), ('ecomorphology', 0.2758), ('forecasting', 0.275), ('predictors', 0.2704), ('rmse', 0.2689), ('biogeochemical', 0.265), ('bathymetry', 0.2636), ('planktonscope', 0.2618), ('estuarine', 0.2598), ('predicts', 0.2589), ('classifier', 0.2584), ('glms', 0.2573), ('forecasts', 0.2557), ('glm', 0.2533), ('prediction', 0.2513), ('eutrophication', 0.2479), ('predictor', 0.2477), ('predictions', 0.245), ('ecologies', 0.2415), ('seabeds', 0.2397), ('predict', 0.2393), ('accuracies', 0.2373), ('bioregion', 0.2371), ('climate', 0.2368), ('marinegeo', 0.2366), ('coralnet', 0.2359), ('reefs', 0.2356), ('planktonic', 0.2354), ('ecologist', 0.2338), ('ecohydrological', 0.2334), ('forecasting6', 0.233), ('predictands', 0.2329)][('oceanography predictions', 0.6108), ('ocean climatologies', 0.596), ('oceanographic biogeochemical', 0.5691), ('quantifying oceanographic', 0.569), ('ocean biogeochemistry', 0.5674), ('seawater prediction', 0.5564), ('prediction ocean', 0.5487), ('ocean forecasting', 0.5453), ('classifier oceanographic', 0.5428), ('sea bioregionalization', 0.5416), ('oceanography climate', 0.5348), ('biogeochemistry forecast', 0.5343), ('oceans climate', 0.532), ('forecasting ocean', 0.5318), ('ocean biogeochemical', 0.5272), ('classifying ocean', 0.5261), ('climate ocean', 0.5232), ('predict ocean', 0.5219), ('predict seawater', 0.5069), ('sea prediction', 0.5059), ('environmental prediction', 0.4997), ('oceans chemistry', 0.499), ('estimating estuarine', 0.4975), ('prediction seawater', 0.4972), ('ocean modelling', 0.4971), ('science oceans', 0.4949), ('biogeochemistry marine', 0.494), ('estimating ocean', 0.4926), ('sea predictions', 0.4897), ('ocean analyzed', 0.4889), ('predicting sea', 0.4886), ('sea classification', 0.4861), ('forecasting coral', 0.4832), ('oceanography global', 0.483), ('forecasting sea', 0.4823), ('oceans dataset', 0.4822), ('undersampled oceans', 0.482), ('ocean climate', 0.4817), ('validating climate', 0.4806), ('quantify oceans', 0.4802), ('ocean evaluation', 0.4799), ('changing oceanographic', 0.479), ('biogeochemistry predicted', 0.4777), ('ocean modeling', 0.4776), ('climate forecasting', 0.4776), ('ocean acidification', 0.4765), ('prediction sea', 0.4764), ('ocean carbon', 0.4754), ('oceans monitoring', 0.4753), ('climate prediction', 0.4742)]machine learning: 509, climate change: 427, deep learning: 286, sea ice: 237, remote sensing: 199, neural network: 153, sea level: 139, sea surface: 127, time series: 114, high resolution: 97, random forest: 94, long term: 90, global warming: 89, surface temperature: 74, neural networks: 71, artificial intelligence: 66, learning algorithms: 66, snow depth: 61, convolutional neural: 60, short term: 60, global climate: 58, water bodies: 56, arctic sea: 54, snow cover: 53, spatial resolution: 51, level rise: 49, support vector: 49, water quality: 49, learning based: 48, surface water: 47, term memory: 47, using machine: 47, large scale: 45, coral reefs: 42, learning techniques: 40, coastal areas: 39, satellite imagery: 38, spatial distribution: 38, forest rf: 37, water body: 37, square error: 36, water temperature: 36, coral reef: 35, vector machine: 35, aperture radar: 32, deep neural: 31, marine ecosystems: 31, synthetic aperture: 31, artificial neural: 30, passive microwave: 30, sar images: 30, spatio temporal: 30, error rmse: 29, using deep: 29, mass balance: 28, learning approach: 27, learning ml: 27, sustainable development: 27, wind speed: 27, land cover: 26, sensing images: 26, air temperature: 25, global ocean: 25, f1 score: 24, glacial lakes: 24, global scale: 24, google earth: 24, ice extent: 24, radar sar: 24, recent years: 24, satellite images: 24, learning approaches: 23, memory lstm: 23, temperature sst: 23, glacial lake: 22, image processing: 22, real time: 22, semantic segmentation: 22, species distribution: 22, water resources: 22, decision tree: 21, earth engine: 21, machine svm: 21, marine environment: 21, qinghai tibet: 21, tibetan plateau: 21, coral bleaching: 20, freeze thaw: 20, human activities: 20, ice sheet: 20, lake area: 20, learning algorithm: 20, mean sea: 20, temperature prediction: 20, tibet plateau: 20, computer vision: 19, fast ice: 19, thermokarst lakes: 19, active layer: 18, gradient boosting: 18sea surface temperature: 66, machine learning algorithms: 55, arctic sea ice: 54, sea level rise: 49, short term memory: 47, using machine learning: 47, global climate change: 40, convolutional neural network: 38, random forest rf: 37, machine learning techniques: 33, support vector machine: 32, synthetic aperture radar: 31, deep learning based: 26, deep neural network: 26, machine learning ml: 26, remote sensing images: 26, aperture radar sar: 24, artificial neural network: 24, surface temperature sst: 23, term memory lstm: 23, using deep learning: 23, convolutional neural networks: 22, square error rmse: 22, google earth engine: 21, machine learning based: 21, vector machine svm: 21, qinghai tibet plateau: 19, machine learning approaches: 18, sea ice concentration: 18, sea ice extent: 18, sea ice prediction: 18, mean sea level: 17, neural network ann: 16, deep learning dl: 15, machine learning algorithm: 15, satellite remote sensing: 15, supervised machine learning: 15, artificial intelligence ai: 14, neural network cnn: 14, deep learning approach: 12, machine learning approach: 12, sea surface salinity: 12, sea surface temperatures: 12, support vector regression: 12, remote sensing imagery: 11, resolution satellite imagery: 11, active layer thickness: 10, deep learning algorithms: 10, high spatial resolution: 10, high water temperature: 10, passive microwave images: 10, supra glacial debris: 10, coastal sea level: 9, el niño southern: 9, future climate change: 9, global sea level: 9, high resolution satellite: 9, japanese spanish mackerel: 9, long time series: 9, moderate resolution imaging: 9, niño southern oscillation: 9, resolution imaging spectroradiometer: 9, sea surface height: 9, storm surge events: 9, using remote sensing: 9, absolute error mae: 8, based deep learning: 8, climate change mitigation: 8, deep convolutional neural: 8, fused snow depth: 8, glacial debris cover: 8, machine learning technique: 8, remote sensing technology: 8, sea ice thickness: 8, south china sea: 8, southern oscillation enso: 8, surface temperature prediction: 8, surface water bodies: 8, use machine learning: 8, using time series: 8, boosted regression tree: 7, coral reef bleaching: 7, east china sea: 7, glacial lake extraction: 7, greenhouse gas emissions: 7, harmful algal blooms: 7, ice concentration sic: 7, memory lstm neural: 7, near real time: 7, radar sar images: 7, sea level variability: 7, snow depth products: 7, squared error rmse: 7, surface salinity sss: 7, term memory neural: 7, unmanned aerial vehicles: 7, unsupervised machine learning: 7, vector regression svr: 7, water body extraction: 7, water quality parameters: 7[('data', 849), ('climate', 651), ('model', 651), ('sea', 611), ('learning', 608), ('machine', 559), ('water', 532), ('change', 517), ('ice', 475), ('%', 455), ('models', 427), ('study', 391), ('ocean', 363), ('results', 339), ('accuracy', 334), ('temperature', 316), ('surface', 307), ('time', 301), ('prediction', 296), ('images', 260), ('method', 259), ('methods', 259), ('resolution', 253), ('level', 235), ('satellite', 234), ('area', 227), ('areas', 217), ('network', 217), ('analysis', 216), ('species', 214), ('changes', 213), ('classification', 209), ('snow', 208), ('approach', 180), ('distribution', 180), ('monitoring', 178), ('performance', 176), ('system', 167), ('image', 165), ('detection', 162), ('algorithms', 161), ('research', 160), ('term', 157), ('information', 154), ('depth', 153), ('mapping', 153), ('scale', 150), ('imagery', 145), ('fish', 139), ('warming', 138), ('management', 136), ('series', 136), ('regions', 132), ('cover', 130), ('features', 128), ('paper', 127), ('carbon', 123), ('forest', 121), ('training', 120), ('extraction', 118), ('environment', 116), ('techniques', 115), ('ecosystems', 114), ('dataset', 113), ('observations', 112), ('region', 110), ('conditions', 110), ('development', 109), ('networks', 109), ('land', 109), ('regression', 108), ('sensing', 107), ('error', 105), ('variables', 104), ('years', 104), ('effects', 104), ('studies', 102), ('factors', 100), ('-', 99), ('seagrass', 99), ('glaciers', 97), ('lakes', 96), ('parameters', 94), ('state', 91), ('wave', 91), ('quality', 90), ('ecosystem', 90), ('segmentation', 90), ('use', 88), ('period', 87), ('impact', 86), ('approaches', 86), ('reef', 86), ('habitat', 85), ('sst', 85), ('dynamics', 82), ('rate', 81), ('lake', 81), ('feature', 81), ('values', 80)][('use', 977), ('base', 591), ('show', 304), ('learn', 280), ('propose', 262), ('provide', 261), ('predict', 247), ('have', 212), ('increase', 201), ('compare', 194), ('improve', 181), ('develop', 178), ('include', 142), ('identify', 135), ('apply', 129), ('evaluate', 126), ('combine', 121), ('make', 119), ('estimate', 118), ('obtain', 115), ('sense', 110), ('monitor', 109), ('understand', 107), ('train', 106), ('achieve', 99), ('find', 98), ('detect', 95), ('exist', 95), ('present', 90), ('perform', 90), ('demonstrate', 89), ('derive', 88), ('reduce', 87), ('assess', 83), ('affect', 83), ('require', 80), ('support', 79), ('extract', 78), ('indicate', 76), ('cause', 74), ('drive', 73), ('consider', 72), ('observe', 70), ('suggest', 68), ('generate', 68), ('produce', 68), ('lead', 67), ('analyze', 67), ('automate', 66), ('relate', 65), ('result', 64), ('classify', 63), ('map', 62), ('allow', 61), ('study', 61), ('integrate', 61), ('cover', 59), ('test', 58), ('collect', 57), ('change', 57), ('reveal', 57), ('be', 54), ('determine', 54), ('become', 52), ('decrease', 52), ('create', 48), ('play', 47), ('validate', 47), ('help', 46), ('mean', 44), ('model', 44), ('associate', 44), ('give', 44), ('need', 44), ('investigate', 44), ('outperform', 43), ('select', 43), ('capture', 42), ('know', 42), ('take', 42), ('focus', 41), ('represent', 41), ('set', 40), ('remain', 40), ('address', 40), ('enhance', 39), ('explore', 39), ('forecast', 39), ('aim', 38), ('employ', 37), ('influence', 37), ('enable', 37), ('range', 37), ('utilize', 37), ('conduct', 36), ('highlight', 36), ('design', 36), ('calculate', 36), ('boost', 35), ('build', 35)][('deep', 402), ('high', 386), ('global', 367), ('coastal', 296), ('spatial', 263), ('-', 259), ('neural', 228), ('remote', 214), ('important', 198), ('different', 197), ('marine', 188), ('such', 187), ('environmental', 181), ('long', 160), ('coral', 154), ('other', 152), ('large', 151), ('temporal', 151), ('new', 146), ('future', 128), ('random', 123), ('significant', 113), ('human', 108), ('artificial', 105), ('low', 104), ('accurate', 99), ('average', 97), ('multi', 94), ('ecological', 90), ('sustainable', 83), ('convolutional', 83), ('recent', 82), ('more', 76), ('current', 76), ('many', 76), ('multiple', 75), ('local', 75), ('potential', 75), ('natural', 74), ('higher', 74), ('regional', 74), ('short', 72), ('underwater', 71), ('overall', 68), ('novel', 68), ('various', 67), ('better', 67), ('available', 66), ('key', 65), ('glacier', 64), ('physical', 63), ('complex', 62), ('anthropogenic', 62), ('arctic', 62), ('dynamic', 61), ('spectral', 61), ('automatic', 60), ('several', 60), ('first', 59), ('mean', 59), ('glacial', 59), ('effective', 58), ('great', 57), ('traditional', 56), ('suitable', 55), ('main', 55), ('small', 54), ('essential', 54), ('critical', 53), ('best', 53), ('rf', 53), ('ensemble', 53), ('rapid', 52), ('efficient', 50), ('non', 50), ('antarctic', 49), ('predictive', 48), ('statistical', 48), ('northern', 48), ('atmospheric', 48), ('open', 47), ('linear', 46), ('optical', 46), ('major', 45), ('crucial', 45), ('single', 45), ('active', 44), ('previous', 44), ('past', 44), ('total', 44), ('scientific', 43), ('oceanic', 43), ('present', 42), ('square', 42), ('monthly', 41), ('seasonal', 41), ('few', 41), ('real', 41), ('good', 40), ('difficult', 40)]{'climate': 13, 'global': 8, 'human': 2, 'environmental': 1, 'wasting': 1, 'topographic': 1, 'enso': 1, 'negative': 1, 'complex': 1, 'chemical': 1, 'fossil': 1, 'adverse': 1, 'thermal': 1, 'view': 1, 'noise': 1}{'natural': 1, 'snow': 1, 'algorithm': 1, 'ecosystem': 1, 'cyclone': 1, 'ocean': 1}[('global ocean biogeochemical models', 0.6378), ('global ocean biogeochemistry analysis', 0.6219), ('global ocean biogeochemistry', 0.6214), ('reconstructed ocean biogeochemistry', 0.6091), ('sustainable marine environment prediction', 0.5892), ('future ocean climatologies', 0.5742), ('ocean biogeochemistry', 0.5674), ('time ocean acidification monitoring model', 0.5664), ('global ocean data analysis project', 0.5618), ('edge analytics ocean acidification', 0.5558), ('quality ocean data', 0.5486), ('regional ocean climate projections', 0.5474), ('ocean biogeochemistry control', 0.5458), ('ocean forecasting', 0.5453), ('neural networks sea surface temperature', 0.5446), ('extensive oceans data', 0.5402), ('ocean acidification data', 0.5374), ('robust oceanic poc models', 0.5367), ('oceanography climate prediction system version', 0.5359), ('sea surface ph model', 0.5347), ('sea surface temperature prediction', 0.5272), ('ocean temperature prediction', 0.5261), ('new sea ice prediction models', 0.5224), ('new global oceanic emission inventory', 0.5223), ('specific sea surface temperature predictions', 0.5221), ('sea subsurface temperature prediction task', 0.5202), ('ocean carbon cycle', 0.5194), ('seawater prediction method', 0.513), ('ocean climate change', 0.5105), ('ocean ecosystem accounting', 0.5003), ('environmental prediction', 0.4997), ('sea surface temperature prediction sea surface temperature', 0.4994), ('marine climate change', 0.4961), ('ocean acidification monitoring system', 0.4944), ('sea surface temperature projections', 0.4942), ('shoreline evolution forecasting models', 0.4942), ('new oceanic emission inventory', 0.4938), ('dimensional seawater temperature prediction task', 0.4934), ('multiple global sea temperature datasets', 0.4919), ('oceanographic variables', 0.4916), ('sea predictions', 0.4897), ('ocean pollution detection', 0.4887), ('world ocean database', 0.488), ('abnormal sea surface temperature prediction', 0.488), ('marine distribution models', 0.4874), ('key ocean temperature estimates', 0.4861), ('dedicated ocean model simulations', 0.4829), ('ocean climate', 0.4817), ('ocean colour climate change initiative', 0.4817), ('marine ecosystem dynamics', 0.4814)]
11
910720.131climate_weather9_climate_water_learning_temperature['climate', 'water', 'learning', 'temperature', 'precipitation', 'change', 'machine', 'using', 'groundwater', 'based', 'rainfall', 'machine learning', 'climate change', 'drought', 'prediction', 'used', 'river', 'future', 'time', 'forecasting', 'deep', 'high', 'hydrological', 'downscaling', 'global', 'term', 'neural', 'mean', 'network', 'long'][('ecoclimatologically', 0.4895), ('evapotranspiration', 0.4638), ('rainfalls', 0.4529), ('climatologically', 0.4352), ('desertification', 0.4297), ('hydroclimatological', 0.4292), ('soil_moisture', 0.4211), ('droughts', 0.4177), ('climatologies', 0.4165), ('precipitations', 0.4101), ('climatenet', 0.409), ('climatology', 0.406), ('rainfall', 0.3931), ('climatological', 0.3897), ('precipitation', 0.3825), ('aridity', 0.3725), ('evaporations', 0.3698), ('reforestation', 0.368), ('irrigation', 0.3654), ('evaporation', 0.3594), ('deforestation', 0.355), ('hydroclimate', 0.3535), ('climatically', 0.3534), ('geosciences', 0.353), ('terraclimate', 0.3526), ('evaporate', 0.3425), ('climate4r', 0.3423), ('climate', 0.3392), ('arid', 0.3387), ('drought', 0.3378), ('rain', 0.3376), ('hydrologically', 0.332), ('rains', 0.3296), ('agroclimatic', 0.3188), ('geoscience', 0.3162), ('soilvegetation', 0.3133), ('hydrological', 0.3124), ('runoff', 0.3106), ('rainy', 0.3091), ('rainwater', 0.3059), ('runoffs', 0.3058), ('geomorphology', 0.3047), ('groundwaters', 0.3034), ('hydrology', 0.3018), ('noaa', 0.3), ('meteorologically', 0.2966), ('bioclimatic', 0.2946), ('monsoon', 0.2946), ('climates', 0.2931), ('droughtprone', 0.2927)][('land evapotranspiration', 0.6835), ('climate evapotranspiration', 0.6788), ('global evapotranspiration', 0.6585), ('drought evapotranspiration', 0.6518), ('rainfall evapotranspiration', 0.6286), ('precipitation evapotranspiration', 0.6203), ('evapotranspiration precipitation', 0.6192), ('evapotranspiration forecasting', 0.618), ('evapotranspiration trends', 0.617), ('land evaporation', 0.6169), ('evapotranspiration global', 0.6109), ('annual evapotranspiration', 0.6045), ('basin evapotranspiration', 0.5971), ('land precipitation', 0.5953), ('evapotranspiration years', 0.5921), ('evapotranspiration trend', 0.5904), ('future evapotranspiration', 0.585), ('evapotranspiration datasets', 0.5848), ('evapotranspiration prediction', 0.5846), ('estimating evapotranspiration', 0.5844), ('predicting droughts', 0.5814), ('forest evapotranspiration', 0.5807), ('evapotranspiration runoff', 0.5801), ('world hydroclimatological', 0.5781), ('crop evapotranspiration', 0.5759), ('global precipitation', 0.5735), ('global drought', 0.5728), ('soil evaporation', 0.5723), ('rainfall evaporation', 0.5718), ('drought modelling', 0.571), ('droughts quantified', 0.5687), ('drought prediction', 0.5682), ('rainfall warming', 0.566), ('forecasting droughts', 0.5651), ('drought scenarios', 0.5644), ('droughts accurately', 0.5628), ('drought modeling', 0.5612), ('2019 evapotranspiration', 0.5604), ('climate rainfall', 0.56), ('climatological drought', 0.56), ('climate droughts', 0.5589), ('terrestrial drought', 0.5583), ('evapotranspiration basin', 0.5581), ('evapotranspiration changes', 0.5565), ('assessed evapotranspiration', 0.5546), ('global hydrological', 0.5535), ('evaporation forecasting', 0.553), ('droughts developing', 0.552), ('runoff terraclimate', 0.5513), ('hydrological droughts', 0.551)]machine learning: 1102, climate change: 1058, deep learning: 493, neural network: 349, soil moisture: 325, random forest: 246, short term: 229, time series: 221, water resources: 216, long term: 212, water quality: 205, support vector: 170, term memory: 166, neural networks: 157, artificial intelligence: 148, artificial neural: 140, air temperature: 138, square error: 137, river basin: 134, large scale: 126, high resolution: 122, using machine: 121, global warming: 120, learning algorithms: 119, remote sensing: 117, global climate: 114, land surface: 114, surface temperature: 110, vector machine: 99, learning techniques: 97, land use: 96, learning ml: 96, memory lstm: 93, convolutional neural: 92, spatial resolution: 92, statistical downscaling: 91, solar radiation: 89, absolute error: 86, water level: 86, learning based: 85, future climate: 84, groundwater level: 84, error rmse: 80, forest rf: 78, linear regression: 78, learning approach: 74, water resource: 73, water temperature: 72, water storage: 66, correlation coefficient: 65, spatio temporal: 65, nash sutcliffe: 62, vector regression: 62, united states: 57, regional climate: 56, semi arid: 56, general circulation: 54, sutcliffe efficiency: 54, water management: 54, groundwater potential: 53, learning algorithm: 53, network ann: 53, resources management: 53, wind speed: 53, error mae: 51, real time: 51, gradient boosting: 50, human activities: 49, weather forecasting: 49, decision making: 48, extreme events: 48, climate changes: 47, relative humidity: 47, surface water: 47, temporal resolution: 46, groundwater quality: 45, climate variability: 44, extreme precipitation: 44, recent years: 44, climatic conditions: 43, extreme weather: 43, land cover: 43, squared error: 43, using deep: 43, meteorological stations: 42, machine svm: 41, river basins: 41, weather prediction: 41, drought events: 39, early warning: 39, groundwater levels: 39, maximum temperature: 39, representative concentration: 39, spatial distribution: 39, deep neural: 38, hydrological drought: 38, water demand: 38, groundwater resources: 37, regression svr: 37, sustainable development: 37short term memory: 161, using machine learning: 120, machine learning algorithms: 100, artificial neural network: 99, machine learning ml: 96, term memory lstm: 93, support vector machine: 91, random forest rf: 78, machine learning techniques: 76, square error rmse: 68, support vector regression: 62, land surface temperature: 61, convolutional neural network: 59, neural network ann: 53, nash sutcliffe efficiency: 51, absolute error mae: 50, water resources management: 50, machine learning based: 44, machine learning approach: 43, artificial neural networks: 41, vector machine svm: 41, deep learning based: 40, global climate change: 37, vector regression svr: 36, machine learning algorithm: 35, using deep learning: 34, water resource management: 34, artificial intelligence ai: 33, climate change impact: 33, convolutional neural networks: 33, deep learning dl: 33, future climate change: 33, climate change scenarios: 32, extreme learning machine: 32, climate change impacts: 31, different machine learning: 30, neural network cnn: 30, deep learning approach: 29, terrestrial water storage: 27, extreme gradient boosting: 26, surface temperature lst: 26, climate change projections: 25, difference vegetation index: 25, normalized difference vegetation: 25, deep neural network: 23, extreme weather events: 23, particle swarm optimization: 23, surface air temperature: 23, moderate resolution imaging: 22, sea surface temperature: 22, sutcliffe efficiency nse: 22, high spatial resolution: 21, multiple linear regression: 21, resolution imaging spectroradiometer: 21, soil moisture products: 21, surface soil moisture: 21, vegetation index ndvi: 21, ensemble machine learning: 20, imaging spectroradiometer modis: 20, representative concentration pathways: 20, high resolution climate: 19, machine learning approaches: 19, deep learning techniques: 18, global solar radiation: 18, learning machine elm: 18, representative concentration pathway: 18, standardized precipitation index: 18, time series forecasting: 18, water quality parameters: 18, empirical mode decomposition: 17, gated recurrent unit: 17, integrated moving average: 17, semi arid regions: 17, climate change initiative: 16, hybrid machine learning: 16, machine learning technique: 16, deep neural networks: 15, multilayer perceptron mlp: 15, precipitation index spi: 15, radial basis function: 15, recurrent neural network: 15, spatio temporal resolution: 15, water assessment tool: 15, diffuse solar radiation: 14, google earth engine: 14, kling gupta efficiency: 14, land use changes: 14, large scale atmospheric: 14, large scale climate: 14, learning ml algorithms: 14, near surface air: 14, neural networks anns: 14, numerical weather prediction: 14, satellite remote sensing: 14, sea level pressure: 14, soil moisture sm: 14, absolute percentage error: 13, assessment tool swat: 13, based machine learning: 13, deep learning algorithms: 13[('climate', 2408), ('model', 2269), ('data', 2039), ('water', 1745), ('models', 1737), ('change', 1250), ('machine', 1248), ('learning', 1242), ('study', 1095), ('temperature', 1005), ('results', 905), ('prediction', 869), ('precipitation', 811), ('%', 809), ('rainfall', 690), ('time', 668), ('groundwater', 664), ('drought', 635), ('performance', 527), ('methods', 518), ('network', 499), ('variables', 488), ('soil', 486), ('method', 486), ('term', 474), ('accuracy', 471), ('analysis', 455), ('approach', 447), ('forecasting', 444), ('changes', 430), ('weather', 429), ('resolution', 408), ('surface', 402), ('error', 401), ('scale', 389), ('management', 376), ('regression', 372), ('river', 370), ('quality', 360), ('land', 358), ('system', 349), ('moisture', 334), ('regions', 323), ('level', 319), ('runoff', 310), ('resources', 298), ('research', 296), ('period', 295), ('lstm', 293), ('events', 292), ('conditions', 292), ('input', 291), ('algorithms', 280), ('area', 278), ('series', 275), ('impact', 274), ('forest', 273), ('techniques', 273), ('satellite', 272), ('information', 269), ('factors', 266), ('use', 261), ('scenarios', 254), ('index', 251), ('parameters', 249), ('region', 247), ('values', 243), ('basin', 239), ('stations', 238), ('flood', 231), ('networks', 228), ('flow', 228), ('training', 227), ('framework', 224), ('paper', 222), ('areas', 220), ('years', 217), ('patterns', 213), ('variability', 211), ('rmse', 211), ('development', 209), ('-', 208), ('predictions', 201), ('correlation', 198), ('studies', 198), ('downscaling', 196), ('modeling', 193), ('impacts', 191), ('effects', 189), ('uncertainty', 189), ('observations', 187), ('dataset', 187), ('assessment', 183), ('memory', 183), ('year', 182), ('vector', 182), ('process', 180), ('radiation', 177), ('air', 175), ('warming', 174)][('use', 2346), ('base', 1223), ('predict', 702), ('show', 701), ('learn', 551), ('have', 489), ('develop', 485), ('increase', 466), ('propose', 453), ('compare', 440), ('provide', 431), ('improve', 386), ('apply', 337), ('include', 310), ('find', 265), ('downscale', 255), ('evaluate', 245), ('estimate', 241), ('perform', 241), ('obtain', 236), ('identify', 234), ('indicate', 225), ('make', 223), ('assess', 215), ('forecast', 215), ('simulate', 191), ('demonstrate', 189), ('affect', 188), ('consider', 185), ('train', 183), ('drive', 180), ('present', 177), ('reduce', 177), ('mean', 174), ('reveal', 169), ('combine', 165), ('model', 165), ('observe', 158), ('analyze', 157), ('achieve', 156), ('support', 155), ('select', 155), ('project', 153), ('integrate', 152), ('cause', 144), ('understand', 143), ('generate', 143), ('test', 138), ('decrease', 132), ('employ', 129), ('relate', 128), ('be', 127), ('suggest', 124), ('change', 118), ('investigate', 118), ('associate', 116), ('require', 114), ('exist', 114), ('help', 112), ('lead', 112), ('outperform', 112), ('capture', 110), ('explore', 108), ('produce', 106), ('become', 105), ('utilize', 104), ('represent', 99), ('quantify', 99), ('take', 98), ('give', 95), ('result', 94), ('derive', 94), ('follow', 94), ('validate', 91), ('influence', 91), ('determine', 90), ('monitor', 90), ('sense', 89), ('study', 89), ('construct', 88), ('play', 87), ('boost', 87), ('detect', 87), ('measure', 84), ('allow', 83), ('aim', 81), ('occur', 80), ('vary', 80), ('couple', 79), ('optimize', 78), ('need', 76), ('focus', 75), ('extract', 75), ('expect', 74), ('contribute', 74), ('calculate', 74), ('introduce', 73), ('address', 73), ('range', 72), ('establish', 72)][('high', 607), ('deep', 606), ('global', 595), ('-', 581), ('different', 545), ('future', 510), ('neural', 509), ('spatial', 475), ('long', 444), ('hydrological', 399), ('other', 365), ('such', 364), ('extreme', 356), ('meteorological', 352), ('daily', 331), ('important', 320), ('large', 314), ('random', 310), ('artificial', 303), ('temporal', 297), ('statistical', 279), ('short', 267), ('monthly', 266), ('climatic', 261), ('accurate', 259), ('regional', 238), ('new', 225), ('significant', 221), ('average', 211), ('annual', 203), ('environmental', 199), ('multi', 197), ('ensemble', 197), ('atmospheric', 194), ('streamflow', 184), ('various', 180), ('low', 178), ('best', 174), ('local', 172), ('better', 171), ('human', 170), ('agricultural', 168), ('potential', 167), ('higher', 160), ('hybrid', 160), ('square', 158), ('multiple', 152), ('sustainable', 151), ('many', 145), ('historical', 143), ('maximum', 143), ('solar', 142), ('relative', 141), ('complex', 140), ('seasonal', 139), ('mean', 134), ('effective', 133), ('recent', 131), ('convolutional', 130), ('several', 130), ('natural', 129), ('available', 128), ('current', 128), ('remote', 127), ('non', 124), ('spatiotemporal', 124), ('essential', 122), ('physical', 120), ('first', 120), ('key', 119), ('absolute', 118), ('linear', 116), ('novel', 116), ('predictive', 115), ('reliable', 113), ('more', 112), ('major', 110), ('critical', 110), ('arid', 105), ('total', 104), ('present', 104), ('main', 103), ('general', 100), ('most', 99), ('crucial', 98), ('rf', 94), ('urban', 93), ('anthropogenic', 93), ('real', 91), ('good', 90), ('highest', 90), ('specific', 89), ('overall', 88), ('single', 88), ('ecological', 88), ('lower', 86), ('empirical', 85), ('past', 84), ('efficient', 82), ('optimal', 80)]{'climate': 68, 'human': 3, 'drought': 3, 'precipitation': 2, 'global': 2, 'hydrological': 2, 'altered': 2, 'different': 2, 'external': 2, 'land': 1, 'sd': 1, 'utilizing': 1, 'future': 1, 'pollen': 1, 'classification': 1, 'covid': 1, 'extreme': 1, 'csos': 1, 'using': 1, 'insufficient': 1, 'mitigation': 1, 'gloti': 1, 'wind': 1, 'lack': 1, 'climatic': 1, 'uncertainties': 1, 'warming': 1, 'water': 1, 'training': 1, 'forecast': 1, 'flooding': 1, 'large': 1, 'non': 1, 'accelerated': 1, 'freshwater': 1, 'input': 1, 'rainfall': 1, 'projected': 1, 'greenhouse': 1, 'weather': 1, 'various': 1, 'urbanization': 1}{'climate': 2, 'flow': 2, 'changes': 1, 'physically': 1, 'temperature': 1, 'abstraction': 1, 'clouds': 1, 'precipitation': 1, 'climatic': 1, 'earth': 1, 'major': 1, 'anthropogenic': 1}[('global land evapotranspiration trend', 0.7866), ('global land evapotranspiration', 0.7819), ('global surface soil moisture trends', 0.7113), ('global land precipitation', 0.6858), ('global annual evapotranspiration', 0.6849), ('land evapotranspiration', 0.6835), ('global hydrological droughts', 0.6598), ('potential evapotranspiration forecasting', 0.6536), ('global land evaporation amsterdam model', 0.6382), ('global evapotranspiration increase', 0.6359), ('regional standardized precipitation evapotranspiration index', 0.6282), ('different climatic environments reference evapotranspiration', 0.6261), ('global soil moisture', 0.6172), ('evapotranspiration trends', 0.617), ('underlying drought dynamics', 0.6154), ('higher annual evapotranspiration', 0.6149), ('future climates soil moisture', 0.6144), ('global extreme hydrological droughts', 0.6144), ('future potential evapotranspiration', 0.6131), ('climate change forecasting water', 0.6083), ('terrestrial water cycle', 0.607), ('global soil moisture data', 0.6013), ('terrestrial hydrological cycle', 0.6002), ('climate change initiative soil moisture', 0.5996), ('potential evapotranspiration data', 0.598), ('global water cycle', 0.5972), ('reference crop evapotranspiration estimation', 0.5968), ('land precipitation', 0.5953), ('future evaporation projections', 0.5951), ('global drought monitoring', 0.5939), ('global soil moisture distribution', 0.5938), ('watershed scale evapotranspiration estimation', 0.5936), ('standard precipitation evapotranspiration index', 0.5929), ('terrestrial water cycles', 0.5926), ('standardized precipitation evapotranspiration', 0.5924), ('water resources climate change projections', 0.5923), ('future drought scenarios', 0.5921), ('evapotranspiration trend', 0.5904), ('future hydrological droughts', 0.5903), ('terrestrial climate change', 0.5878), ('monthly evapotranspiration estimation', 0.5875), ('land water cycle', 0.5874), ('terrestrial drought evolution', 0.5861), ('evapotranspiration datasets', 0.5848), ('daily reference crop evapotranspiration', 0.5836), ('hydrological drought change', 0.5826), ('high spatiotemporal resolution land surface temperature climate change', 0.5811), ('global hydrological cycle', 0.5791), ('terrestrial water storage changes', 0.5777), ('evaporative demand drought index', 0.5764)]
12
101480.018wildfires10_wildfire_forest_fires_wildfires['wildfire', 'forest', 'fires', 'wildfires', 'smoke', 'forest fires', 'learning', 'severity', 'detection', 'using', 'climate', 'area', 'areas', 'based', 'machine', 'risk', 'machine learning', 'change', 'occurrence', 'deep', 'prediction', 'used', 'climate change', 'forests', 'high', 'deep learning', 'burn', 'images', 'network', 'human'][('bushfires', 0.447), ('wildfires', 0.4457), ('forestry', 0.3899), ('forests', 0.3888), ('landfire', 0.3839), ('lidar', 0.3825), ('bushfire', 0.3773), ('forest', 0.368), ('multispectral', 0.3638), ('wildfire', 0.3615), ('landsat', 0.3571), ('hyperspectral', 0.3531), ('wildlandfire', 0.3501), ('fires', 0.3397), ('firefighting', 0.3294), ('forestation', 0.3175), ('vegetation', 0.3161), ('meteorology', 0.3105), ('trees', 0.3027), ('forested', 0.2988), ('classifiers', 0.2981), ('firefighters', 0.2772), ('rainforests', 0.276), ('unburn', 0.2757), ('reflectometry', 0.2743), ('flame', 0.2713), ('infrared', 0.2712), ('elmfire', 0.2656), ('shrublands', 0.2595), ('classifier', 0.2537), ('bowfire', 0.2532), ('predictors', 0.2502), ('glm', 0.2474), ('boosting', 0.2457), ('deforestation', 0.2434), ('overfitting', 0.2425), ('peatlands', 0.2419), ('extinguishing', 0.2373), ('peatland', 0.2369), ('woods', 0.2359), ('imagenet', 0.2354), ('meteorological', 0.2352), ('predictive', 0.2349), ('xgboost', 0.2317), ('topographic', 0.2312), ('climates', 0.2303), ('sensors', 0.2283), ('postfire', 0.2271), ('rmsr', 0.227), ('woodlands', 0.2268)][('wildfires detection', 0.6839), ('wildfire detecting', 0.6825), ('detection wildfires', 0.6799), ('predicting wildfire', 0.6796), ('predicting wildfires', 0.6777), ('wildfire detection', 0.6741), ('detect wildfires', 0.6691), ('wildfire prediction', 0.6554), ('predict wildfires', 0.6536), ('estimating wildfire', 0.6516), ('classifying wildfire', 0.6478), ('wildfires accurately', 0.6449), ('predict wildfire', 0.6397), ('forecasting wildfire', 0.636), ('sensed wildfires', 0.6351), ('detection wildfire', 0.6347), ('detect wildfire', 0.6302), ('wildfire classification', 0.6283), ('wildfires analyzed', 0.6257), ('wildfire monitoring', 0.6178), ('predicting fires', 0.6138), ('assessment wildfires', 0.6113), ('assess wildfire', 0.6074), ('wildfires monitoring', 0.6062), ('wildfire predictions', 0.6021), ('forecast wildfires', 0.6004), ('wildfire surveillance', 0.5975), ('detects wildfire', 0.5965), ('monitoring wildfire', 0.5941), ('predict fires', 0.5937), ('predicted wildfire', 0.5907), ('classification wildfire', 0.5903), ('wildfires studied', 0.587), ('quantification wildfires', 0.5835), ('forest wildfires', 0.5828), ('classify wildfires', 0.5816), ('map wildfires', 0.5776), ('datasets wildfires', 0.5773), ('wildfires spatiotemporal', 0.577), ('learning wildfires', 0.5768), ('detect fires', 0.574), ('fires weather', 0.5683), ('forestry predicting', 0.5678), ('classify wildfire', 0.5654), ('mapping wildfire', 0.5648), ('prediction wildfire', 0.5609), ('fires climate', 0.5604), ('wildfire segmentation', 0.5595), ('wildfires early', 0.5586), ('wildfire mapping', 0.5586)]machine learning: 136, climate change: 108, forest fires: 92, deep learning: 81, random forest: 48, burned areas: 39, neural network: 38, burned area: 32, real time: 32, artificial intelligence: 28, remote sensing: 27, global warming: 26, support vector: 26, smoke detection: 22, using machine: 21, learning algorithms: 20, recent years: 19, vector machine: 19, land cover: 18, learning based: 18, burn severity: 16, neural networks: 16, convolutional neural: 15, forest rf: 15, learning techniques: 15, wildfire susceptibility: 15, natural disasters: 14, air quality: 13, satellite images: 13, wildfire detection: 13, wildfire risk: 13, area mapping: 12, learning approaches: 12, short term: 12, transfer learning: 12, wildfire smoke: 12, early detection: 11, learning approach: 11, machine svm: 11, large scale: 10, logistic regression: 10, near real: 10, normalized difference: 10, open burning: 10, smart cities: 10, soil properties: 10, united states: 10, unmanned aerial: 10, using deep: 10, wind speed: 10, artificial neural: 9, climatic conditions: 9, detection using: 9, early warning: 9, future climate: 9, learning ml: 9, vegetation index: 9, weather conditions: 9, decision support: 8, difference vegetation: 8, ed visits: 8, f1 score: 8, human health: 8, learning algorithm: 8, learning dl: 8, long term: 8, pre trained: 8, relative humidity: 8, risk assessment: 8, satellite imagery: 8, smoke exposure: 8, spatial resolution: 8, susceptibility maps: 8, wildfire occurrence: 8, wildfire spread: 8, 95 ci: 7, based forest: 7, burn ratio: 7, climate changes: 7, computer vision: 7, curve auc: 7, decision makers: 7, extreme weather: 7, forest resources: 7, global climate: 7, gradient boosting: 7, high resolution: 7, human activity: 7, mapping using: 7, ml approaches: 7, network cnn: 7, normalized burn: 7, primary headache: 7, rating prediction: 7, regeneration failure: 7, roc curve: 7, south korea: 7, using satellite: 7, wildfire danger: 7, wildfire management: 7using machine learning: 21, support vector machine: 19, machine learning algorithms: 17, random forest rf: 15, burned area mapping: 11, vector machine svm: 11, deep learning based: 10, near real time: 10, machine learning ml: 9, convolutional neural networks: 8, deep learning dl: 8, difference vegetation index: 8, machine learning based: 8, normalized difference vegetation: 8, using deep learning: 8, artificial neural network: 7, convolutional neural network: 7, machine learning approach: 7, machine learning techniques: 7, neural network cnn: 7, normalized burn ratio: 7, artificial intelligence ai: 6, bp neural network: 6, deep learning techniques: 6, balanced random forest: 5, decision support systems: 5, deep learning approaches: 5, global climate change: 5, google earth engine: 5, machine learning approaches: 5, novel machine learning: 5, unmanned aerial vehicles: 5, wildfire susceptibility mapping: 5, area mapping using: 4, burned area detection: 4, climate change wildfires: 4, convolution neural network: 4, deep learning algorithm: 4, different machine learning: 4, extreme gradient boosting: 4, fold cross validation: 4, high density smoke: 4, learning based approach: 4, machine learning algorithm: 4, moderate resolution imaging: 4, new machine learning: 4, risk rating prediction: 4, support vector machines: 4, temperature wind speed: 4, unmanned aerial vehicle: 4, using random forest: 4, western united states: 4, wildfire risk assessment: 4, μg m3 increase: 4, adaptive regression splines: 3, air quality forecasting: 3, artificial intelligence xai: 3, burn ratio nbr: 3, californias northern coastal: 3, climate change scenarios: 3, climatic water deficit: 3, dadia lefkimi soufli: 3, danger rating prediction: 3, deep learning algorithms: 3, deep learning approach: 3, deep neural network: 3, deep neural networks: 3, density smoke exposure: 3, density smoke treatment: 3, different environmental conditions: 3, early warning systems: 3, explainable artificial intelligence: 3, fine particulate matter: 3, forest cover type: 3, forest rf machine: 3, forest support vector: 3, grapevine smoke contamination: 3, high risk areas: 3, land cover changes: 3, learning based forest: 3, location aware adaptive: 3, machine learning random: 3, machine learning wildfires: 3, modis thermal anomalies: 3, morphological attribute profiles: 3, multi scale feature: 3, multivariate adaptive regression: 3, neural network ann: 3, northern coastal mountains: 3, open field burning: 3, optical remote sensing: 3, permanent forest loss: 3, primary headache disorders: 3, random forest support: 3, random forests rf: 3, real time wildfire: 3, resolution imaging spectroradiometer: 3, rf machine learning: 3, smoke detection algorithm: 3, southern oscillation enso: 3[('fire', 610), ('forest', 407), ('wildfire', 235), ('model', 226), ('climate', 202), ('fires', 192), ('%', 173), ('learning', 166), ('data', 165), ('machine', 158), ('detection', 132), ('models', 129), ('study', 128), ('change', 127), ('areas', 122), ('wildfires', 120), ('area', 119), ('accuracy', 103), ('smoke', 102), ('results', 101), ('prediction', 98), ('risk', 95), ('severity', 92), ('time', 68), ('images', 66), ('factors', 65), ('network', 65), ('forests', 63), ('occurrence', 63), ('classification', 62), ('approach', 60), ('system', 60), ('weather', 56), ('mapping', 55), ('satellite', 55), ('method', 50), ('methods', 49), ('dataset', 49), ('conditions', 48), ('performance', 47), ('management', 46), ('variables', 46), ('years', 46), ('image', 46), ('vegetation', 46), ('algorithms', 43), ('research', 42), ('-', 42), ('systems', 41), ('techniques', 41), ('regression', 40), ('temperature', 40), ('paper', 39), ('analysis', 39), ('events', 39), ('information', 39), ('drivers', 37), ('environment', 37), ('land', 36), ('damage', 36), ('danger', 35), ('approaches', 34), ('burn', 34), ('resolution', 34), ('level', 33), ('fuel', 33), ('frequency', 32), ('effects', 32), ('index', 32), ('decision', 32), ('impact', 31), ('datasets', 31), ('intelligence', 31), ('warming', 31), ('disasters', 30), ('increase', 30), ('training', 30), ('year', 30), ('assessment', 29), ('result', 29), ('maps', 29), ('cover', 28), ('exposure', 28), ('susceptibility', 28), ('loss', 27), ('world', 26), ('scale', 26), ('vector', 26), ('case', 26), ('number', 26), ('work', 26), ('air', 26), ('prevention', 25), ('region', 25), ('monitoring', 25), ('potential', 24), ('ecosystems', 24), ('regions', 24), ('networks', 24), ('score', 23)][('use', 335), ('base', 170), ('burn', 110), ('increase', 105), ('learn', 82), ('propose', 80), ('predict', 77), ('have', 68), ('show', 64), ('detect', 54), ('cause', 53), ('provide', 51), ('improve', 47), ('occur', 47), ('develop', 47), ('compare', 40), ('train', 38), ('apply', 37), ('identify', 36), ('assess', 36), ('include', 33), ('find', 29), ('achieve', 29), ('evaluate', 29), ('reduce', 29), ('create', 27), ('support', 27), ('become', 27), ('affect', 26), ('contribute', 26), ('make', 26), ('sense', 25), ('wildfire', 24), ('estimate', 24), ('obtain', 24), ('perform', 24), ('test', 23), ('indicate', 23), ('analyze', 23), ('demonstrate', 23), ('be', 22), ('consider', 22), ('relate', 21), ('result', 21), ('lead', 21), ('understand', 21), ('prevent', 21), ('associate', 20), ('observe', 20)][('deep', 98), ('-', 94), ('high', 91), ('global', 63), ('such', 63), ('human', 61), ('different', 58), ('random', 57), ('other', 56), ('neural', 54), ('natural', 52), ('spatial', 50), ('environmental', 47), ('large', 46), ('recent', 43), ('early', 41), ('artificial', 38), ('real', 36), ('important', 35), ('climatic', 33), ('extreme', 32), ('future', 31), ('new', 31), ('low', 31), ('various', 30), ('remote', 29), ('major', 29), ('accurate', 26), ('spectral', 25), ('overall', 25), ('effective', 24), ('temporal', 24), ('economic', 24), ('ecological', 23), ('non', 23), ('significant', 23), ('fire', 22), ('multi', 22), ('open', 22), ('several', 20), ('best', 20)]{'fireworks': 2, 'forest': 2, 'climate': 1, 'natural': 1, 'hfs': 1}{'climatic': 1, 'climate': 1, 'meteorological': 1}[('forest fire detection', 0.7217), ('forest wildfire detection', 0.7175), ('effective forest fire prediction systems', 0.7151), ('early forest fire detection systems', 0.7051), ('forest fire classification evaluation', 0.7025), ('forest fire prediction systems', 0.6996), ('machine learning wildfires', 0.6914), ('effective wildfire prediction', 0.69), ('forest fire prediction', 0.689), ('forest fire danger prediction', 0.6878), ('forest fire risk image recognition processing', 0.6832), ('wildfire prediction accuracy assessment method', 0.6813), ('forest fire monitoring', 0.6812), ('early forest fire detection system', 0.6796), ('forest fire risk prediction', 0.6762), ('techniques forest fire prediction', 0.6762), ('wildfire detection', 0.6741), ('forest fire detection method', 0.6654), ('forest wildfire monitoring', 0.665), ('forecasting wildfire danger', 0.6645), ('wildfire danger prediction', 0.6644), ('forest fire risk mapping', 0.6643), ('forest fire prediction method', 0.6631), ('forest fire detection system', 0.6608), ('neural network forest fire identification algorithm', 0.6584), ('random forest wildfires', 0.6557), ('global wildfire prediction', 0.655), ('autonomous satellite wildfire detection', 0.6549), ('forest fire classification', 0.6539), ('forest fire smoke detection', 0.6536), ('improved forest fire detection method', 0.6516), ('improved forest fire risk identification algorithm', 0.6516), ('forest fire prediction map', 0.6515), ('time forest fire detection', 0.6508), ('wildfire risk assessment', 0.6507), ('effective forest fire risk rating prediction desires', 0.6491), ('wildfire danger forecasting climate change', 0.6487), ('spot wildfire detection', 0.6472), ('wildfire susceptibility prediction', 0.6455), ('wildfire risk assessments', 0.643), ('forest fire risk dataset', 0.6411), ('bushfire risk detection', 0.6408), ('wildfire smoke detection', 0.6396), ('machine learning algorithms wildfires', 0.6393), ('forest fire risk rating prediction approaches', 0.6378), ('efficient wildfire surveillance', 0.6356), ('time wildfire detection', 0.6355), ('wildfire susceptibility assessments', 0.6297), ('intelligent forest fire detection system design', 0.6291), ('forest fire monitoring technique', 0.629)]
13
119550.117communication_information_education11_ai_sustainable_intelligence_learning['ai', 'sustainable', 'intelligence', 'learning', 'social', 'artificial', 'artificial intelligence', 'development', 'environment', 'sustainability', 'industry', 'climate', 'technology', 'education', 'digital', 'change', 'business', 'students', 'based', 'paper', 'technologies', 'climate change', 'new', 'manufacturing', 'environmental', 'machine', 'human', 'approach', 'using', 'process'][('entrepreneurs', 0.4863), ('entrepreneurship', 0.4406), ('sociotechnic', 0.4254), ('entrepreneurial', 0.414), ('startups', 0.4138), ('sociotechnical', 0.4085), ('digitality', 0.3894), ('intellectualization', 0.3885), ('bioeconomy', 0.3838), ('digitalisation', 0.3823), ('digitalization', 0.3725), ('bibliometricians', 0.3697), ('technologists', 0.3662), ('sociodemographic', 0.3648), ('researchers', 0.3641), ('invention', 0.3602), ('innovation', 0.3592), ('interdisciplinarity', 0.3573), ('computerisation', 0.3528), ('technoscientific', 0.352), ('bibliometric', 0.3496), ('ventures', 0.3487), ('cyberspace', 0.3472), ('technological', 0.3472), ('technocrats', 0.3417), ('influencers', 0.3406), ('informatization', 0.3405), ('academicians', 0.3405), ('academias', 0.3394), ('sociological', 0.3381), ('innovate', 0.3367), ('industry', 0.3365), ('ceos', 0.3355), ('organisations', 0.3353), ('organizations', 0.3345), ('societys', 0.3344), ('industries', 0.3339), ('fintech', 0.3332), ('biomimicry', 0.3329), ('businesss', 0.3326), ('academia', 0.3323), ('sustainableentrepreneurship', 0.3316), ('sociocultural', 0.3314), ('inventions', 0.3302), ('interdisciplinary', 0.3287), ('academics', 0.3281), ('bibliometrics', 0.3264), ('businesses', 0.3262), ('firms', 0.3246), ('socioeconomics', 0.3244)][('digital entrepreneurship', 0.6052), ('entrepreneurial ecosystem', 0.5878), ('entrepreneurship ecosystem', 0.5825), ('ecosystem entrepreneurial', 0.5504), ('entrepreneurship ecosystems', 0.5483), ('ai entrepreneurial', 0.5415), ('sociotechnical endeavors', 0.5406), ('emergent entrepreneurial', 0.5383), ('digitalization intellectualization', 0.538), ('digitalization social', 0.5372), ('innovation ecosystem', 0.5363), ('tech entrepreneurs', 0.5341), ('sociotechnical digital', 0.533), ('innovation digitalization', 0.5307), ('digital economy', 0.5291), ('digital innovation', 0.5283), ('emerging sociotechnical', 0.5247), ('technological social', 0.5217), ('innovativeness digitality', 0.5206), ('innovation society', 0.5166), ('digital societies', 0.5139), ('society digitalization', 0.512), ('investigate entrepreneurial', 0.5075), ('digitalisation economy', 0.5051), ('digital businesss', 0.505), ('innovation digital', 0.4966), ('impact entrepreneurial', 0.4951), ('emergent technologies', 0.4951), ('digital enterprise', 0.4931), ('gender scientific', 0.4926), ('reshaping entrepreneurial', 0.4917), ('digital society', 0.4917), ('entrepreneurship field', 0.4913), ('technoscientific sociocultural', 0.4909), ('empowering digital', 0.4903), ('organizations entrepreneurs', 0.4865), ('entrepreneurs', 0.4863), ('emergent digital', 0.486), ('researchers social', 0.4844), ('business ecosystem', 0.4837), ('entrepreneurship examines', 0.4821), ('digital economic', 0.481), ('emergence industry', 0.4801), ('businesses digital', 0.4784), ('entrepreneurship people', 0.4783), ('academic ecosystem', 0.4782), ('entrepreneurial initiatives', 0.4768), ('collaboration entrepreneurial', 0.4766), ('organising sociotechnical', 0.4735), ('researchers industrialists', 0.4719)]artificial intelligence: 682, climate change: 591, machine learning: 453, sustainable development: 273, supply chain: 187, intelligence ai: 170, decision making: 167, social media: 140, deep learning: 125, covid 19: 96, decision support: 74, development goals: 68, natural language: 64, real time: 64, global warming: 63, digital technologies: 58, language processing: 56, energy consumption: 53, long term: 52, life cycle: 51, using machine: 49, cloud computing: 47, digital transformation: 47, supply chains: 44, circular economy: 43, higher education: 42, topic modeling: 42, neural network: 41, literature review: 40, recent years: 40, active learning: 39, industrial revolution: 38, real world: 38, learning algorithms: 37, learning techniques: 37, environmental sustainability: 35, smart manufacturing: 35, decision makers: 34, learning based: 34, new technologies: 34, 19 pandemic: 33, cyber physical: 33, problem solving: 33, paper presents: 32, social responsibility: 32, virtual reality: 31, learning process: 30, business environment: 29, learning approach: 29, learning ml: 29, random forest: 29, united nations: 29, learning environment: 28, neural networks: 28, support vector: 28, artificial neural: 27, chain management: 27, fourth industrial: 27, ai based: 26, design methodology: 26, engineering education: 26, methodology approach: 26, originality value: 26, paper aims: 26, sustainable manufacturing: 26, digital twins: 25, environmental protection: 25, extreme weather: 25, global climate: 25, practical implications: 25, remote sensing: 25, carbon emissions: 24, competitive advantage: 24, information technology: 24, large scale: 24, machine tool: 24, proposed approach: 24, change mitigation: 23, goals sdgs: 23, greenhouse gas: 23, logistic regression: 23, paper proposes: 23, text mining: 23, achieve sustainable: 22, ai technology: 22, digital technology: 22, latent dirichlet: 22, public health: 22, socio technical: 22, using artificial: 22, based learning: 21, carbon footprint: 21, conceptual framework: 21, making process: 21, social sustainability: 21, change adaptation: 20, digital twin: 20, environmental performance: 20, wide range: 20, ai systems: 19artificial intelligence ai: 170, sustainable development goals: 66, natural language processing: 56, using machine learning: 48, covid 19 pandemic: 33, machine learning ml: 29, machine learning algorithms: 28, fourth industrial revolution: 27, supply chain management: 27, design methodology approach: 26, machine learning techniques: 24, climate change mitigation: 23, development goals sdgs: 23, climate change adaptation: 20, machine learning based: 20, global climate change: 19, using artificial intelligence: 18, decision making process: 17, language processing nlp: 17, greenhouse gas emissions: 16, machine learning approach: 16, artificial intelligence technology: 15, artificial neural network: 15, corporate social responsibility: 15, extreme weather events: 15, support vector machine: 15, achieve sustainable development: 14, artificial intelligence based: 14, life cycle assessment: 14, machine learning approaches: 14, criteria decision making: 13, critical success factors: 12, cyber physical systems: 12, sustainable supply chain: 12, green supply chain: 11, machine learning algorithm: 11, product life cycle: 11, social media platforms: 11, unsupervised machine learning: 11, ant colony optimization: 10, artificial neural networks: 10, climate change related: 10, corporate environmental performance: 10, decision making processes: 10, macro task crowdsourcing: 10, multi criteria decision: 10, socio technical systems: 10, supervised machine learning: 10, sustainable competitive advantage: 10, using deep learning: 10, human resource management: 9, mitigate climate change: 9, analytic hierarchy process: 8, artificial intelligence applications: 8, artificial intelligence techniques: 8, climate change issues: 8, climate change using: 8, deep learning techniques: 8, higher education institutions: 8, machine learning technique: 8, random forest algorithm: 8, real time monitoring: 8, social networking sites: 8, supply chain sc: 8, ai supply chain: 7, anthropogenic climate change: 7, artificial intelligence robotics: 7, common value auctions: 7, ice snow tourism: 7, intelligence ai based: 7, key performance indicators: 7, multiple criteria decision: 7, semi structured interviews: 7, structural equation modeling: 7, supply chain resilience: 7, systematic literature review: 7, text mining techniques: 7, traditional machine learning: 7, uses machine learning: 7, 17 sustainable development: 6, achieving sustainable development: 6, artificial intelligence driven: 6, based decision support: 6, carbon neutrality cognition: 6, case based reasoning: 6, change artificial intelligence: 6, circular economy ce: 6, citrullus lanatus extract: 6, climate change artificial: 6, climate change impacts: 6, climate change ipcc: 6, closed loop supply: 6, computer aided technologies: 6, decision support systems: 6, deep learning based: 6, esg information disclosure: 6, high performance computing: 6, legal advisory institutions: 6, legal ai bot: 6, medium sized enterprises: 6[('data', 1025), ('climate', 880), ('research', 802), ('learning', 769), ('intelligence', 751), ('development', 748), ('environment', 711), ('study', 703), ('change', 684), ('machine', 581), ('model', 571), ('sustainability', 570), ('analysis', 550), ('paper', 517), ('technology', 507), ('industry', 471), ('approach', 433), ('system', 426), ('technologies', 422), ('results', 407), ('systems', 379), ('management', 374), ('business', 364), ('process', 363), ('education', 363), ('information', 348), ('students', 343), ('decision', 340), ('time', 313), ('design', 294), ('performance', 289), ('knowledge', 284), ('production', 283), ('framework', 271), ('energy', 271), ('impact', 268), ('manufacturing', 265), ('use', 252), ('-', 252), ('challenges', 250), ('methods', 245), ('supply', 237), ('case', 232), ('method', 230), ('models', 229), ('%', 229), ('media', 220), ('world', 219), ('innovation', 218), ('chain', 214), ('issues', 210), ('science', 209), ('ai', 203), ('work', 201), ('companies', 197), ('level', 196), ('techniques', 195), ('literature', 193), ('risk', 189), ('findings', 183), ('health', 175), ('value', 173), ('studies', 172), ('factors', 172), ('role', 171), ('field', 171), ('order', 170), ('problem', 170), ('quality', 169), ('support', 168), ('economy', 165), ('problems', 164), ('context', 162), ('application', 161), ('article', 160), ('engineering', 160), ('society', 159), ('network', 158), ('life', 158), ('approaches', 155), ('processes', 154), ('topics', 153), ('tools', 151), ('resources', 146), ('people', 143), ('strategies', 141), ('algorithms', 141), ('policy', 140), ('implementation', 140), ('environments', 139), ('applications', 139), ('sentiment', 139), ('efficiency', 138), ('topic', 135), ('service', 135), ('tool', 133), ('product', 133), ('solutions', 132), ('goals', 130), ('carbon', 130)][('use', 1077), ('base', 728), ('learn', 458), ('provide', 430), ('propose', 400), ('develop', 392), ('have', 380), ('make', 355), ('identify', 335), ('include', 301), ('improve', 292), ('relate', 282), ('increase', 260), ('show', 249), ('analyze', 232), ('achieve', 231), ('apply', 228), ('present', 210), ('address', 207), ('focus', 200), ('consider', 194), ('become', 191), ('ai', 190), ('create', 187), ('aim', 183), ('find', 171), ('take', 168), ('understand', 168), ('discuss', 166), ('support', 164), ('predict', 163), ('help', 161), ('explore', 161), ('need', 158), ('enable', 155), ('require', 153), ('lead', 149), ('integrate', 143), ('drive', 143), ('be', 142), ('exist', 142), ('implement', 141), ('enhance', 138), ('give', 136), ('build', 136), ('emerge', 134), ('reduce', 133), ('contribute', 132), ('promote', 125), ('evaluate', 119), ('generate', 119), ('examine', 118), ('change', 114), ('suggest', 111), ('design', 110), ('assess', 109), ('investigate', 109), ('affect', 108), ('introduce', 105), ('involve', 103), ('follow', 100), ('solve', 99), ('conduct', 99), ('face', 98), ('compare', 96), ('offer', 96), ('determine', 95), ('indicate', 93), ('collect', 92), ('combine', 92), ('adopt', 91), ('obtain', 91), ('demonstrate', 86), ('describe', 85), ('grow', 85), ('associate', 83), ('reveal', 83), ('work', 82), ('establish', 81), ('allow', 80), ('perform', 80), ('study', 79), ('ensure', 76), ('test', 73), ('play', 73), ('model', 72), ('highlight', 70), ('employ', 70), ('facilitate', 69), ('do', 68), ('optimize', 65), ('extract', 65), ('represent', 64), ('regard', 63), ('adapt', 63), ('result', 62), ('utilize', 62), ('train', 61), ('automate', 61), ('bring', 61)][('sustainable', 870), ('artificial', 747), ('social', 621), ('such', 525), ('environmental', 478), ('new', 451), ('digital', 421), ('-', 374), ('human', 332), ('global', 323), ('different', 276), ('other', 264), ('economic', 223), ('public', 210), ('current', 200), ('smart', 195), ('future', 189), ('key', 179), ('various', 179), ('green', 177), ('many', 175), ('important', 168), ('technological', 168), ('natural', 166), ('big', 163), ('real', 160), ('high', 159), ('financial', 155), ('more', 155), ('deep', 152), ('industrial', 152), ('scientific', 148), ('effective', 138), ('main', 137), ('critical', 137), ('significant', 132), ('large', 122), ('complex', 121), ('educational', 119), ('positive', 117), ('specific', 115), ('corporate', 113), ('online', 112), ('intelligent', 112), ('dynamic', 110), ('innovative', 106), ('relevant', 101), ('recent', 100), ('higher', 99), ('virtual', 97), ('traditional', 95), ('several', 95), ('potential', 95), ('practical', 92), ('non', 92), ('technical', 91), ('possible', 91), ('major', 87), ('physical', 86), ('better', 85), ('multi', 85), ('international', 84), ('first', 83), ('academic', 78), ('political', 78), ('negative', 78), ('pandemic', 78), ('collaborative', 76), ('competitive', 76), ('ethical', 76), ('long', 75), ('neural', 74), ('present', 74), ('open', 72), ('efficient', 72), ('novel', 71), ('most', 71), ('ai', 71), ('available', 70), ('common', 69), ('fuzzy', 68), ('active', 68), ('best', 67), ('essential', 65), ('necessary', 64), ('general', 64), ('particular', 64), ('same', 63), ('multiple', 63), ('able', 62), ('advanced', 61), ('strategic', 60), ('hybrid', 60), ('low', 60), ('comprehensive', 59), ('individual', 58), ('circular', 58), ('computational', 58), ('systematic', 58), ('crucial', 58)]{'ai': 7, 'artificial': 7, 'climate': 6, 'extreme': 3, 'service': 3, 'digital': 2, 'intelligent': 2, 'ml': 2, 'dis': 2, 'covid': 2, 'digitalization': 2, 'human': 2, 'algorithmic': 1, 'generic': 1, '4ir': 1, 'computing': 1, 'anthropogenic': 1, 'future': 1, 'variability': 1, 'sustainable': 1, 'corporate': 1, 'new': 1, 'environmental': 1, 'rule': 1, 'machine': 1, 'active': 1, 'adoption': 1, 'economics': 1, 'companies': 1, 'crisis': 1, 'technology': 1, 'carbon': 1, 'industry': 1, 'big': 1, 'various': 1, 'disruptive': 1, 'managerial': 1, 'scientific': 1, 'perceived': 1, 'substituting': 1, 'basic': 1, 'social': 1, 'bots': 1, 'investments': 1, 'production': 1, 'nonperforming': 1, 'external': 1, 'negative': 1, 'different': 1, 'customer': 1, 'ict': 1, 'sustainability': 1, 'summarisation': 1, 'aiserviceops': 1, 'decisions': 1, 'green': 1, 'globalization': 1, 'aviation': 1}{'ai': 9, 'artificial': 8, 'technology': 5, 'emotional': 3, 'psychological': 3, 'social': 2, 'blockchain': 2, 'deep': 2, 'business': 2, 'management': 2, 'corporate': 2, 'perceived': 1, 'neural': 1, 'customers': 1, 'mosaic': 1, 'debt': 1, 'digital': 1, 'macro': 1, 'beliefs': 1, 'employee': 1, 'esg': 1, 'structural': 1, 'educator': 1, 'innovative': 1, 'norms': 1, 'planned': 1, 'ethics': 1, 'robots': 1, 'courts': 1, 'emerging': 1, 'legal': 1, 'smart': 1, 'vaccine': 1, 'people': 1, 'universities': 1, 'demand': 1, 'symbiotic': 1, 'environment': 1, 'humans': 1, 'big': 1, 'machine': 1, 'ml': 1, 'information': 1, 'tolerant': 1, 'semi': 1}[('digital entrepreneurship ecosystem', 0.6781), ('digital entrepreneurship', 0.6052), ('revolutionary digital entrepreneurship', 0.6035), ('entrepreneurial ecosystem', 0.5878), ('ai innovation ecosystem', 0.5533), ('sociotechnical endeavors', 0.5406), ('digital economy', 0.5291), ('digital innovation', 0.5283), ('profile tech entrepreneurs', 0.5185), ('global digital knowledge economy', 0.5142), ('society digitalization', 0.512), ('digital enterprise revolution', 0.5109), ('digital economy environment', 0.5107), ('sustainable digital societies', 0.5027), ('sociotechnical digital transition', 0.5017), ('emergent digital technologies', 0.5005), ('business model innovation digitalization', 0.4984), ('digital era individuals', 0.4971), ('emergent technologies', 0.4951), ('digital society', 0.4917), ('entrepreneurs', 0.4863), ('business ecosystem', 0.4837), ('innovation ecosystem development', 0.4834), ('modern digital economy', 0.4785), ('ai industry capitalizes', 0.4752), ('sustainable digital society', 0.4724), ('human innovation', 0.4648), ('sociotechnical systems', 0.4645), ('innovative academic socioedu', 0.4644), ('innovative digital race', 0.4631), ('sustainable digital governance', 0.4617), ('digital economic life', 0.4617), ('digital innovations', 0.4599), ('competitive digital economy', 0.4569), ('new economy cyberspace', 0.4561), ('digital agenda', 0.4556), ('digital businesss success', 0.4528), ('gender analysis', 0.4511), ('digital humanities', 0.4464), ('collaborative innovation', 0.4459), ('social scientific research', 0.4458), ('knowledge economy', 0.4452), ('ai companies', 0.4445), ('business model innovation field', 0.4442), ('tech industrialists', 0.4441), ('digital disciplines', 0.4422), ('digital motivations', 0.4419), ('digital economic challenges', 0.4415), ('entrepreneurship', 0.4406), ('new transdisciplinary knowledge economy', 0.4401)]
14
8191