Skip to content

A collection aiming to bring all the amazing work of Deep Learning for Climate Super-res together.

Notifications You must be signed in to change notification settings

paulaharder/deep-downscaling-overview

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 

Repository files navigation

Overview Deep Learning for Climate Downscaling/Super-Resolution

Feel free to add any paper on Deep Learning for Climate Super-resolution. Just create a pull request.

Papers from 2023

Title Input data Target data Model(s) Baselines Metrics Paper Code Year Month
Using Explainability to Inform Statistical Downscaling Based on Deep Learning Beyond Standard Validation Approaches ERA_Interim EWEMBI CNN - - https://arxiv.org/pdf/2302.01771.pdf - 2023 Febr
Algorithmic Hallucinations of Near-Surface Winds: Statistical Downscaling with Generative Adversarial Networks to Convection-Permitting Scales - GAN - - - https://arxiv.org/abs/2302.08720 - 2023 Febr
Physics-Constrained Deep Learning for Climate Downscaling ERA5 downsampled, WRF T2, NorESM LM TAS ERA5, WRF T2, NorESM MM TAS constr. CNN, GAN, ConvGRU, DeepVoxel Bicubic, CNN, GAN MSE, MAE, bias, SSIM, MS-SSIm, CRPS, Pearcon corr. https://arxiv.org/abs/2208.05424 https://github.com/RolnickLab/constrained-downscaling 2023 Febr
ClimaX: A foundation model for weather and climate MPI-ESM ERA5 ClimaX - Pretrained ViT UNet, ResNet RMSE, Pearson, bias https://arxiv.org/abs/2301.10343 https://github.com/microsoft/climax 2023 Jan
DL4DS—Deep learning for empirical downscaling CAMSRA NO2, ERA5, elevation, land mask CAMS NO2 CNN, GAN - MAE, SSIM, Pearson cor., PSNR https://www.cambridge.org/core/journals/environmental-data-science/article/dl4dsdeep-learning-for-empirical-downscaling https://github.com/carlos-gg/dl4ds 2023 Jan

Papers from 2022

Title Input data Target data Model(s) Baselines Metrics Paper Code Year Month
High-resolution downscaling with interpretable deep learning: Rainfall extremes over New Zealand - - - - - https://www.sciencedirect.com/science/article/pii/S2212094722001049 - 2022 Dec
Downscaling Extreme Rainfall Using Physical-Statistical Generative Adversarial Learning - - - - - https://arxiv.org/pdf/2212.01446.pdfhttps://arxiv.org/pdf/2212.01446.pdf 2022 Dec
Downscaled hyper-resolution (400 m) gridded datasets of daily precipitation and temperature (2008–2019) for the East–Taylor subbasin (western United States) - - - - - https://essd.copernicus.org/articles/14/4949/2022/ 2022 Nov
ResDeepD: A residual super-resolution network for deep downscaling of daily precipitation over India - - - - - https://www.cambridge.org/core/journals/environmental-data-science/article/resdeepd-a-residual-superresolution-network-for-deep-downscaling-of-daily-precipitation-over-india - 2022 Nov
Contrastive Learning for Climate Model Bias Correction and Super-Resolution - - - - - https://arxiv.org/abs/2211.07555 - 2022 Nov
A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts - - - - - https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2022MS003120 - 2022 Oct
Physically constrained generative adversarial networks for improving precipitation fields from Earth system models - - - - - https://www.nature.com/articles/s42256-022-00540-1 - 2022 Oct
RainNet: A Large-Scale Dataset for Spatial Precipitation Downscaling - - - - - https://arxiv.org/pdf/2012.09700.pdf https://github.com/neuralchen/RainNet 2022 Oct
Downscaling Atmospheric Chemistry Simulations with Physically Consistent Deep Learning - - - - - https://gmd.copernicus.org/preprints/gmd-2022-76/gmd-2022-76.pdf - 2022 Sept
Downscaling multi-model climate projection ensembles with deep learning (DeepESD): contribution to CORDEX EUR-44 - - - - - https://gmd.copernicus.org/articles/15/6747/2022/ - 2022 Sept
Urban precipitation downscaling using deep learning: a smart city application over Austin, Texas, USA - - - - - https://arxiv.org/abs/2209.06848 - 2022 Aug
Repeatable high-resolution statistical downscaling through deep learning - - - - - https://gmd.copernicus.org/articles/15/7353/2022/gmd-15-7353-2022.pdf - 2022 Aug
Downscaling Earth System Models with Deep Learning - - - - - https://dl.acm.org/doi/pdf/10.1145/3534678.3539031 - 2022 Aug
Machine Learning as a Downscaling Approach for Prediction of Wind Characteristics under Future Climate Change Scenarios - - - - - https://www.hindawi.com/journals/complexity/2022/8451812/ - 2022 Aug
Regional climate model emulator based on deep learning: concept and first evaluation of a novel hybrid downscaling approach - - - - - https://link.springer.com/article/10.1007/s00382-022-06343-9 - 2022 Jul
On the modern deep learning approaches for precipitation downscaling - - - - - https://arxiv.org/abs/2207.00808 - 2022 Jul
A Novel Bayesian Deep Learning Approach to the Downscaling of Wind Speed with Uncertainty Quantification - - - - - https://link.springer.com/chapter/10.1007/978-3-031-05981-0_5 - 2022 May
On deep learning-based bias correction and downscaling of multiple climate models simulations - - - - - https://link.springer.com/article/10.1007/s00382-022-06277-2 - 2022 Apr
Wind-Topo: Downscaling near-surface wind fields to high-resolution topography in highly complex terrain with deep learning - - - - - https://rmets.onlinelibrary.wiley.com/doi/full/10.1002/qj.4265 - 2022 Mar
Increasing the accuracy and resolution of precipitation forecasts using deep generative models - - - - - https://arxiv.org/pdf/2203.12297.pdf https://github.com/raspstephan/nwp-downscale - 2022
Super-resolution of near-surface temperature utilizing physical quantities for real-time prediction of urban micrometeorology - - - - - https://www.sciencedirect.com/science/article/pii/S0360132321009884 - 2022 Febr
Reconstructing High Resolution ESM Data Through a Novel Fast Super Resolution Convolutional Neural Network (FSRCNN) - - - - - https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2021GL097571 - 2022 Febr
Convolutional conditional neural processes for local climate downscaling - - - - - https://gmd.copernicus.org/articles/15/251/2022/gmd-15-251-2022.pdf https://github.com/annavaughan/convCNPClimate 2022 Jan
A Novel Deep Learning Approach to the Statistical Downscaling of Temperatures for Monitoring Climate Change - - - - - https://dl.acm.org/doi/10.1145/3523150.3523151 - 2022 Jan
Deep Learning-Based Downscaling of Temperatures for Monitoring Local Climate Change Using Global Climate Simulation Data - - - - - https://doi.org/10.1142/S2811032322500011 - 2022 Sept
A Novel Reference-Based and Gradient-Guided Deep Learning Model for Daily Precipitation Downscaling - - - - - https://www.mdpi.com/2073-4433/13/4/511 - 2022 Mar
Wind-Topo: Downscaling near-surface wind fields to high-resolution topography in highly complex terrain with deep learning - - - - - https://doi.org/10.1002/qj.4265 - 2022 Mar

Papers from 2021

Title Input data Target data Model(s) Baselines Metrics Paper Code Year Month
Extension of Convolutional Neural Network along Temporal and Vertical Directions for Precipitation Downscaling - - - - - https://arxiv.org/abs/2112.06571 - 2021 Dez
Deconditional Downscaling with Gaussian Processes - - - - - https://proceedings.neurips.cc/paper/2021/file/94aef38441efa3380a3bed3faf1f9d5d-Paper.pdf - 2021 Dec
MSG-GAN-SD: A Multi-Scale Gradients GAN for Statistical Downscaling of 2-Meter Temperature over the EURO-CORDEX Domain - - - - - https://www.mdpi.com/2673-2688/2/4/36 - 2021 Nov
Fast and accurate learned multiresolution dynamical downscaling for precipitation WRF precip., T2, IWV, SLP, topography WRF Precip. cGAN CNN, bilinear MSE, J-S distance, pattern corr. https://gmd.copernicus.org/articles/14/6355/2021/gmd-14-6355-2021.pdf https://github.com/lzhengchun/DSGAN 2021 Oct
WiSoSuper: Benchmarking Super-Resolution Methods on Wind and Solar Data - - - - - https://arxiv.org/pdf/2109.08770.pdf https://github.com/RupaKurinchiVendhan/WiSoSuper 2021 Sept
Super-resolution data assimilation - - - - - https://arxiv.org/pdf/2109.08017.pdf - 2021 Sept
Deep Learning-Based Super-Resolution Climate Simulator-Emulator Framework for Urban Heat Studies - - - - - https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2021GL094737 - 2021 Sept
Towards Representation Learning of Atmospheric Dynamics - - - - - https://arxiv.org/abs/2109.09076 https://github.com/sehoffmann/atmodist 2021 Sept
Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields With a Generative Adversarial Network - - - - - https://ieeexplore.ieee.org/document/9246532 https://github.com/jleinonen/downscaling-rnn-gan 2021 sept
A downscaling approach for constructing high-resolution precipitation dataset over the Tibetan Plateau from ERA5 reanalysis - - - - - https://www.sciencedirect.com/science/article/pii/S0169809521001265 - 2021 Jul
Comparisons of Machine Learning Methods of Statistical Downscaling Method: Case Studies of Daily Climate Anomalies in Thailand - - - - - https://journals.riverpublishers.com/index.php/JWE/article/view/4869 - 2021 Jul
Adjusting spatial dependence of climate model outputs with cycle-consistent adversarial networks - - - - - https://link.springer.com/article/10.1007/s00382-021-05869-8 - 2021 Jul
On the suitability of deep convolutional neural networks for continental-wide downscaling of climate change projections - - - - - https://link.springer.com/article/10.1007/s00382-021-05847-0 - 2021 Jun
Spatio-\ Downscaling of Climate Data Using Convolutional and Error-Predicting Neural Networks - - - - - https://www.frontiersin.org/articles/10.3389/fclim.2021.656479/full https://github.com/aserifi/convolutional-downscaling 2021 Apr
Deep Learning for Daily Precipitation and Temperature Downscaling - - - - - https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2020WR029308 - 2021 April
Augmented Convolutional LSTMs for Generation of High-Resolution Climate Change Projections - - - - - https://ieeexplore.ieee.org/document/9348885 https://github.com/cryptonymous9/Augmented-ConvLSTM 2021 Febr
ClimAlign: Unsupervised statistical downscaling of climate variables via normalizing flows - - - - - https://dl.acm.org/doi/10.1145/3429309.3429318 https://github.com/bgroenks96/generative-downscaling 2021 Jan
Deep learning-based downscaling of summer monsoon rainfall data over Indian region - - - - - https://link.springer.com/article/10.1007/s00704-020-03489-6 - 2021 Jan
Regional downscaling of climate data using deep learning and applications for drought and rainfall forecasting - - - - - https://eresearchnz.figshare.com/articles/presentation/Regional_downscaling_of_climate_data_using_deep_learning_and_applications_for_drought_and_rainfall_forecasting/14110157/1 - 2021 Feb
Deep learning-based downscaling of seasonal forecasts over the Iberian Peninsula - - - - - https://meetingorganizer.copernicus.org/EGU21/EGU21-12253.html - 2021 Mar
Deep learning-based downscaling of tropospheric nitrogen dioxide using ground-level and satellite observations - - - - - https://pubmed.ncbi.nlm.nih.gov/33940718/ - 2021 Jun

Papers from 2020

Title Input data Target data Model(s) Baselines Metrics Paper Code Year Month
Investigating two super-resolution methods for downscaling precipitation: ESRGAN and CAR - - - - - https://arxiv.org/pdf/2012.01233.pdf - 2020 Dec
Deep-Learning-Based Gridded Downscaling of Surface Meteorological Variables in Complex Terrain. Part I: Daily Maximum and Minimum 2-m Temperature Downsampled PRISM, elevation TMAX/TMIN PRISM UNet bicubic, regression MAE, pearson, corr. https://journals.ametsoc.org/view/journals/apme/59/12/jamc-d-20-0057.1.xml https://github.com/yingkaisha/JAMC_20_0057 2020 Nov
Deep-Learning-Based Gridded Downscaling of Surface Meteorological Variables in Complex Terrain. Part II: Daily Precipitation - - - - - https://journals.ametsoc.org/view/journals/apme/59/12/jamc-d-20-0058.1.xml https://github.com/yingkaisha/JAMC_20_0057 2020 Nov
CliGAN: A structurally sensitive convolutional neural network model for statistical downscaling of precipitation from multi-model ensembles - - - - - https://www.mdpi.com/2073-4441/12/12/3353 - 2020 Nov
Radar Super Resolution Using a Deep Convolutional Neural Network - - - - - https://journals.ametsoc.org/view/journals/atot/37/12/jtech-d-20-0074.1.xml?tab_body=pdf - 2020 Nov
Deep-Learning based climate downscaling using the super-resolution method: a case study over the western US - - - - - https://gmd.copernicus.org/preprints/gmd-2020-214/gmd-2020-214.pdf - 2020 Sept
A comparative study of convolutional neural network models for wind field downscaling - - - - - https://arxiv.org/ftp/arxiv/papers/2008/2008.12257.pdf - 2020 Sept
Climate Downscaling Using YNet: A Deep Convolutional Network with Skip Connections and Fusion - - - - - https://dl.acm.org/doi/pdf/10.1145/3394486.3403366 https://github.com/yuminliu/Downscaling 2020 Aug
Statistical Downscaling of Temperature Distributions from the Synoptic Scale to the Mesoscale Using Deep Convolutional Neural Networks - - - - - https://arxiv.org/abs/2007.10839 - 2020 Jul
Adversarial super-resolution of climatological wind and solar data NREL Wind toolkit + NSRDB downsampled (train), NCAR CCSM (test) NREL Wind toolkit + NSRDB GAN bicubic, CNN MSE https://www.pnas.org/doi/10.1073/pnas.1918964117 https://github.com/NREL/PhIRE 2020 Jul
Statistical downscaling of daily temperature and precipitation over China using deep learning neural models: Localization and comparison with other methods - - - - - https://rmets.onlinelibrary.wiley.com/doi/abs/10.1002/joc.6769 - 2020 Jul
Generalization Properties of Machine-Learning Based Weather Model Downscaling - - - - - https://ai4earthscience.github.io/iclr-2020-workshop/papers/ai4earth25.pdf - 2020 May
Configuration and Intercomparison of Deep Learning Neural Models for Statistical Downscaling ERA-Interim geopot., zonal + mer. wind, tempt, humidity E-Obs temp. precip. CNN CNN, GLM bias mean, bias 2-perc., bias 98-perc., RMSE, Pearson correlation, Spearman correlation, ROC sklill score https://gmd.copernicus.org/preprints/gmd-2019-278/gmd-2019-278.pdf https://github.com/SantanderMetGroup/DeepDownscaling 2020 Apr
ResLab: Generating High-Resolution Climate Prediction Through Image Super-Resolution CMA precip, humidity downsampled, topography CMA precip CNN bilinear, DeepSD, VDSR, ESPCN, RDN, LapSRN RMSE, prediction correction, prediction ommision, fasle alarm ratio, threat score https://ieeexplore.ieee.org/document/9001044 https://github.com/Jianxin-Cheng/SR-Climate-Prediction 2020 Febr
Performance of statistical and machine learning ensembles for daily temperature downscaling - - - - - https://link.springer.com/article/10.1007/s00704-020-03098-3 - 2020

Papers from 2017-2019

Title Input data Target data Model(s) Baselines Metrics Paper Code Year Month
Downscaling numerical weather models with GANs - - - - - https://alok.github.io/assets/ci-2019.pdf - 2019 Oct
Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning - - - - - https://arxiv.org/abs/1802.04742 - 2018 May
Downscaling rainfall using deep learning long short-term memory and feedforward neural network - - - - - https://rmets.onlinelibrary.wiley.com/doi/abs/10.1002/joc.6066 - 2019 Mar
Improving Precipitation Estimation Using Convolutional Neural Network - - - - - https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2018WR024090 - 2019 Jan
Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation - - - - - https://link.springer.com/article/10.1007/s00704-018-2613-3 - 2018 Sept
Generating High Resolution Climate Change Projections through Single Image Super-Resolution: An Abridged Version - - - - - https://www.ijcai.org/proceedings/2018/0759.pdf - 2018 Aug
Statistical downscaling of precipitation using long short-term memory recurrent neural networks - - - - - https://link.springer.com/article/10.1007/s00704-017-2307-2 - 2017 Nov
A Machine Learning Approach to Non-uniform Spatial Downscaling of Climate Variables - - - - - https://ieeexplore.ieee.org/abstract/document/8215681 - 2017 Nov
DeepSD: Generating High-Resolution Climate Change Projections through Single Image Super-Resolution - - - - - https://dl.acm.org/doi/10.1145/3097983.3098004 https://github.com/tjvandal/deepsd 2017 Aug

Papers before 2017

Title Input data Target data Model(s) Baselines Metrics Paper Code Year Month
Spatial Interpolation of Surface Air Temperatures Using Artificial Neural Networks: Evaluating Their Use for Downscaling GCMs - - - - - https://doi.org/10.1175/1520-0442(2000)013%3C0886:SIOSAT%3E2.0.CO;2 - 2000 Mar
Simulation of daily temperatures for climate change scenarios over Portugal: a neural network model approach - - - - - https://www.jstor.org/stable/24866022 - 1999 Sep

At the moment not included: Other ML techniques than Deep Learning and application to satellite imagery.

About

A collection aiming to bring all the amazing work of Deep Learning for Climate Super-res together.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •