Allison Lee
This project was created over the course of 2.5 weeks as part of the Flatiron School Data Science Fellowship in DC. This project is part of a longer-term goal to explore whether we can use machine learning approaches to predict the spread of wildfires.
--Project Status: [Active]
Can we apply machine learning techniques to predict where wildfires are most likely to spread? This project explores a subset of that question: for one point in time (December 22, 2019), can we use weather data to identify active fires, burned areas, land (other), and water in Australia?
- Python
- Google Earth Engine
- Google Cloud Platform
- Rasterio
- Xarray
- Geopandas
- Pandas
- Numpy
- Sci-kit Learn
- Scipy
- Pyarrow
- IMBLearn
- Joblib
- Matplotlib
- Tableau
- Yellowbrick
- Git
- Jupyter Lab
- Slidedeck (PDF)
- Data Sources (accessed via Google Earth Engine)
- MCD64A1.006 MODIS Burned Area Monthly Global 500m (Land Processes Distributed Active Archive Center (LP-DAAC) within NASA’s Earth Observing System Data and Information System)
- MOD14A1.006: Terra Thermal Anomalies & Fire Daily Global 1km (Land Processes Distributed Active Archive Center (LP-DAAC) within NASA’s Earth Observing System Data and Information System)
- GSMaP Operational: Global Satellite Mapping of Precipitation (Earth Observation Research Center, Japan Aerospace Exploration Agency)
- Global Land Data Assimilation System (GLDAS 2.1) (NASA’s Goddard Earth Sciences Data and Information Services Center)
- Notebooks
- Master Notebook
- Data Collection
- Data Cleaning
- Modeling
- Python Files
- Data Cleaning
- Modeling
Feel free to reach out at allison.alee@gmail.com if you have questions.