Skip to content

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?

Notifications You must be signed in to change notification settings

acl2171/wildfire_model

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

64 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Identifying Wildfires: Geospatial Data and Machine Learning

Allison Lee

Blog Post

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]

Project Goal

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?

Technologies

  • 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

Links to Files

  • 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
  • Python Files
    • Data Cleaning
    • Modeling

Contact

Feel free to reach out at allison.alee@gmail.com if you have questions.

About

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?

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published