Canada Wildfire Prediction Using Deep Learning.
The objective is to predict the future fire occurrences for the next year given various features from the past year.
- MODIS/Terra Vegetation Indices Monthly L3 Global 1 km SIN Grid
- Normalized Difference Vegetation Index (NDVI)
- Enhanced Vegetation Index (EVI)
- MODIS/Terra Leaf Area Index/FPAR 8-Day L4 Global 500 m SIN Grid
- Leaf Area Index (LAI)
- MODIS/Terra Land Surface Temperature/Emissivity 8-Day L3 Global 1 km SIN Grid
- Land Surface Temperature (LST)
- MODIS/Terra Thermal Anomalies/Fire 8-Day L3 Global 1 km SIN Grid
- Fire Mask
- MODIS/Terra+Aqua Burned Area Monthly L3 Global 500 m SIN Grid
- Burn Area
- MODIS/Terra Net Evapotranspiration Gap-Filled 8-Day L4 Global 500 m SIN Grid
- Total Evapotranspiration
- Daymet: Daily Surface Weather Data on a 1-km Grid for North America, Version 4 R1
- Day Length (dayl)
- Precipitation (prcp)
- Maximum air temperature (tmax)
- Minimum air temperature (tmin)
- Water vapor pressure (vp)
- NASADEM Merged DEM Global 1 arc second
- Elevation
- ASTER Global Water Bodies Database
- Water Bodies
- All features that are not already monthly based are averaged to have a monthly temporal granularity.