Orion-AI-Lab/mesogeos
A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean. Deep Learning models for wildfire modeling, e.g. danger forecasting, burned area prediction, etc
Integrates multi-source geospatial data including MODIS satellite imagery, ERA5-Land weather variables, soil moisture indices, and topographic features into a Zarr-based datacube spanning 2006-2022 across the Mediterranean at 1km daily resolution. Provides two standardized ML tracks: binary classification for danger forecasting and regression for final burned area prediction, with accessible notebooks and reproducible evaluation frameworks for benchmarking models.
No commits in the last 6 months.
Stars
62
Forks
13
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Orion-AI-Lab/mesogeos"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mnpinto/banet
A deep learning approach for mapping and dating burned areas using temporal sequences of satellite images
Orion-AI-Lab/wildfire_forecasting
Deep Learning Models for Wildfire Danger Forecasting
IBM/predict-wildfire-intensity
WARNING: This repository is no longer maintained ⚠️ This repository will not be updated.
aravind-selvam/forest-fire-prediction
Project for Predicting Algerian Forest Fires and Fire Weather Index Using Machine Learning with Python.
UBC-MDS/forest-fire-area-prediction
This project aims to predict the burned area of forest fires in the northeast region of...