Orion-AI-Lab/wildfire_forecasting
Deep Learning Models for Wildfire Danger Forecasting
Implements LSTM and ConvLSTM architectures for spatiotemporal wildfire danger classification on multi-spectral satellite imagery and meteorological data. Built on PyTorch Lightning with Hydra configuration management, enabling reproducible experiment tracking and modular training pipelines. Includes a Random Forest baseline and supports both temporal and spatiotemporal feature modeling on large-scale geospatial datasets (250GB+).
No commits in the last 6 months.
Stars
79
Forks
17
Language
Python
License
MIT
Category
Last pushed
Sep 01, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Orion-AI-Lab/wildfire_forecasting"
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
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WARNING: This repository is no longer maintained ⚠️ This repository will not be updated.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.
Orion-AI-Lab/mesogeos
A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean. Deep Learning...
UBC-MDS/forest-fire-area-prediction
This project aims to predict the burned area of forest fires in the northeast region of...