Machine learning models improve near real time fire detection from satellite
Construction and Evaluation of Machine Learning Models for Near-Real-Time Fire Detection from MTG FCI Imagery
Computer Vision and Pattern Recognition
Summary
Detecting wildfires quickly is important to help stop them from spreading. The authors tested computer programs that learn from data to spot fires using images from a satellite called MTG FCI. These learning models, especially with finer 1-kilometer detail, found fires more accurately and faster than older methods. Their models also picked up on small fires better and could detect fires over four hours earlier. The trained models are shared openly so others can use them.
What this means in practice
- •For emergency response teams: Use improved machine learning fire detection models to identify wildfires earlier for faster response and containment.
- •For environmental monitoring services: Implement these 1-km resolution models into near-real-time satellite monitoring to enhance detection accuracy across different ecological regions.
Authors
Asaf Vanunu, Boaz Nadler, Arnon Karnieli
Abstract
Geostationary satellite observations are important for wildfire detection and monitoring. The current study evaluates machine learning models for MTG FCI near-real-time fire detection in 1- and 2-km spatial configurations and compares them with threshold-based algorithms. The models were trained and evaluated using VIIRS fire reference data across diverse ecological regions in Europe, Africa, and the Middle East. The key results are that 1-km models significantly outperform both their 2-km variants and operational threshold products. The constructed 1-km models achieved F1 scores higher by up to 0.36 compared to baseline products. Importantly, the 1-km models detected small fires with higher probability compared to competing models. Finally, the models robustly detected fires up to 260 min earlier than baseline products. To support opensource applications, our trained models are publicly available.