TS-SatFire: A Multi-Task Satellite Image Time-Series Dataset for Wildfire Detection and Prediction
This dataset addresses wildfire research challenges for environmental scientists and policymakers by providing a foundation for deep learning applications, though it is incremental as it builds on existing data collection efforts.
The authors tackled wildfire monitoring and prediction by creating a comprehensive multi-temporal satellite image dataset covering the contiguous U.S. from 2017 to 2021, including 3552 images and auxiliary data totalling 71 GB, to support active fire detection, burned area mapping, and wildfire progression prediction tasks.
Wildfire monitoring and prediction are essential for understanding wildfire behaviour. With extensive Earth observation data, these tasks can be integrated and enhanced through multi-task deep learning models. We present a comprehensive multi-temporal remote sensing dataset for active fire detection, daily wildfire monitoring, and next-day wildfire prediction. Covering wildfire events in the contiguous U.S. from January 2017 to October 2021, the dataset includes 3552 surface reflectance images and auxiliary data such as weather, topography, land cover, and fuel information, totalling 71 GB. The lifecycle of each wildfire is documented, with labels for active fires (AF) and burned areas (BA), supported by manual quality assurance of AF and BA test labels. The dataset supports three tasks: a) active fire detection, b) daily burned area mapping, and c) wildfire progression prediction. Detection tasks use pixel-wise classification of multi-spectral, multi-temporal images, while prediction tasks integrate satellite and auxiliary data to model fire dynamics. This dataset and its benchmarks provide a foundation for advancing wildfire research using deep learning.