CanadaFire2023: Burned Area Mapping Datasets and Benchmarks for Canadian Wildfires in 2023 (Papers Track)
Zilong Zhong (McMaster University); Alemu Gonsamo (McMaster University)
Abstract
In 2023, wildfires burned record-breaking areas in Canada, resulting in significant carbon loss, exacerbating climate change, and underscoring the need for relevant datasets and machine learning methods for effective and efficient analysis. To understand the fire development processes and assess the climate impact of this natural disaster, burned area mapping datasets are essential for generating high-quality burned scar maps, enabling a comprehensive analysis of the 2023 wildfires, particularly given the vast expanse of Canada. To this end, we propose the CanadaFire2023 dataset, which includes burned area mapping data collected from multiple satellite platforms, namely, Landsat-8, Landsat-9, and Sentinel-2, specifically focused on these wildfires in the recorded history of Canada. To our knowledge, this is the first dataset specifically focused on burned area detection related to the unprecedented 2023 Canadian wildfires, using individual satellite imagery. We also trained four deep learning models—FCN, U-Net, multiscale ResNet, and SegFormer—for burned area mapping and evaluated the mapping performance using binary segmentation metrics, demonstrating that these datasets can serve as benchmarks for the research community studying wildfires and their environmental consequences. The CanadaFire2023 dataset could facilitate downstream applications such as disaster management, carbon emission estimation, and climate change mitigation.