Robust Burned Area Delineation through Multitask Learning
This work addresses the challenge of robust burned area delineation for environmental monitoring and post-fire assessment, representing an incremental improvement over existing methods.
The paper tackled the problem of accurately delineating burned areas from satellite imagery by proposing a multitask learning framework that incorporates land cover classification as an auxiliary task, resulting in improved performance over standard binary segmentation models like UPerNet and SegFormer.
In recent years, wildfires have posed a significant challenge due to their increasing frequency and severity. For this reason, accurate delineation of burned areas is crucial for environmental monitoring and post-fire assessment. However, traditional approaches relying on binary segmentation models often struggle to achieve robust and accurate results, especially when trained from scratch, due to limited resources and the inherent imbalance of this segmentation task. We propose to address these limitations in two ways: first, we construct an ad-hoc dataset to cope with the limited resources, combining information from Sentinel-2 feeds with Copernicus activations and other data sources. In this dataset, we provide annotations for multiple tasks, including burned area delineation and land cover segmentation. Second, we propose a multitask learning framework that incorporates land cover classification as an auxiliary task to enhance the robustness and performance of the burned area segmentation models. We compare the performance of different models, including UPerNet and SegFormer, demonstrating the effectiveness of our approach in comparison to standard binary segmentation.