Enhancing deep learning performance on burned area delineation from SPOT-6/7 imagery for emergency management
This work addresses the need for fast and accurate burned area mapping to support emergency response and ecosystem recovery after wildfires, though it is incremental in improving existing methods.
This study tackled the problem of efficiently delineating burned areas from SPOT-6/7 imagery for emergency management by introducing a supervised semantic segmentation workflow, finding that U-Net and SegFormer performed similarly with limited data, but SegFormer required more resources, while incorporating land cover data enhanced robustness without increasing inference time.
After a wildfire, delineating burned areas (BAs) is crucial for quantifying damages and supporting ecosystem recovery. Current BA mapping approaches rely on computer vision models trained on post-event remote sensing imagery, but often overlook their applicability to time-constrained emergency management scenarios. This study introduces a supervised semantic segmentation workflow aimed at boosting both the performance and efficiency of BA delineation. It targets SPOT-6/7 imagery due to its very high resolution and on-demand availability. Experiments are evaluated based on Dice score, Intersection over Union, and inference time. The results show that U-Net and SegFormer models perform similarly with limited training data. However, SegFormer requires more resources, challenging its practical use in emergencies. Incorporating land cover data as an auxiliary task enhances model robustness without increasing inference time. Lastly, Test-Time Augmentation improves BA delineation performance but raises inference time, which can be mitigated with optimization methods like Mixed Precision.