Sentinel-2 Active Fire Segmentation: Analyzing Convolutional and Transformer Architectures, Knowledge Transfer, Fine-Tuning, and Seam Lines

Active fire segmentation in satellite imagery is a critical remote sensing task, providing essential support for planning, decision-making, and policy development. Several techniques have been proposed for this problem over the years, generally based on specific equations and thresholds, which are sometimes empirically chosen. Some satellites, such as MODIS and Landsat-8, have consolidated algorithms for this task. However, for other important satellites such as Sentinel-2, this is still an open problem. In this letter, we explore the possibility of using transfer learning to train convolutional and transformer-based deep architectures (U-Net, DeepLabV3+, and SegFormer) for active fire segmentation. We pretrain these architectures based on Landsat-8 images and automatically labeled samples and fine-tune them to Sentinel-2 images. The experiments show that the proposed method achieves $F1$ -scores of up to 88.4% for Sentinel-2 images, outperforming three threshold-based algorithms by at least 19% while maintaining a low demand for manually labeled samples. We also address detection over seam-line regions that present a particular challenge for existing methods. The source code and trained models are available at https://github.com/Minoro/l8tos2-transf-seamlines.