2026 IEEE Mediterranean and Middle-East geoscience and remote sensing symposium (M2GARSS)

This study evaluates convolutional U-Net and transformer-based SegFormer architectures using very high-resolution (20 cm) airborne imagery for landslide segmentation in the Emilia-Romagna region in northern Italy. In May 2023, the region experienced two extreme rainfall events that triggered a large number of landslides, motivating the need for accurate post-event mapping. Results show that transformer models consistently outperform CNNs, with SegFormer MiT-B2 achieving strong baseline performance (F1=84.57%,IoU=55.11%,mIoU=75.81%). Regarding loss-function, the Tversky configuration with α=0.6 and β=0.4 yields the best overall improvement, increasing performance to F1=85.43%,IoU=56.11%, and mIoU=75.97%. These results suggest the effectiveness of hierarchical transformer encoders and carefully tuned loss functions for accurate and reliable landslide mapping.