High-precision flood detection and mapping via multi-temporal SAR change analysis with semantic token-based transformer

• Published in: International journal of applied earth observation and geoinformation Vol. 131; p. 103991
• Main Authors: Saleh, Tamer, Holail, Shimaa, Xiao, Xiongwu, Xia, Gui-Song
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.07.2024; Elsevier
• Subjects: CNN; Flood extraction; Khartoum–Sudan; Sentinel-1 SAR; Transformer; CNN; Transformer; Khartoum–Sudan; Flood extraction; Sentinel-1 SAR
• ISSN: 1569-8432; 1872-826X
• DOI: 10.1016/j.jag.2024.103991

Flood detection in crisis and disaster management is significantly facilitated by the analysis of synthetic aperture radar (SAR) imagery. Traditional flood detection techniques focus more on SAR image pairs than on the optical level. However, the distinctive characteristics of SAR images, characterized by limited visual information, pervasive speckle noise, and analogous backscatter signals, present formidable obstacles to accurately identifying water bodies and extracting change features. Consequently, the performance of existing methods remains unsatisfactory. This paper addresses this challenge by focusing on disparities between SAR image pairs and introducing a pioneering semantic token-based transformer network, denoted as SemT-Former, to enhance flood detection accuracy. SemT-Former operates by prioritizing changes of interest rather than fully comprehending the entire image scene. This is achieved through the integration of temporal-wise feature representation and the introduction of a class token to capture high-level segmentation associated with changes in water bodies. These innovations augment the model’s capacity to discriminate between genuine changes in water bodies and spurious changes induced by similar signals or speckle noise. The effectiveness of SemT-Former is evaluated through a case study in Khartoum, Sudan, focusing on flood detection and the estimation of damaged farmland near river confluences. Experimental results demonstrate that SemT-Former outperforms existing methods, exhibiting a 90.6% improvement in F1-score and an 88.5% enhancement in IoU. This underscores SemT-Former as a promising solution for precise and effective flood mapping from SAR images. •TSCA is proposed for capturing contextual information and reducing self-attention complexity.•CTCE is introduced for enhancing the change features of multi-temporal SAR imagery.•The differential relationship between change features and semantic tokens is founded.•DFF is proposed to enhance differential image features and address speckle noises.•A novel SemT-Former framework is proposed and it performed best for flood mapping.