Cross-Polarization Fusion of VV AND VH SAR Observations for Improved Flood Mapping

2026-05-03

AI Summary

This study addresses the challenge of accurately delineating flood extents in complex terrains—particularly vegetated areas—where single-polarization synthetic aperture radar (SAR) struggles to distinguish between surface and volume scattering. To overcome this limitation, the authors propose a deep learning–based cross-polarization fusion semantic segmentation method that jointly models dual-polarization SAR data (VV and VH) through a multi-channel input framework, thereby leveraging their complementary scattering characteristics. Experimental results demonstrate that, under identical training conditions, the proposed fusion strategy significantly outperforms single-polarization models, achieving consistent improvements in key metrics such as Intersection over Union (IoU) and F1-score. Notably, the approach enables more accurate and robust extraction of flood boundaries over heterogeneous surfaces and densely vegetated regions.

Abstract

Synthetic Aperture Radar (SAR) imagery is widely used for flood monitoring due to its all-weather and day-night imaging capability. However, flood mapping using single-polarization SAR data remains challenging in complex environments where surface and volume scattering coexist. In this paper, we investigate the effectiveness of cross-polarization fusion of VV and VH SAR observations for improved flood mapping. A deep learning-based segmentation framework is employed to jointly exploit complementary information from VV and VH polarizations. To ensure a fair evaluation, three configurations are compared under identical training conditions: VV only, VH only, and fused VV-VH input. Performance is assessed using standard flood mapping metrics, including Intersection over Union (IoU) and F1-score, along with qualitative visual analysis. Experimental results demonstrate that VV-VH fusion consistently outperforms single-polarization models, particularly in vegetated and heterogeneous flood regions, leading to more accurate flood boundary delineation. The findings highlight the importance of cross-polarization SAR fusion for enhancing the reliability of SAR-based flood mapping in disaster monitoring applications.

Problem

• flood mapping
• single-polarization SAR
• surface and volume scattering
• complex environments
• flood boundary delineation

Innovation

• cross-polarization fusion
• VV-VH SAR
• deep learning segmentation
• flood mapping
• synthetic aperture radar