Evaluation of Simulated SAR images for building damage classification

Synthetic Aperture Radar (SAR) imagery is invaluable for assessing disaster-induced changes due to its capacity to capture detailed surface information despite varying environmental conditions. However, the scarcity of high-resolution SAR imagery before disasters presents significant challenges for accurately recognizing changes in damaged buildings, particularly in scenarios requiring pre- and post-disaster image pairs for machine-learning methods that rely on large samples. To address this challenge, our study proposes an innovative solution utilizing Simulated SAR imagery generated through ray tracing-based SAR simulation, we generated high-quality pre-disaster SAR images that closely replicate the scattering properties of Authentic SAR imagery using same sensor orientation as post-disaster image. In this study, to evaluate the feasibility of using Simulated SAR images for deep learning-based building damage classification, we investigate three different scenarios: (1) Authentic pre- and post-disaster image pairs, (2) Simulated pre-disaster images and Authentic post-disaster images, and (3) post-disaster images alone. The methodology was applied in Mashiki Town, Japan, which was heavily impacted by the 2016 Kumamoto earthquake. Our classification results showed that the simulated pre-disaster SAR data produced outcomes comparable to those of using authentic image pairs and were clearly superior to the approach that utilized only post-event images. These findings illustrate that Simulated SAR imagery is a reliable alternative when Authentic pre-disaster data is unavailable, enabling fast, accurate damage assessments to support emergency decision-making.