Unsupervised Structural Damage Assessment from Space using the Segment Anything Model (USDA-SAM): A Case Study of the 2023 Türkiye Earthquake

Abstract

This paper explores advanced deep learning methods, specifically utilising the Segment Anything Model (SAM) along with image processing techniques, to evaluate the structural damages caused by the devastating earthquake that occurred in Turkey on February 6, 2023. Leveraging exceptionally high-resolution pre- and post-disaster imagery provided by Maxar Technologies, this paper showcases the efficacy of SAM in contrasting and quantifying the magnitude of structural devastation. The proposed \textit{unsupervised structural damage assessment} (USDA-SAM) method entails a thorough comparative analysis of aerial imagery captured both before and after the seismic event, facilitating a nuanced evaluation of its impact on buildings and critical infrastructure. USDA-SAM also proposes two metrics - \textit{damage assessment score} ($DAS$) and \textit{affected number of buildings} ($N_{\text{b}/km^2}$) - to quantitatively measure the damage caused by the disasters. The study highlights the transformative potential of deep learning and image processing, shedding light on their key role in fortifying disaster response strategies and emphasising technology's indispensable contribution to mitigating the challenges posed by natural disasters, such as earthquakes.