A Deep Learning framework for building damage assessment using VHR SAR and geospatial data: demonstration on the 2023 Turkiye Earthquake

2025-06-27

AI Summary

Optical imagery-based building damage assessment is often hindered by cloud/fog occlusion or unavailability of pre-disaster reference imagery. Method: This paper proposes a multimodal deep learning framework that relies solely on single-epoch, very-high-resolution SAR imagery—specifically COSMO-SkyMed—augmented with OpenStreetMap building footprints, digital surface models (DSMs), and Global Earthquake Model (GEM) seismic exposure attributes, to enable end-to-end damage identification without pre-disaster optical data. Contribution/Results: The method innovatively incorporates geospatial priors to enhance model generalization and discriminative accuracy in the absence of pre-event imagery. Evaluated on the 2023 Turkey earthquake region, it achieves significant F1-score improvement through multi-source geospatial feature integration. The framework demonstrates strong scalability and supports rapid, automated post-disaster damage assessment in complex urban environments.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Building damage identification shortly after a disaster is crucial for guiding emergency response and recovery efforts. Although optical satellite imagery is commonly used for disaster mapping, its effectiveness is often hampered by cloud cover or the absence of pre-event acquisitions. To overcome these challenges, we introduce a novel multimodal deep learning (DL) framework for detecting building damage using single-date very high resolution (VHR) Synthetic Aperture Radar (SAR) imagery from the Italian Space Agency (ASI) COSMO SkyMed (CSK) constellation, complemented by auxiliary geospatial data. Our method integrates SAR image patches, OpenStreetMap (OSM) building footprints, digital surface model (DSM) data, and structural and exposure attributes from the Global Earthquake Model (GEM) to improve detection accuracy and contextual interpretation. Unlike existing approaches that depend on pre and post event imagery, our model utilizes only post event data, facilitating rapid deployment in critical scenarios. The framework effectiveness is demonstrated using a new dataset from the 2023 earthquake in Turkey, covering multiple cities with diverse urban settings. Results highlight that incorporating geospatial features significantly enhances detection performance and generalizability to previously unseen areas. By combining SAR imagery with detailed vulnerability and exposure information, our approach provides reliable and rapid building damage assessments without the dependency from available pre-event data. Moreover, the automated and scalable data generation process ensures the framework's applicability across diverse disaster-affected regions, underscoring its potential to support effective disaster management and recovery efforts. Code and data will be made available upon acceptance of the paper.

Problem

• Detects building damage post-disaster using SAR and geospatial data
• Overcomes optical imagery limitations like cloud cover with SAR
• Enables rapid assessment without pre-event imagery dependency

Innovation

• Uses VHR SAR and geospatial data for damage assessment
• Integrates OSM, DSM, and GEM data for accuracy
• Operates with only post-event data for rapid deployment