Rapid post-earthquake building damage mapping with object-oriented SAM fine-tuning: a case study of the 2023 Jishishan earthquake
Authors:
Preprint
- 11 December 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Earthquakes pose severe risks to lives and infrastructure, demanding rapid and accurate building-damage assessments to guide response. High-spatial-resolution (HSR) imagery is essential for this task, yet conventional convolutional neural networks (CNNs) can be limited in capturing long-range dependencies, especially in dense urban fabrics. We introduce S2AC-Net, an operational framework that fuses global context with local features for post-earthquake damage mapping. In S2AC-Net, the Segment Anything Model (SAM) replaces traditional multi-resolution segmentation for pre-event imagery: a frozen Vision Transformer encoder with lightweight adapters produces building-probability maps, which are merged with SAM masks to delineate building footprints. Spectral and texture features from pre- and post-event images are then mapped to these objects to form feature vectors, which—together with field survey labels—drive a CNN classifier for multi-class damage grading. Applied to the December 2023 Jishishan earthquake (Gansu, China), S2AC-Net achieved 0.928 overall accuracy for building localization and an overall F1 of 0.882 for damage assessment. These results demonstrate that integrating SAM-based global context with object-level feature fusion overcomes key limitations of purely CNN-based pipelines and provides a scalable pathway for rapid, reliable remote-sensing–based disaster assessment and urban resilience planning.Keywords
All Related Versions
This publication has 46 references indexed in Scilit:
- Tunnel SAM adapter: Adapting segment anything model for tunnel water leakage inspectionGeohazard Mechanics, 2024
- InSAR-based rapid damage assessment of urban building portfolios following the 2023 Turkey earthquakeInternational Journal of Disaster Risk Reduction, 2024
- A multimodal hyper-fusion transformer for remote sensing image classificationInformation Fusion, 2023
- Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modelingEngineering Structures, 2020
- Extraction of urban building damage using spectral, height and corner information from VHR satellite images and airborne LiDAR dataISPRS Journal of Photogrammetry and Remote Sensing, 2020
- A prediction method of building seismic loss based on BIM and FEMA P-58Automation in Construction, 2019
- Investigation on damage progression during the 2016–2017 seismic sequence in Central Italy using the European Macroseismic Scale (EMS-98)Bulletin of Earthquake Engineering, 2019
- Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high resolution oblique aerial images, and multiple-kernel-learningISPRS Journal of Photogrammetry and Remote Sensing, 2018
- A New Neuro-Fuzzy Approach for Post-earthquake Road Damage Assessment Using GA and SVM Classification from QuickBird Satellite ImagesJournal of the Indian Society of Remote Sensing, 2017
- Classification of Collapsed Buildings for Fast Damage and Loss AssessmentBulletin of Earthquake Engineering, 2006