Rapid Assessment of Earthquake-Induced Building Damage Using Optical Image Correlation
- 26 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 1-11
Abstract
Rapid assessment of earthquake-damaged building-such as area, quantity, and severity-is crucial for timely post-earthquake rescue. Pre- and post-earthquake data collected from optical remote sensing systems can effectively resolve earthquake deformation. Among them, the normalized correlation coefficient reduction (NCCR) shows promise in directly reflecting building damage. Here we propose an automated processing chain for building damage detection, which integrates subpixel image correlation technique, deep-learning-based segmentation and anomaly detection models, and a weight stacking method. We applied this chain to assess building damage of 77 cities affected by the 2023 Türkiye earthquake doublet. Our results demonstrate that the method effectively and accurately detects earthquake-induced building damages, aligning closely with officially reported damage and PGA data. By comparing our findings with official damage degree data from Kahramanmaraş, we constrained the NCCR thresholds for five damage levels: no damage (0.21), slight damage (0.37), moderate damage (0.50), serious damage (0.71), and destroyed (0.82). Additionally, we found that cities on the fault hanging wall and footwall need to be over 23 km and 12 km away from the fault, respectively, to experience low damage levels (NCCR below 0.16). This reveals significant differences in building damage between the two fault walls, improving our understanding of the relationship between building damage and proximity to causative faults. Our proposed methodology holds great potential for rapidly providing critical building damage information, thereby supporting efficient post-earthquake rescue and emergency response efforts.Keywords
Funding Information
- National Natural Science Foundation of China (42494861)
- National Natural Science Foundation of China (42504005)
- Postdoctoral Fellowship Program (Grade B) of China Postdoctoral Science Foundation (GZB20250098)
- China Postdoctoral Science Foundation (2025M770383)
- National Natural Science Foundation of China (2025M770383)
- National Nonprofit Fundamental Research of the Institute of Geology, China Earthquake Administration (IGCEA2523)
This publication has 35 references indexed in Scilit:
- Evaluation of ground motions and seismic performance of RC buildings after 2023 Kahramanmaraş earthquakes: design and construction deficienciesBulletin of Earthquake Engineering, 2025
- Technical and Socio‐Economic Perspective on the Disaster of the Century (6 February 2023 Earthquake) in Türkiye on the Second AnniversaryGeological Journal, 2025
- The aftermath of 2023 Kahramanmaras earthquakes: evaluation of strong motion data, geotechnical, building, and infrastructure issuesNatural Hazards, 2024
- A Deep Learning Application for Building Damage Assessment Using Ultra-High-Resolution Remote Sensing Imagery in Turkey EarthquakeInternational Journal of Disaster Risk Science, 2023
- Preliminary investigation of building damage in Hatay under February 6, 2023 Turkey earthquakesEarthquake Engineering and Engineering Vibration, 2023
- A novel attention-based deep learning method for post-disaster building damage classificationExpert Systems with Applications, 2022
- Active fault database of TurkeyBulletin of Earthquake Engineering, 2016
- Application of open‐source photogrammetric software MicMac for monitoring surface deformation in laboratory modelsJournal of Geophysical Research: Solid Earth, 2016
- Geodetic Imaging Using Optical Systems2015
- Classification of Collapsed Buildings for Fast Damage and Loss AssessmentBulletin of Earthquake Engineering, 2006