A Review on Building Earthquake Damage Assessment Using Multi-Source Remote Sensing Imagery

Liyi Han

doi:10.6911/WSRJ.202609_12(9).0006

Authors

Liyi Han Gansu Earthquake Agency, Lanzhou 730000, China

DOI:

https://doi.org/10.6911/WSRJ.202609_12(9).0006

Keywords:

Multi-source remote sensing imagery; Building earthquake damage assessment; Multimodal data fusion; Damage grading standards; Emergency decision support.

Abstract

The seismic damage assessment of buildings is an important basis for post-earthquake emergency response, deployment of search and rescue forces, disaster loss assessment and post-disaster reconstruction. With the advantages of large-scale coverage and non-contact observation, multi-source remote sensing images have become an important data source for rapid and automated evaluation of post-earthquake building damage. This paper focuses on the application of multi-source remote sensing images in the evaluation of earthquake damage of buildings, and systematically sorts out the data sets, task paradigms, damage levels, evaluation indicators and typical methods in this field. First, compare the four commonly used public data sets of xBD, QuickQuakeBuildings, BRIGHT and MEDBFS, and analyze their image modality, time-phase configuration, spatial resolution, task granularity and damage label system; then, according to the vein of technical evolution, the system Summarize the development process from spectral, texture and visual feature engineering to traditional machine learning, deep learning, two-time phase change detection, single-time phase evaluation, two-stage method, integrated learning and visual basic large models. On this basis, four major problems faced by the current research are summarized: insufficient cross-regional generalization ability, difficulty in identifying category imbalance and fine-grained damage, high cost of large-scale model adaptation and inference calculation, and ununiform destruction grading standards. In response to the above problems, we further look forward to the development direction of basic model and pre-training strategy, multi-modal and multi-phase information integration, efficient model adaptation and deployment, standardized evaluation system, and deep connection between seismic assessment and emergency decision-making system. This article aims to provide a systematic research context and reference for the follow-up research of the earthquake damage assessment method of buildings and its practical emergency application.

Downloads

Download data is not yet available.

References

[1] Al Shafian, S., & Hu, D. (2024). Integrating machine learning and remote sensing in disaster management: A decadal review of post-disaster building damage assessment. Buildings, 14(8), 2344. https://doi.org/10.3390/buildings14082344.

[2] Nia, K. R., & Mori, G. (2017). Building damage assessment using deep learning and ground-level image data. In 2017 14th Conference on Computer and Robot Vision (CRV) (pp. 95–102). IEEE. https://doi.org/10.1109/CRV.2017.19

[3] Gupta, R., Hosfelt, R., Sajeev, S., & others. (2019). xbd: A dataset for assessing building damage from satellite imagery. arXiv preprint arXiv:1911.09296.

[4] Sun, Y., Wang, Y., & Eineder, M. (2024). Quickquakebuildings: Post-earthquake SAR-optical dataset for quick damaged-building detection. IEEE Geoscience and Remote Sensing Letters, 21, 1–5. https://doi.org/10.1109/LGRS.2024.3370827

[5] Chen, H., Song, J., Dietrich, O., & others. (2025). BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response. Earth System Science Data, 17(11), 6217–6253. https://doi.org/10.5194/essd-17-6217-2025

[6] Gao, G., Wang, F., Wang, Z., & others. (2024). Multi-scale earthquake damaged building feature set. Data, 9(7), 88. https://doi.org/10.3390/data9070088

[7] Lu, W., Wei, L., & Nguyen, M. (2024). Bitemporal attention transformer for building change detection and building damage assessment. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 4917–4935. https://doi.org/10.1109/JSTARS.2024.3380488

[8] Deng, L., & Wang, Y. (2022). Post-disaster building damage assessment based on improved U-Net. Scientific Reports, 12(1), 15862. https://doi.org/10.1038/s41598-022-19985-4

[9] Del Mese, S., Graziani, L., Meroni, F., & others. (2023). Considerations on using MCS and EMS-98 macroseismic scales for the intensity assessment of contemporary Italian earthquakes. Bulletin of Earthquake Engineering, 21(9), 4167–4189. https://doi.org/10.1007/s10518-023-01654-7

[10] Wang, L., Li, J., & Liu, Y. (2015). Comparative study on extraction methods of earthquake damage information of buildings from high-resolution remote sensing images. Journal of Heilongjiang Institute of Technology, 29(4), 11–13.

[11] Wang, C., & others. (2024). Scalable and rapid building damage detection after hurricane Ian using causal Bayesian networks and InSAR imagery. International Journal of Disaster Risk Reduction, 104, 371–387. https://doi.org/10.1016/j.ijdrr.2024.104371

[12] Macchiarulo, V., Giardina, G., Milillo, P., & others. (2025). Integrating post-event very high resolution SAR imagery and machine learning for building-level earthquake damage assessment. Bulletin of Earthquake Engineering, 23(12), 5021–5047. https://doi.org/10.1007/s10518-025-02112-1

[13] Bai, Y., Mas, E., & Koshimura, S. (2018). Towards operational satellite-based damage-mapping using u-net convolutional network: A case study of 2011 tohoku earthquake-tsunami. Remote Sensing, 10(10), 1626. https://doi.org/10.3390/rs10101626

[14] Chen, L. C., Zhu, Y., Papandreou, G., & others. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In European Conference on Computer Vision (pp. 833–851). Springer International Publishing. https://doi.org/10.1007/978-3-030-01234-2_49

[15] Chen, H., Song, J., Han, C., & others. (2024). ChangeMamba: Remote sensing change detection with spatiotemporal state space model. IEEE Transactions on Geoscience and Remote Sensing, 62, 1–20. https://doi.org/10.1109/TGRS.2024.3364758

[16] Gebre, T. S., Talreja, J., & Hashemi-Beni, L. (2026). Multi-Modal Attention for Automated Disaster Damage Assessment Using Remote Sensing Imagery and Deep Learning. arXiv preprint arXiv:2606.14963.

[17] Gomroki, M., Hasanlou, M., Chanussot, J., & others. (2024). EMYNet-BDD: EfficientViTB Meets Yolov8 in the encoder–decoder architecture for building damage detection using postevent remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 13120–13134. https://doi.org/10.1109/JSTARS.2024.3414684

[18] Gomroki, M., Hasanlou, M., Chanussot, J., & others. (2025). UNet-GCViT: a UNet-based framework with global context vision transformer blocks for building damage detection. International Journal of Remote Sensing, 46(6), 2587–2610. https://doi.org/10.1080/01431161.2025.2444761

[19] Benedict, R., Winartio, R. B., Adinata, M. F., & others. (2024). Comparison on difference deep learning models for building damage assessment using xbd dataset. In 2024 Arab ICT Conference (AICTC) (pp. 181–186). IEEE. https://doi.org/10.1109/AICTC62075.2024.10710337

[20] Zhao, Z., Wang, F., Chen, S., & others. (2024). Deep object segmentation and classification networks for building damage detection using the xBD dataset. International Journal of Digital Earth, 17(1), 2302577. https://doi.org/10.1080/17538947.2024.2302577

[21] Sirma, A., Plastropoulos, A., Tang, G., & others. (2025). DRespNeT: A UAV Dataset and YOLOv8-DRN Model for Aerial Instance Segmentation of Building Access Points for Post-Earthquake Search-and-Rescue Missions. arXiv preprint arXiv:2508.16016.

[22] Soleimani-Babakamali, M. H., Askari, M., Heravi, M. A., & others. (2025). Deep ensemble learning for rapid large-scale postearthquake damage assessment: Application to satellite images from the 2023 Türkiye earthquakes. ASCE OPEN: Multidisciplinary Journal of Civil Engineering, 3(1), 04025003. https://doi.org/10.1061/AO.MJCE.0000158

[23] Bhardwaj, D., Nagabhooshanam, N., Singh, A., & others. (2025). Enhanced satellite imagery analysis for post-disaster building damage assessment using integrated ResNet-U-Net model. Multimedia Tools and Applications, 84(5), 2689–2714. https://doi.org/10.1007/s11042-024-19221-1

[24] Chen, K., Liu, C., Chen, H., & others. (2024). RSPrompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model. IEEE Transactions on Geoscience and Remote Sensing, 62, 1–17. https://doi.org/10.1109/TGRS.2024.3370103

[25] Siva, S., & Cross-Zamirski, J. (2026). Building Damage Detection using Satellite Images and Patch-Based Transformer Methods. arXiv preprint arXiv:2602.08117.

[26] Bhatta, S., & Dang, J. (2024). Multiclass seismic damage detection of buildings using quantum convolutional neural network. Computer-Aided Civil and Infrastructure Engineering, 39(3), 406–423. https://doi.org/10.1111/mice.13061