Automated Post-Earthquake Damage Assessment in Reinforced Concrete Structures Using U-Net-Based Convolutional Neural Networks

Authors

https://doi.org/10.48314/ijrceai.v3i2.58

Abstract

Rapid and accurate assessment of damage to structures following an earthquake is critical for disaster management, emergency response, and rehabilitation planning. Traditional visual inspection methods are time-consuming, costly, and inherently subjective. This research presents an automated approach based on deep learning for identifying and quantifying cracks in Reinforced Concrete (RC) structures after seismic events. The proposed model utilizes a U-Net architecture, a type of Convolutional Neural Network (CNN), for pixel-level crack segmentation. It is trained and evaluated on a dataset of real-world images from the recent Kahramanmaraş earthquake (Türkiye, 2023). Results demonstrate that the model effectively identifies various crack patterns with high accuracy, achieving a strong Intersection over Union (IoU) score of 0.745. This approach offers an efficient, objective, and scalable tool for structural engineers to assess integrity and prioritize repairs. The integration of an Efficient Channel Attention (ECA) mechanism further enhances feature extraction, leading to improved segmentation performance, particularly for subtle and narrow cracks.    

Keywords:

Deep learning, Convolutional neural networks, U-net, Crack detection, Post-earthquake damage assessment, Reinforced concrete structures, Structural health monitoring, Image segmentation

References

  1. [1] Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention - miccai 2015 (pp. 234–241). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-319-24574-4_28%0A%0A
  2. [2] Hacıefendioğlu, K., & Demir, S. (2026). Deep learning–based automated crack detection for post-earthquake damage assessment in reinforced concrete structures. Advances in civil engineering, 2026(1), 6845779. https://doi.org/10.1155/adce/6845779
  3. [3] Turer, A., Bai, Y., Sezen, H., & Yilmaz, A. (2025). Deep learning-based automated damage detection in concrete structures using images from earthquake events. https://doi.org/10.48550/arXiv.2510.21063
  4. [4] Wu, Y., Li, S., Li, J., Yu, Y., Li, J., & Li, Y. (2025). Deep learning in crack detection: A comprehensive scientometric review. Journal of infrastructure intelligence and resilience, 4(3), 100144. https://doi.org/10.1016/j.iintel.2025.100144
  5. [5] Song, Y., Zhang, Q., Su, Y., Zhang, S., Wang, R., Zhang, W., … ., & Yu, Y. (2025). Advances in crack dataset development and deep learning-based detection models. Journal of building engineering, 116, 114734. https://doi.org/10.1016/j.jobe.2025.114734
  6. [6] Li, S., Yan, F., Li, Z., Hu, Q., Xu, S., & Liu, S. (2025). TCI-Net: Structural feature enhancement and multi-level constrained network for reliable thin crack identification on concrete surfaces. IEEE access, 13, 65604–65616. https://doi.org/10.1109/ACCESS.2025.3558409
  7. [7] Feng, M., & Xu, J. (2025). Lightweight dual-attention network for concrete crack segmentation. Sensors, 25(14), 1–15. https://doi.org/10.3390/s25144436
  8. [8] Fan, C., Ding, Y., Liu, X., & Yang, K. (2025). A review of crack research in concrete structures based on data-driven and intelligent algorithms. Structures, 75, 108800. https://doi.org/10.1016/j.istruc.2025.108800
  9. [9] Wang, J., & Ueda, T. (2025). Automatic damage detection and segmentation using deep learning algorithms in reinforced concrete structure inspections. Structural concrete, 26(5), 5511–5534. https://doi.org/10.1002/suco.202400722
  10. [10] Ataei, S., Adibnazari, S., & Ataei, S. T. (2025). Data-driven detection and evaluation of damages in concrete structures: Using deep learning and computer vision. https://doi.org/10.48550/arXiv.2501.11836
  11. [11] Huang, B., Kang, F., & Liu, X. (2026). Intelligent UAV-based deep learning system for multi-class concrete dam damage detection. Automation in construction, 182, 106730. https://doi.org/10.1016/j.autcon.2025.106730
  12. [12] Huang, C., Li, H., & Yu, Z. (2025). Intelligent concrete defect identification using an attention-enhanced VGG16-U-Net. Structural durability & health monitoring, 19(5), 1287–1304. https://doi.org/10.32604/sdhm.2025.065930
  13. [13] Li, J. (2025). Research on crack image segmentation method based on unet and cbam. 2025 5th international conference on artificial intelligence, big data and algorithms (CAIBDA) (pp. 258–261). IEEE. https://doi.org/10.1109/CAIBDA65784.2025.11182640
  14. [14] Salehi, H., Jamshidighadikolaei, N., Gopu, V., & Alaywan, W. (2026). Lab-to-field integration in bridge monitoring: A hybrid structural health monitoring framework employing deep learning and unmanned aerial vehicle imagery. Machine learning with applications, 24, 100872. https://doi.org/10.1016/j.mlwa.2026.100872
  15. [15] Zhang, L., Deng, K., Akiyama, M., Frangopol, D. M., & Xin, J. (2026). Multimodal YOLO-based identification and 3D characterization of concrete surface defects via integrated LiDAR and photogrammetry. Automation in construction, 188, 107035. https://doi.org/10.1016/j.autcon.2026.107035
  16. [16] Matich, H., & Mousannif, H. (2026). Implementation of an ıntelligent vision approach for automated structural defect detection. Discover artificial intelligence, 6(1), 225. https://doi.org/10.1007/s44163-026-00961-6

Downloads

Published

2026-06-20

Issue

Vol. 3 No. 2 (2026): International Journal of Researches on Civil Engineering with Artificial Intelligence (IJRCEAI)

Section

Articles

How to Cite

Mirabedini, S., & Nourani, S. F. (2026). Automated Post-Earthquake Damage Assessment in Reinforced Concrete Structures Using U-Net-Based Convolutional Neural Networks. International Journal of Researches on Civil Engineering With Artificial Intelligence , 3(2), 144-154. https://doi.org/10.48314/ijrceai.v3i2.58

Similar Articles

21-30 of 33

You may also start an advanced similarity search for this article.