An Experimental Study of Predictive Metal Surface Corrosion via U-Net Segmentation and Random Forest Regression

Corrosion of metal surfaces threatens the structural integrity and operational life of industrial assets, and there is a need to move from reactive inspection to proactive predictive maintenance. In this study, an intelligent monitoring framework is proposed for evaluating and predicting corrosion progression based on deep learning-based segmentation and ensemble-based regression. Pixel-level segmentation of corrosive features was performed using a U-Net convolutional neural network, which provided a quantitative basis for further analysis. The geographical data were then applied to Random Forest regression models to forecast future growth of the corrosion area and greyscale-based severity levels. According to the experimental results, the accuracy, precision and recall of the segmentation are 78.6%, 61.8% and 73.5%, respectively. The predicted models were found to be reliable with R2 values of 0.8477 for the growth in area and 0.9926 for increasing levels of severity. This study shows that computer vision along with predictive analytics provide a solid data-driven method for long-term asset management and threat prevention.

Metal surface, corrosion detection, U-Net segmentation, predictive analytics, Random Forest regression.

1. A. Das, S. Dorafshan, and N. Kaabouch, Autonomous Image-Based Corrosion Detection in Steel Structures Using Deep Learning, Sensors, 24(11), 3630, (2024). [Google Scholar] [Crossref]

2. Z. Duan, X. Huang, J. Hou, W. Chen, and L. Cai, Research on Intelligent Diagnosis of Corrosion in the Operation and Maintenance Stage of Steel Structure Engineering Based on U-Net Attention, Buildings, 14(12), 3972, (2024). [Google Scholar] [Crossref]

3. D. Guidotti, L. Pandolfo, and L. Pulina, A Systematic Literature Review of Supervised Machine Learning Techniques for Predictive Maintenance in Industry 4.0, IEEE Access. 13, pp. 102479-102504, (2025). [Google Scholar] [Crossref]

4. M. Gavryushina, A. Marshakov, and Y. Panchenko, Application of the random forest algorithm to predict the corrosion losses of carbon steel over the first year of exposure in various regions of the world, Corrosion Engineering, Science and Technology, 58(3), pp. 205–213, (2023). [Google Scholar] [Crossref]

5. K. K. Brar et al., Image segmentation review: Theoretical background and recent advances, Information Fusion, 114, 102608, (2025). [Google Scholar] [Crossref]

6. M. K. Effendi, B. Atmaja, A. Wahjudi, and D. B. Purwanto, Automated Corrosion Detection on Steel Structures Using Convolutional Neural Network, The International Journal of Mechanical Engineering and Science, Vol 7, No 1 (2023), 36-44, (2023). [Google Scholar] [Crossref]

7. S. Wu, M. Zhu, Z. Zhang, Y. Yao, Y. Li, and D. Li, Prediction and risk assessment of stress corrosion failures of prestressed anchors in underground mines, International Journal of Mining, Reclamation and Environment, April, 1–15, (2025). [Google Scholar] [Crossref]

8. M. Majors et al., Automated corrosion mapping AI & machine learning, Society of Petroleum Engineers - Abu Dhabi International Petroleum Exhibition and Conference 2020, ADIP 2020, (2020). [Google Scholar] [Crossref]

9. C. Carpenter, Artificial-Intelligence and Machine-Learning Technique for Corrosion Mapping, J. Pet. Technology, 74 (2022): 99–102, (2022). [Google Scholar] [Crossref]

10. F. Ren, L. B. Xu, J. Fei, J. P. Q. Tomas, H. S. Li, and B. T. Doma, Design of multi-mode intelligent system architecture for surface defect detection of steel based on cloud technology, Scientific Reports, 15, 39735, (2025). [Google Scholar] [Crossref]

11. R. Yang, Z. Chen, Z. Qin, Y. Lu, and L. Qi, Steel Surface Defect Segmentation Using U-Net with SLMA-Gray Attention and AdamW Optimization, Informatica, , 49 (31). (2025). [Google Scholar] [Crossref]

12. K. Luo, X. Kong, J. Zhang, J. Hu, J. Li, and H. Tang, Computer Vision-Based Bridge Inspection and Monitoring: A Review, Sensors, 23 (18), 7863, (2023). [Google Scholar] [Crossref]

13. Y. Lai et al., Framework for long-term structural health monitoring by computer vision and vibration-based model updating, Case Studies in Construction Materials, Volume 16, e01020, (2022). [Google Scholar] [Crossref]

14. Z. Zheng, F. Wang, G. Gong, H. Yang, and D. Han, Intelligent technologies for construction machinery using data-driven methods, Automation in Construction, Volume 147, 104711, (2023). [Google Scholar] [Crossref]

15. A. Elbeltagi et al., Prediction of meteorological drought and standardized precipitation index based on the random forest (RF), random tree (RT), and Gaussian process regression (GPR) models, Environmental Science and Pollution Research, 30, 43183–43202, (2023). [Google Scholar] [Crossref]

16. S. Tiwari, K. Dash, N. Park, and N. G. S. Reddy, Machine Learning-Based Prediction of Atmospheric Corrosion Rates Using Environmental and Material Parameters, Coatings, 15 (8), 888, (2025). [Google Scholar] [Crossref]

17. Y. Li and L. Liu, Physics-Informed Neural Network-Based Nonlinear Model Predictive Control for Automated Guided Vehicle Trajectory Tracking, World Electric Vehicle Journal, 15 (10), 460, (2024). [Google Scholar] [Crossref]

18. M. M. H. Imran et al., Application of Artificial Intelligence in Marine Corrosion Prediction and Detection, Journal of Marine Science and Engineering. 11 (2), 256, (2023). [Google Scholar] [Crossref]

19. T. Bitam, A. Yahiaoui, D. E. Boubiche, R. Martínez-Peláez, H. Toral-Cruz, and P. Velarde-Alvarado, Artificial Intelligence of Things for Next-Generation Predictive Maintenance, Sensors, 25 (24), 7636, (2025). [Google Scholar] [Crossref]

20. C. Dong, S. Bas, and F. N. Catbas, Applications of Computer Vision-Based Structural Monitoring on Long-Span Bridges in Turkey, Sensors, 23 (19), 8161 (2023). [Google Scholar] [Crossref]

21. C. I. Ossai, A data-driven machine learning approach for corrosion risk assessment—a comparative study, Big Data Cognitive Computing, 3 (2), 28, (2019). [Google Scholar] [Crossref]

22. A. Srivastava, G. Ji, and R. K. Singh, Application of Deep-Learning Architecture for Image Analysis based Corrosion Detection, 2021 Smart Technologies, Communication and Robotics (STCR), pp. 1-5, (2021). [Google Scholar] [Crossref]

23. F. R. Elmas, M. P. Rios, E. R. de Almeida Lima, R. G. Gusmão Caiado, and R. S. Santos, Prediction of external corrosion rate in Oil and Gas platforms using ensemble learning: a Maintenance 4.0 approach, Brazilian Journal of Operations & Production Management, 20(3), 1952, (2023). [Google Scholar] [Crossref]

24. A. K. I. A.-G. Nahla Ibraheem Jabbar1, Shaker Salih Bahar, Detectıon Corrosıon By Usıng Convolutıonal Neural Networks Technıque, Academıc Journal Of Manufacturıng Engıneerıng, vol. 23, no. 2, pp. 2–7, (2025). [Google Scholar] [Crossref]

25. Z. May, M. K. Alam, N. A. Nayan, N. A. A. Rahman, and M. S. Mahmud, Acoustic emission corrosion feature extraction and severity prediction using hybrid wavelet packet transform and linear support vector classifier, PLoS One, 16 (12): e0261040, (2021). [Google Scholar] [Crossref]

26. M. F. Sheikh, K. Kamal, F. Rafique, S. Sabir, H. Zaheer, and K. Khan, Corrosion detection and severity level prediction using acoustic emission and machine learning based approach, Ain Shams Engineering Journal, volume 12, Issue 4, December 2021, Pages 3891-3903, (2021). [Google Scholar] [Crossref]

• The Impact Of UI/UX Design on User Trust and Task Completion in Civic Tech Platforms
• Solar Cell Photovoltaic Model Shell Sp 75
• Development of an Intelligent Traffic Management System to Address Visibility Obstruction at Urban Intersections: A Case Study of Ibadan Metropolis
• Optimum Placement of Facts Devices on an Interconnected Power Systems Using Particle Swarm Optimisation Technique
• Assessing Construction Transformation and Implication on Future Production Flow System