Development of an Artificial Intelligence-Based Marine Pipeline Corrosion Prediction and Detection Model for Offshore Platforms

Corrosion in subsea and marine pipelines remains one of the most persistent threats to the structural integrity, environmental safety, and operational continuity of offshore oil and gas installations. Conventional monitoring practices, which rely on manual inspection, electrochemical testing, and periodic non-destructive evaluation, are reactive, labour-intensive, and poorly suited to the scale and hazard profile of modern offshore assets. This study develops and evaluates an artificial intelligence (AI)-based framework for the prediction, classification, and image-based detection of marine pipeline corrosion. Two complementary AI pathways were investigated. First, four supervised machine learning (ML) classifiers - Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) - were trained on a simulated offshore sensor dataset comprising 2,500 samples described by wall thickness, temperature, pressure, humidity, pH, and vibration, and labelled into normal, minor, and severe corrosion classes. The Synthetic Minority Over-sampling Technique (SMOTE) was applied to correct class imbalance, and best-first attribute selection reduced the feature space to the three most informative predictors (wall thickness, humidity, and pH). Second, a hybrid convolutional neural network (CNN) coupled with the YOLOv8 detection architecture was trained on inspection imagery to localise and classify corroded pipeline surfaces. The RF and DT classifiers achieved the strongest performance, with a weighted-average accuracy, precision, recall, and F1-score of 99.8%, while the MLP and SVM attained 94.8% and 80.8% respectively. The CNN-YOLOv8 detector converged rapidly, reaching a test accuracy of 100% within three training epochs, with a final model loss of 0.060 and model accuracy of 97.4%. These results demonstrate that hybridising interpretable ensemble classifiers with deep image-based detection offers a promising, proof-of-concept route to proactive corrosion management on offshore platforms, reducing reliance on manual inspection while improving the timeliness and reliability of maintenance decisions. Because the sensor data are simulated and rule-labelled and the image set is small, the reported accuracies indicate separability within these datasets rather than field performance; robustness to sensor noise and explainability of predictions remain to be evaluated before safety-critical deployment.

marine pipeline corrosion; artificial intelligence; machine learning; convolutional neural network

1. Ahuir-Torres, J. I., Bausch, N., Farrar, A., Webb, S., Simandjuntak, S., Nash, A., Thomas, B., Muna, J., Jonsson, C., & Mathew, D. (2019). Benchmarking parameters for remote electrochemical corrosion detection and monitoring of offshore wind turbine structures. Wind Energy, 22(6), 857-876. [Google Scholar] [Crossref]

2. Ali, A. A. I., Mohd, S. J., Imran, M. H. H., Ayob, A. F. M., Ahmad, S. Z. A. S., Akhbar, M. F. A., Suhrab, M. I. R., & Ramli, M. R. (2023). Computer vision and image processing approaches for corrosion detection. Journal of Marine Science and Engineering, 11(10), 1954. [Google Scholar] [Crossref]

3. Amaechi, C. V., Wang, F., Ja'e, I. A., Aboshio, A., Odijie, A. C., & Ye, J. (2022). A literature review on the technologies of bonded hoses for marine applications. Ships and Offshore Structures, 17(12), 2819-2850. [Google Scholar] [Crossref]

4. Amiri, N., Shaterabadi, M., Reza Kashyzadeh, K., & Chizari, M. (2021). A comprehensive review of design, monitoring, and failure in fixed offshore platforms. Journal of Marine Science and Engineering, 9(12), 1349. [Google Scholar] [Crossref]

5. Baba, S. Y., & Avadhani, P. S. (2020). Data acquisition by using WSN and to develop CAD models in subsea, marine, oil and gas exploration fields. i-Manager's Journal on Future Engineering and Technology, 15(3), 11. [Google Scholar] [Crossref]

6. Bai, Y., & Bai, Q. (2012). Subsea engineering handbook. Gulf Professional Publishing. [Google Scholar] [Crossref]

7. Dang, T., Nguyen, T. T., Liew, A. W. C., & Elyan, E. (2025). Event classification on subsea pipeline inspection data using an ensemble of deep learning classifiers. Cognitive Computation, 17(1), 1-23. [Google Scholar] [Crossref]

8. Das, A., Dorafshan, S., & Kaabouch, N. (2024). Autonomous image-based corrosion detection in steel structures using deep learning. Sensors, 24(11), 3630. [Google Scholar] [Crossref]

9. Diao, Y., Yan, L., & Gao, K. (2021). Improvement of the machine learning-based corrosion rate prediction model through the optimization of input features. Materials & Design, 198, 109326. [Google Scholar] [Crossref]

10. DNV GL. (2015). Recommended Practice DNV-RP-F116: Integrity management of submarine pipeline systems. DNV GL. [Google Scholar] [Crossref]

11. Fayomi, O. S. I., Akande, I. G., & Odigie, S. (2019, December). Economic impact of corrosion in oil sectors and prevention: An overview. Journal of Physics: Conference Series, 1378(2), 022037. [Google Scholar] [Crossref]

12. Imran, M. M. H., Jamaludin, S., Ayob, A. F. M., Ali, A. A. I. M., Ahmad, S. Z. A. S., Akhbar, M. F. A., Suhrab, M. I. R., Zainal, N., Norzeli, S. M., & Mohamed, S. B. (2023). Application of artificial intelligence in marine corrosion prediction and detection. Journal of Marine Science and Engineering, 11(2), 256. [Google Scholar] [Crossref]

13. Khalid, F. (2019). Reliability assessment approach through geospatial mapping for offshore wind energy [Doctoral dissertation, University of Exeter]. [Google Scholar] [Crossref]

14. Kim, D. K., Lim, H. L., & Cho, N. K. (2020). An advanced technique to predict time-dependent corrosion damage of onshore, offshore, nearshore and ship structures: Part II - Application to the ship's ballast tank. International Journal of Naval Architecture and Ocean Engineering, 12(1), 645-656. [Google Scholar] [Crossref]

15. Komary, M., Komarizadehasl, S., Tošić, N., Segura, I., Lozano-Galant, J. A., & Turmo, J. (2023). Low-cost technologies used in corrosion monitoring. Sensors, 23(3), 1309. [Google Scholar] [Crossref]

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

17. Melchers, R. E., & Jeffrey, R. (2008). Marine corrosion of steel piles: Progress and challenges. Corrosion Science, 50(11), 2959-2973. [Google Scholar] [Crossref]

18. Ojie, E.E., Inegiyemiema, M., & Nitonye, S., (2026). Offshore Pipeline Stress and Stability Analysis in the Gulf of Guinea. International Journal of Research and Innovation in Applied Science. DOI: https://doi.org/10.51584/IJRIAS.2026.11080065 [Google Scholar] [Crossref]

19. Ojie, E.E., Nwoka, B.G., & Ekine, A.A. (2026). Adaptive thruster allocation and integrated performance evaluation for dynamic positioning of semisubmersible drilling units. Global Journal of Engineering and Technology Advances, 28(3), 298–311. https://doi.org/10.30574/gjeta.2026.28.3.0264 [Google Scholar] [Crossref]

20. Palmer, A. C., & King, R. A. (2008). Subsea pipeline engineering (2nd ed.). PennWell Books. [Google Scholar] [Crossref]

21. Ruiz, D., Casas, A., Escobar, C. A., Perez, A., & Gonzalez, V. (2024). Advanced machine learning techniques for corrosion rate estimation and prediction in industrial cooling water pipelines. Sensors, 24(11), 3564. [Google Scholar] [Crossref]

22. Salgueiro, F., Ribeiro, M., Carvalho, A., Covas, G., Baltzersen, Ø., & Proença, C. S. (2024). Monitoring of wall thickness to predict corrosion in marine environments using ultrasonic transducers. NDT, 2(3), 255-269. [Google Scholar] [Crossref]

23. Saminathan, R., Nashali, A. Y. A., Haqawi, A. A. A., Marappan, S., Natesan, S. P., & Shakeel, F. (2024). Role of artificial intelligence (AI) and machine learning (ML) in the corrosion monitoring processes. Zastita Materijala, 65(3), 473-480. [Google Scholar] [Crossref]

24. Seghier, M. E. A. B., Höche, D., & Zheludkevich, M. (2022). Prediction of the internal corrosion rate for oil and gas pipeline: Implementation of ensemble learning techniques. Journal of Natural Gas Science and Engineering, 99, 104425. [Google Scholar] [Crossref]

25. Shojaei, A. R., Ramezanzadeh, B., & Mohammadloo, H. E. (2025). Corrosion in the marine and offshore industry. In Industrial corrosion: Fundamentals, failure, analysis and prevention (pp. 65-104). [Google Scholar] [Crossref]

26. Singh, B., & Poblete, B. (2025). Offshore pipeline risk, corrosion, and integrity management with lessons learned. In Oil and gas pipelines: Integrity, safety, and security handbook (Vol. 2, pp. 1224-1256). [Google Scholar] [Crossref]

27. Spahić, R., Poolla, K., Hepsø, V., & Lundteigen, M. A. (2023). Image-based and risk-informed detection of subsea pipeline damage. Discover Artificial Intelligence, 3(1), 23. [Google Scholar] [Crossref]

28. Tansel, B., & Zhang, K. (2022). Effects of saltwater intrusion and sea level rise on aging and corrosion rates of iron pipes in water distribution and wastewater collection systems in coastal areas. Journal of Environmental Management, 315, 115153. [Google Scholar] [Crossref]

29. Xia, R., Jia, C., & Garbatov, Y. (2025). Deterioration of marine offshore structures and subsea installations subjected to severely corrosive environment: A review. Materials and Corrosion, 76(6), 758-775. [Google Scholar] [Crossref]

30. Yang, J., Zou, D., Zhang, M., Que, Z., Liu, T., Zhou, A., & Li, Y. (2024). Marine steel corrosion prediction and zonation using feature extraction and machine learning in the seas around China. Ocean Engineering, 314, 119649. [Google Scholar] [Crossref]

31. Zardasti, L., Hanafiah, N. M., Noor, N. M., Yahaya, N., & Rashid, A. S. A. (2015). The consequence assessment of gas pipeline failure due to corrosion. Solid State Phenomena, 227, 225-228. [Google Scholar] [Crossref]

32. Zhang, H., & Hong, X. (2019). Recent progresses on object detection: A brief review. Multimedia Tools and Applications, 78(19), 27809-27847. [Google Scholar] [Crossref]

33. Zhou, X. G., & Hou, C. (2025). Automated corrosion diagnosis of marine concrete-filled steel tubular structures using deep learning-based machine vision. Automation in Construction, 178, 106403. [Google Scholar] [Crossref]

34. Zhou, X., Hou, C., Yu, Y., & Zhou, Y. (2025, March). Machine learning-based techniques for marine structures: A state-of-the-art review. Ocean, 1(1), 9470005. [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition