Automated Assessment of Marine Steel Corrosion Using Visible–Near-Infrared Hyperspectral Imaging
Source abstract
Abstract
Marine steel structures face severe corrosion risks due to harsh environmental conditions, posing significant logistical, economic, and safety challenges for inspection and maintenance. Traditional corrosion assessment methods are costly, labor-intensive, and potentially hazardous. This study evaluated the capabilities of visible-to-near-infrared hyperspectral imaging (HSI) for automating corrosion detection and severity classification in steel samples subjected to accelerated corrosion conditions simulating marine exposure. Marine steel coupons were partially coated to simulate protective paint and immersed in natural brackish water from the Panama Canal, creating varying corrosion levels. Hyperspectral images were acquired in controlled illumination conditions, calibrated radiometrically, and reduced in dimensionality via principal component analysis (PCA). Four machine learning models, including k-nearest neighbors, support vector machine, random forest, and multilayer perceptron, were tested for classifying corrosion severity. The multilayer perceptron achieved the highest accuracy at 96.18%, clearly distinguishing among five defined corrosion stages. These findings demonstrate that hyperspectral imaging, coupled with machine learning techniques, provides a viable, accurate, non-destructive methodology for assessing marine steel corrosion, potentially reducing costs, improving safety, and streamlining maintenance procedures.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Structural Integrity and Reliability Analysis · Thermography and Photoacoustic Techniques · Advanced Measurement and Detection Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Grupo de Investigación en Tecnologías Avanzadas de Telecomunicación y Procesamiento de Señales (GITTS), Facultad de Ingeniería Eléctrica, Universidad Tecnológica de Panamá, Panama City 0819-07289, Panama
Centro de Estudios Multidisciplinarios en Ciencias, Ingeniería y Tecnología AIP (CEMCIT-AIP), Universidad Tecnológica de Panamá, Panama City 0819-07289, Panama
Funding
Secretaría Nacional de Ciencia, Tecnología e Innovación (SENACYT)
References (100+)
Show source-provided references
1. Reliability of maintained, corrosion protected plates subjected to non-linear corrosion and compressive loads10.1016/S0951-8339(99)00028-3 ↗
2. Refait, P., Grolleau, A.M., Jeannin, M., Rémazeilles, C., and Sabot, R. (2020). Corrosion of carbon steel in marine environments: Role of the corrosion product layer. Corros. Mater. Degrad., 1.10.3390/cmd1010010 ↗
3. Alcántara, J., de la Fuente, D., Chico, B., Simancas, J., Díaz, I., and Morcillo, M. (2017). Marine atmospheric corrosion of carbon steel: A review. Materials, 10.10.3390/ma10040406 ↗
4. The role of rusts in corrosion and corrosion protection of iron and steel10.1016/j.corsci.2008.03.008 ↗
5. Risk-based life-cycle optimal dry-docking inspection of corroding ship hull tankers10.1016/j.engstruct.2019.05.063 ↗
6. The modelling of maintenance cost: The case of container-ships in dry-dock
7. Michalopoulos, K. (2024). Dry-Docking Costs Analysis. [Master’s Thesis, Πανεπιστήμιo Πειραιώς].
8. Callís Oliver, L.M. (2018). SOLAS Convention: Safety on Board. [Bachelor’s Thesis, Universitat Politècnica de Catalunya].
9. Johansson, T. (2022). International standards for hull inspection and maintenance of robotics and autonomous systems. Emerging Technology and the Law of the Sea, Cambridge University Press.10.1017/9781009042178.008 ↗
10. Application of steel thin film electrical resistance sensor for in situ corrosion monitoring10.1016/j.snb.2006.02.029 ↗
11. Mansfeld, F. (1976). The polarization resistance technique for measuring corrosion currents. Advances in Corrosion Science and Technology, Springer.10.1007/978-1-4684-8986-6_3 ↗
12. Hernández, H.H., Reynoso, A.M.R., González, J.C.T., Morán, C.O.G., Hernández, J.G.M., Ruiz, A.M., Hernández, J.M., and Cruz, R.O. (2020). Electrochemical impedance spectroscopy (EIS): A review study of basic aspects of the corrosion mechanism applied to steels. Electrochemical Impedance Spectroscopy, IntechOpen.10.5772/intechopen.94470 ↗
13. Sodsai, K., Noipitak, M., and Sae-Tang, W. (2019, January 7–9). Detection of corrosion under coated surface by Eddy current testing method. Proceedings of the 2019 7th International Electrical Engineering Congress (iEECON), Phetchaburi, Thailand.10.1109/iEECON45304.2019.8938940 ↗
14. Ramanaidou, E., Wells, M., Lau, I., and Laukamp, C. (2015). Characterization of iron ore by visible and infrared reflectance and, Raman spectroscopies. Iron Ore, Elsevier.10.1016/B978-1-78242-156-6.00006-X ↗
15. The long term growth of the protective rust layer formed on weathering steel by atmospheric corrosion during a quarter of a century10.1016/0010-938X(94)90158-9 ↗
16. Characterization of corrosion products on carbon steel exposed to natural weathering and to accelerated corrosion tests10.1155/2014/419570 ↗
17. De Kerf, T., Pipintakos, G., Zahiri, Z., Vanlanduit, S., and Scheunders, P. (2022). Identification of Corrosion Minerals Using Shortwave Infrared Hyperspectral Imaging. Sensors, 22.10.3390/s22010407 ↗
18. Characterization of Delhi iron pillar rust by X-ray diffraction, Fourier transform infrared spectroscopy and Mössbauer spectroscopy10.1016/S0010-938X(00)00045-7 ↗
19. Spectroscopic study of decontaminated corroded carbon steel surfaces
20. FTIR spectroscopic semi-quantification of iron phases: A new method to evaluate the protection ability index (PAI) of archaeological artefacts corrosion systems10.1016/j.corsci.2018.01.016 ↗
21. Formation and characterization of δ-FeOOH10.1016/0167-577X(94)90192-9 ↗
22. Quantitative analysis of iron oxides using Fourier transform infrared spectrophotometry10.1016/j.corsci.2008.06.034 ↗
23. Corrosion product analysis of corrosion resistant ancient indian iron10.1016/S0010-938X(98)00024-9 ↗
24. X-ray diffraction and Fourier transform-infrared analysis of the rust formed by corrosion of steel in aqueous solutions10.1007/BF00365176 ↗
25. Atomic-scale structure and morphology of ferric oxyhydroxides formed by corrosion of iron in various aqueous media10.1016/j.corsci.2006.01.001 ↗
26. XRD and SEM studies of the layer of corrosion products for carbon steel in various different environments in the province of Las Palmas (The Canary Islands, Spain)10.1016/S0010-938X(02)00047-1 ↗
27. Long-term atmospheric corrosion of mild steel10.1016/j.corsci.2010.10.007 ↗
28. The influence of inhibitors molecular structure and steel microstructure on corrosion layers in CO2 corrosion: An XPS and SEM characterization10.1016/j.apsusc.2004.03.247 ↗
29. Corrosion behaviour of laser-cleaned AA7024 aluminium alloy10.1016/j.apsusc.2017.11.141 ↗
30. The use of infrared thermography in the corrosion science area10.1002/maco.200905525 ↗
31. Hyperspectral imaging based corrosion detection in nuclear packages10.1109/JSEN.2023.3312938 ↗
32. Artificial intelligence-based hull structural plate corrosion damage detection and recognition using convolutional neural network10.1016/j.apor.2019.05.008 ↗
33. Recognition of rust grade and rust ratio of steel structures based on ensembled convolutional neural network10.1111/mice.12563 ↗
34. Wang, K., Li, C., Lu, J., Nan, C., Zhang, Q., and Zhang, H. (2022). Intelligent Evaluation of Marine Corrosion of Q420 Steel Based on Image Recognition Method. Coatings, 12.10.3390/coatings12070881 ↗
35. Scheibenreif, L., Mommert, M., and Borth, D. (2023, January 18–22). Masked vision transformers for hyperspectral image classification. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPRW59228.2023.00210 ↗
36. Light self-Gaussian-attention vision transformer for hyperspectral image classification
37. Vision transformer with contrastive learning for hyperspectral image classification
38. Detection and classification of surface defects on hot-rolled steel using vision transformers10.1016/j.heliyon.2024.e38498 ↗
39. Enjikalayil Abdulkader, R., Veerajagadheswar, P., Htet Lin, N., Kumaran, S., Vishaal, S.R., and Mohan, R.E. (2020). Sparrow: A magnetic climbing robot for autonomous thickness measurement in ship hull maintenance. J. Mar. Sci. Eng., 8.10.3390/jmse8060469 ↗
40. Towards optimal hydro-blasting in reconfigurable climbing system for corroded ship hull cleaning and maintenance10.1016/j.eswa.2020.114519 ↗
41. Yang, K., Shi, C., Guo, Y., Zhang, X., Li, C., and Wu, G. (2021, January 11–15). Non-contact Identification Method for Carbon Steel Corrosion Grade of Transmission Tower Based on Hyperspectral Technology. Proceedings of the 2021 International Conference on Electrical Materials and Power Equipment (ICEMPE), Chongqing, China.10.1109/ICEMPE51623.2021.9509165 ↗
42. Hyperspectral imaging for the elimination of visual ambiguity in corrosion detection and identification of corrosion sources10.1177/14759217211041690 ↗
43. Advances in cost-effective integrated spectrometers10.1038/s41377-022-00853-1 ↗
44. Spectral imaging with deep learning10.1038/s41377-022-00743-6 ↗
45. ElMasry, G., and Sun, D.W. (2010). Principles of hyperspectral imaging technology. Hyperspectral Imaging for Food Quality Analysis and Control, Elsevier.10.1016/B978-0-12-374753-2.10001-2 ↗
46. Automated labeling of materials in hyperspectral imagery
47. Material based object tracking in hyperspectral videos10.1109/TIP.2020.2965302 ↗
48. Hyperspectral imaging for rice cultivation: Applications, methods and challenges
49. Arias, F., Zambrano, M., Galagarza, E., and Broce, K. (2025). Mapping Harmful Algae Blooms: The Potential of Hyperspectral Imaging Technologies. Remote Sens., 17.10.3390/rs17040608 ↗
50. Applications of hyperspectral imaging technology in the food industry10.1038/s44287-024-00033-w ↗
51. Non-destructive hyperspectral imaging technology to assess the quality and safety of food: A review10.1186/s43014-024-00246-4 ↗
52. Wang, S., Cen, Y., Qu, L., Li, G., Chen, Y., and Zhang, L. (2024). Virtual Restoration of Ancient Mold-Damaged Painting Based on 3D Convolutional Neural Network for Hyperspectral Image. Remote Sens., 16.10.3390/rs16162882 ↗
53. The man who became a Blue Glass. Reflectance hyperspectral imaging discloses a hidden Picasso painting of the Blue period10.1016/j.culher.2023.07.003 ↗
54. Quantitative detection of corrosion minerals in carbon steel using shortwave infrared hyperspectral imaging10.1039/D2RA05267A ↗
55. Li, X., Li, R., Wang, M., Liu, Y., Zhang, B., and Zhou, J. (2017). Hyperspectral imaging and their applications in the nondestructive quality assessment of fruits and vegetables. Hyperspectral Imaging in Agriculture, Food and Environment, IntechOpen.10.5772/intechopen.72250 ↗
56. Chen, G. (2025, April 27). Hyperspectral Imaging and Data Analytics for Civil Infrastructure Inspection. Available online: https://scholarsmine.mst.edu/cgi/viewcontent.cgi?article=1017&context=inspire_webinars.
57. Supervised classification in high-dimensional space: Geometrical, statistical, and asymptotical properties of multivariate data10.1109/5326.661089 ↗
58. Improving execution time for supervised sparse representation classification of hyperspectral images using the Moore–Penrose pseudoinverse10.1117/1.JRS.13.026512 ↗
59. High-dimensional data analysis: The curses and blessings of dimensionality
60. Stuart, M.B., Davies, M., Hobbs, M.J., Pering, T.D., McGonigle, A.J., and Willmott, J.R. (2022). High-resolution hyperspectral imaging using low-cost components: Application within environmental monitoring scenarios. Sensors, 22.10.3390/s22124652 ↗
61. Altamimi, A., and Ben Youssef, B. (2021). A systematic review of hardware-accelerated compression of remotely sensed hyperspectral images. Sensors, 22.10.3390/s22010263 ↗
62. Shaikh, M.S., Jaferzadeh, K., Thörnberg, B., and Casselgren, J. (2021). Calibration of a hyper-spectral imaging system using a low-cost reference. Sensors, 21.10.3390/s21113738 ↗
63. Methods, procedures, and example results for evaluating commercial off-the-shelf hyperspectral instruments for use as satellite cross-calibration radiometers10.1117/1.JRS.19.027501 ↗
64. Podlesnykh, I., Kovalev, M., and Platonov, P. (2024). Towards the future of ubiquitous hyperspectral imaging: Innovations in sensor configurations and cost reduction for widespread applicability. Technologies, 12.10.3390/technologies12110221 ↗
65. Mineral quantification at deposit scale using drill-core hyperspectral data: A case study in the Iberian Pyrite Belt10.1016/j.oregeorev.2021.104514 ↗
66. Nersesian, R., and Mahmood, S. (2010). International association of classification societies. Handbook of Transnational Economic Governance Regimes, Brill Nijhoff.10.1163/ej.9789004163300.i-1081.675 ↗
67. Spatiotemporal distribution of salinity in Gatun Lake and the Panama Canal pre-and post-expansion10.1016/j.ejrh.2025.102199 ↗
68. Mitigating illumination-, leaf-, and view-angle dependencies in hyperspectral imaging using polarimetry10.34133/plantphenomics.0157 ↗
69. Spectral irradiance model for tungsten halogen lamps in 340–850 nm wavelength range10.1364/AO.49.000880 ↗
70. Principal component analysis for hyperspectral image classification
71. PCA-based feature reduction for hyperspectral remote sensing image classification10.1080/02564602.2020.1740615 ↗
72. Fleck, T., Zipfl, M., and Zöllner, J.M. (, January 24–28). Semi-Automatic Ground Truth Trajectory Estimation and Smoothing using Roadside Cameras. Proceedings of the 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Bilbao, Spain.10.1109/ITSC57777.2023.10422115 ↗
73. Casasent, D.P., and Chen, X. (2000, January 6–8). Hyperspectral data discrimination methods. Proceedings of the Biological Quality and Precision Agriculture II. SPIE, Boston, MA, USA.
74. Graepel, T., Herbrich, R., Bollmann-Sdorra, P., and Obermayer, K. (1998). Classification on pairwise proximity data. Adv. Neural Inf. Process. Syst., 11.
75. Analysis of knn density estimation10.1109/TIT.2022.3195870 ↗
76. Support vector machines for hyperspectral image classification with spectral-based kernels10.1109/IGARSS.2003.1293752 ↗
77. Comparing support vector machines with Gaussian kernels to radial basis function classifiers10.1109/78.650102 ↗
78. Support vector machines for predictive modeling in heterogeneous catalysis: A comprehensive introduction and overfitting investigation based on two real applications10.1021/cc050093m ↗
79. The problem of overfitting10.1021/ci0342472 ↗
80. Chollet, F. (2021). Deep Learning with Python, Simon and Schuster.
81. Müller, A.C., and Guido, S. (2016). Introduction to Machine Learning with Python: A Guide for Data Scientists, O’Reilly Media, Inc.
82. Parmar, A., Katariya, R., and Patel, V. (2018). A review on random forest: An ensemble classifier. Proceedings of the International Conference on Intelligent Data Communication Technologies and Internet of Things, Springer.10.1007/978-3-030-03146-6_86 ↗
83. Random forest classifier for remote sensing classification10.1080/01431160412331269698 ↗
84. Géron, A. (2019). Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O’Reilly Media, Inc.
85. Multilayer perceptron and neural networks
86. Perceptrons of large weight10.1134/S0032946009010062 ↗
87. Rojas, R., and Rojas, R. (1996). The backpropagation algorithm. Neural Networks: A Systematic Introduction, Springer.10.1007/978-3-642-61068-4_7 ↗
88. Backpropagation neural networks: A tutorial10.1016/0169-7439(93)80052-J ↗
89. Zhang, Z. (2018, January 4–6). Improved adam optimizer for deep neural networks. Proceedings of the 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS), Banff, AB, Canada.10.1109/IWQoS.2018.8624183 ↗
90. An improved categorical cross entropy for remote sensing image classification based on noisy labels10.1016/j.eswa.2022.117296 ↗
91. Regularizing multilayer perceptron for robustness10.1109/TSMC.2017.2664143 ↗
92. Doan, C.D., and Liong, S.Y. (2004, January 5–8). Generalization for multilayer neural network bayesian regularization or early stopping. Proceedings of the Asia Pacific Association of Hydrology and Water Resources 2nd Conference, Singapore.
93. Input layer regularization of multilayer feedforward neural networks10.1109/ACCESS.2017.2713389 ↗
94. Hyperspectral imaging: Calibration problems and solutions10.1016/j.chemolab.2004.01.023 ↗
95. Calibration-Jitter: Augmentation of hyperspectral data for improved surgical scene segmentation10.1049/htl2.12102 ↗
96. Adjé, E.A., Delmaire, G., Ahouandjinou, A.S., Puigt, M., and Roussel, G. (2024, January 9–11). Robust Approach for Butterfly Species Classification Using A Single Spatio-Hyperspectral Image. Proceedings of the 2024 14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), Helsinki, Finland.10.1109/WHISPERS65427.2024.10876422 ↗
97. 3D residual spatial–spectral convolution network for hyperspectral remote sensing image classification10.1007/s00521-022-07933-8 ↗
98. Yoon, J., Grigoroiu, A., and Bohndiek, S.E. (2020). A background correction method to compensate illumination variation in hyperspectral imaging. PLoS ONE, 15.10.1371/journal.pone.0229502 ↗
99. Adaptive Nonuniformity Correction Methods for Push-Broom Hyperspectral Cameras10.1109/JSTARS.2025.3540594 ↗
100. He, J., Riley, D.N., and Barton, I. (2024). Is Endmember Extraction a Critical Step in the Analysis of Hyperspectral Images in Mining Environments?. Remote Sens., 16.10.3390/rs16122137 ↗