Automated Assessment of Marine Steel Corrosion Using Visible–Near-Infrared Hyperspectral Imaging

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.