Towards understanding and prediction of corrosion degradation of organic coatings under tropical marine atmospheric environment via a data-driven approach

Corrosion degradation of organic coatings in tropical marine atmospheric environments leads to substantial economic losses across various industries. The complexity of the dynamic environment, combined with high costs, extended experimental periods, and limited data, has made understanding this process challenging. This study addresses these challenges by investigating the corrosion degradation of damaged organic coatings in a tropical marine environment using an atmospheric corrosion monitoring (ACM) sensor and a random forest (RF) model. A polyurethane coating applied to an Fe/graphite corrosion sensor was intentionally scratched to simulate damage and then exposed to the marine atmosphere for over one year. Environmental and corrosion current data were collected and filtered using Pearson correlation analysis. The RF model identified specific conditions that contribute to accelerated degradation: relative humidity (RH) above 80% and temperatures below 22.5°C, with the risk increasing significantly when RH exceeds 90%. High RH and temperature were found to have a cumulative effect on the degradation of coatings. A high risk of corrosion was observed in the nighttime. The RF model was also used to predict the coating degradation process using environmental data as input parameters, with an accuracy improved by considering the duration of influential environmental ranges.