Demarcating Wetting States Classification of the Textured Surfaces Using Machine Learning

The accurate categorization and anticipation of wetting conditions on surfaces with texture play a crucial role in the advancement of specialty materials that possess customized characteristics suitable for various applications, such as self- cleaning surfaces, anti-fouling coatings, and fluid manipulation technologies. The conventional approaches for assessing wetting states, predominantly relying on contact angle measurements, encounter constraints in terms of operational efficiency, scalability, and responsiveness, especially when confronted with intricate surface characteristics. The present study investigates the use of machine learning (ML) models to address these obstacles, presenting an innovative strategy for the automated categorization and predictive modeling of wetting phenomena on engineered surfaces. The experimental findings provide evidence of the effectiveness of machine learning models in properly classifying hydrophilic, hydrophobic, and superhydrophilic states, resulting in a substantial reduction in the time and effort required compared to conventional estimation techniques. From this present study, it has been found that Random Forest and XGBoost models are found to be more accurate in classifying the surfaces based on hydrophobicity.