This study investigates the performance of a polypropylene myristic acid-modified copper (Cu) superhydrophobic coating under various conditions, including immersion in NaCl solution, abrasion tests, pH levels, and temperature variations. We utilized specific machine learning models, such as random forest (RF) and XGBoost, to predict the wettability behavior of materials under varying voltage and temperature conditions. Gaussian noise data augmentation was employed to improve the model accuracy and prevent overfitting. The RF model demonstrated strong generalization capabilities, with consistently low MSE values and high R 2 values across training and testing data sets. In contrast, the XGBoost model showed a slight performance decline when transitioning from training data to testing data, indicating potential generalization limitations. For variables such as immersion days, abrasion cycles, pH levels, and temperatures, multiple polynomial regression models were developed to predict the contact angle, showing a high degree of alignment with experimental data. The predictions of contact angle after 122 days of immersion in the NaCl solution (3.5 wt %), 350 abrasion cycles (each cycle of 18 cm), and exposure to 400 °C indicated sustained hydrophobic properties. The predicted contact angles were 110°for immersion in NaCl, 400 °C, and for abrasion cycles it is 99°. These predictions closely match with the experimental results, which showed contact angles of 103.7°for immersion, abrasion cycles and 97°for temperature exposure. The coating's robustness is attributed to its micro/nanostructured surface, which traps air and reduces water contact, and the chemical stability imparted by polypropylene myristic acid modification, ensuring low surface energy and durability. This study demonstrates the effectiveness of higher-degree polynomial models in accurately predicting the performance of superhydrophobic coatings, underscoring the potential of advanced modeling techniques in the development of durable, high-performance coatings.