Creating durable, eco-friendly coatings for long-term corrosion protection requires innovative strategies. Machine learning is a promising catalyst, but high-quality datasets are scarce. This research created an extensive electrochemical library of 80 inhibitor candidates, testing their behavior on AA2024-T3 substrates using linear polarization resistance, electrochemical impedance spectroscopy, and potentiodynamic polarization. The results provide target parameters and input features for developing quantitative structure-property relationship (QSPR) models, augmented by mechanistic input features, to streamline inhibitor discovery.

Can Özkan, Lisa Sahlmann, Christian Feiler, Mikhail Zheludkevich, Sviatlana Lamaka, Parth Sewlikar, Agnieszka Kooijman, Peyman Taheri, Arjan Mol