This project focuses on exploring the capabilities of Bayesian optimization, specifically employing BayBE, in the discovery of novel corrosion inhibitors for materials design. Initially, we work with a randomly chosen subset from a comprehensive database of electrochemical responses of small organic molecules for aluminum alloys. Our goal is to assess how Bayesian optimization can speed up the screening process across the design space to identify promising compounds. We compare different strategies for incorporating chemical information, while optimizing the experimental parameters with respect to the inhibitive performance of the screened compounds. Finally, we explore the potential of transfer learning to accelerate corrosion inhibitor discovery for other base materials as well.

If you want to connect and/or want to learn more about our contributions and learnings, feel free to reach out and check our postings on LinkedIn by Michail Mitsakis, Alexander Wieczorek, Can Özkan and Tim Würger!

References:

1. Galvão, T.L.P., Ferreira, I., Kuznetsova, A. et al. CORDATA: an open data management web application to select corrosion inhibitors. npj Mater Degrad 6, 48 (2022).
2. Özkan, C., Sahlmann, L., Feiler, C. et al. Laying the experimental foundation for corrosion inhibitor discovery through machine learning. npj Mater Degrad 8, 21 (2024).
3. Würger, T., Mei, D., Vaghefinazari, B. et al. Exploring structure-property relationships in magnesium dissolution modulators. npj Mater Degrad 5, 2 (2021).