DATACORTECH: artificial intelligence platform for the virtual screen of aluminum corrosion inhibitors

• Published in: Npj Materials degradation Vol. 8; no. 1; pp. 70 - 9
• Main Authors: Galvão, Tiago L. P., Ferreira, Inês, Maia, Frederico, Gomes, José R. B., Tedim, João
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 11-07-2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/301/1023/1026; 639/301/1034/1037; Aluminum alloys; Aluminum base alloys; Artificial intelligence; Chemistry and Materials Science; Classification; Corrosion; Corrosion and Coatings; Corrosion inhibitors; Corrosion tests; Efficiency; Electrochemistry; Electrolytes; Machine learning; Materials Science; Molecular structure; Structural Materials; Technological change; Tribology
• ISSN: 2397-2106; 2397-2106
• DOI: 10.1038/s41529-024-00489-z

The machine learning framework reported herein can greatly accelerate the development of more effective and sustainable corrosion inhibitors for aluminum alloys, which still rely mostly on the experience of corrosion scientists, and trial and error laboratory testing. It can be used to design inhibitors for specific applications, which can be immobilized into nanocontainers or included directly into coatings in the search for less hazardous corrosion protective technologies. Therefore, a machine learning (ML) classification model that allows to identify promising compounds ( > 70% inhibitor efficiency) among less promising ones, and an online application (
https://datacor.shinyapps.io/datacortech/
) were developed for the virtual screen (simulation) of potential inhibitors for aluminum alloys, capable of considering the molecular structure and the influence of pH as an input.