Data science framework to select corrosion inhibitors

Organic corrosion inhibitors embedded in coatings play a crucial role substituting traditional anti-corrosion pigments, which can cause acute toxicity problems to human health and the environment. However, why some organic compounds inhibit corrosion and others do not, is still not well understood. Therefore, we are currently developing two complementary technological approaches to help corrosion scientists and engineers working in academia and across different industries choose the optimal inhibitor for each specific problem: 1) build an interactive exploratory data tool for the selection of the ideal corrosion inhibitor taking into account different conditions (type of alloy, electrolyte, pH, etc.) based on previously published information (https://datacor.shinyapps.io/cordata/), and 2) develop machine learning models and an online tool to perform an initial virtual screen of potential molecules for the design of more efficient organic corrosion inhibitors (1). These two approaches will contribute to the digitalization of inhibitor search, helping speed up research in the corrosion science and tailor corrosion protective technologies in a more efficient and condition specific manner.

Acknowledgements: Project DataCor (refs. POCI-01-0145-FEDER-030256 and PTDC/QUI-QFI/30256/2017, datacorproject.wixsite.com/datacor).

(1) T.L.P. Galvão, G. Novell-Leruth, A. Kuznetsova, J. Tedim, J.R.B. Gomes, J. Phys. Chem. C, 124, 2020, 5624-5635.