Cross-category prediction of corrosion inhibitor performance based on molecular graph structures via a three-level message passing neural network model. (December 2022)

• Record Type: Journal Article
• Authors: Dai, Jiaxin; Fu, Dongmei; Song, Guangxuan; Ma, Lingwei; Guo, Xin; Mol, Arjan; Cole, Ivan; Zhang, Dawei
• Is Part Of: Corrosion science. Volume 209(2022)
• Publication Date: 2022-12
• Subjects: Corrosion inhibitors -- Molecular structure -- Machine learning -- Message passing neural network -- SMILES; Corrosion and anti-corrosives -- Periodicals; 620.11223
• DOI: 10.1016/j.corsci.2022.110780
• Languages: English
• ISSNs: 0010-938X

Abstract

Abstract: Current experimental verification, computational modeling, and machine learning methods for predicting corrosion inhibition efficiency (IE) are limited to specific inhibitor categories with high cost and poor generalization. In this study, a cross-category corrosion inhibitor dataset is constructed and a three-level direct message passing neural network (3 L–DMPNN) model using molecular structure information that integrates atomic-level, chemical bond-level, and molecular-level features to predict the IEs of compounds in a specific environment is established. This work demonstrates that the 3 L–DMPNN model can predict IEs of cross-category corrosion inhibitors from other independent literature and experimental dataset effectively and quickly. Highlights: A cross-category corrosion inhibitor molecular dataset is constructed from literature. Corrosion inhibition data are processed by a three-level message passing neural network (3 L–DMPNN) model. Atomic-level, bond-level and molecular-level features are integrated into the model. 3 L–DMPNN model shows superior accuracy for cross-category inhibition efficiency prediction.