Predicting the inhibition efficiencies of magnesium dissolution modulators using sparse machine learning models

The degradation behaviour of magnesium and its alloys can be tuned by small organic molecules. However, an automatic identification of effective organic additives within the vast chemical space of potential compounds needs sophisticated tools. Herein, we propose two systematic approaches of sparse feature selection for identifying molecular descriptors that are most relevant for the corrosion inhibition efficiency of chemical compounds. One is based on the classical statistical tool of analysis of variance, the other one based on random forests. We demonstrate how both can-when combined with deep neural networks-help to predict the corrosion inhibition efficiencies of chemical compounds for the magnesium alloy ZE41. In particular, we demonstrate that this framework outperforms predictions relying on a random selection of molecular descriptors. Finally, we point out how autoencoders could be used in the future to enable even more accurate automated predictions of corrosion inhibition efficiencies.

Automated summary

The article proposes two systematic approaches for identifying molecular descriptors most relevant for the corrosion inhibition efficiency of chemical compounds using sparse feature selection, one based on analysis of variance and the other on random forests. Both combined with deep neural networks can predict the corrosion inhibition efficiencies, outperforming predictions relying on random selection of molecular descriptors. Autoencoders could be used in the future to enable even more accurate automated predictions of corrosion inhibition efficiencies.