Composition based oxidation state prediction of materials using deep learning

TL;DR

This paper introduces BERTOS, a deep learning transformer model that predicts oxidation states of inorganic compounds solely from their chemical composition, achieving high accuracy and aiding large-scale material discovery.

Contribution

The paper presents a novel composition-based deep learning model for oxidation state prediction, addressing a gap where structural data is unavailable, and demonstrates its effectiveness on large datasets.

Findings

Achieves 96.82% accuracy on all-element oxidation state prediction.

Achieves 97.61% accuracy for oxide materials.

Enables large-scale screening of hypothetical materials.

Abstract

Oxidation states are the charges of atoms after their ionic approximation of their bonds, which have been widely used in charge-neutrality verification, crystal structure determination, and reaction estimation. Currently only heuristic rules exist for guessing the oxidation states of a given compound with many exceptions. Recent work has developed machine learning models based on heuristic structural features for predicting the oxidation states of metal ions. However, composition based oxidation state prediction still remains elusive so far, which is more important in new material discovery for which the structures are not even available. This work proposes a novel deep learning based BERT transformer language model BERTOS for predicting the oxidation states of all elements of inorganic compounds given only their chemical composition. Our model achieves 96.82\% accuracy for all-element oxidation states prediction benchmarked on the cleaned ICSD dataset and achieves 97.61\% accuracy for oxide materials. We also demonstrate how it can be used to conduct large-scale screening of hypothetical material compositions for materials discovery.