Composition based oxidation state prediction of materials using deep learning

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. Oxidation states (OS) are the charges of atoms after their ionic approximation of their bonds, which are the fundamental attributes of elements that help to explain redox reactions, reactivity, chemical bonding, and chemical properties of different elements and compounds. In electrochemistry, oxidation states are used to represent relevant compounds and ions in Latimer and Frost diagrams, and they can also be used to calculate the charge neutrality of chemical compounds to screen potential hypothetical materials generated by computational design algorithms. Oxidation states have also been used to study the complexes of transition metals.