Matrix- and tensor-based recommender systems for the discovery of currently unknown inorganic compounds

TL;DR

This paper introduces matrix- and tensor-based recommender systems to predict unknown inorganic compound compositions, successfully identifying stable compounds and demonstrating potential to accelerate materials discovery.

Contribution

It presents a novel application of recommender systems, especially Tucker decomposition, for predicting unknown inorganic compositions from crystal structure databases.

Findings

Tucker decomposition recommender system achieved the highest discovery rate.

23 out of 27 predicted compounds were found to be stable.

Recommender systems effectively identify promising new inorganic compounds.

Abstract

Chemically relevant compositions (CRCs) and atomic arrangements of inorganic compounds have been collected as inorganic crystal structure databases. Machine-learning is a unique approach to search for currently unknown CRCs from vast candidates. Herein we propose matrix- and tensor-based recommender system approaches to predict currently unknown CRCs from database entries of CRCs. Firstly, the performance of the recommender system approaches to discover currently unknown CRCs is examined. A Tucker decomposition recommender system shows the best discovery rate of CRCs as the majority of the top 100 recommended ternary and quaternary compositions correspond to CRCs. Secondly, systematic density functional theory (DFT) calculations are performed to investigate the phase stability of the recommended currently unknown CRCs. The phase stability of the 27 compositions reveals that 23 currently unknown compounds are stable. These results indicate that the recommender system has great potential to accelerate the discovery of new compounds.