Density of states prediction for materials discovery via contrastive learning from probabilistic embeddings

Journal Article · 16 February 2022 · Nature Communications

DOI: https://doi.org/10.1038/s41467-022-28543-x · OSTI ID:1845605

Kong, Shufeng ; Ricci, Francesco; Guevarra, Dan; Neaton, Jeffrey B. ; Gomes, Carla P. ; Gregoire, John M.

Abstract Machine learning for materials discovery has largely focused on predicting an individual scalar rather than multiple related properties, where spectral properties are an important example. Fundamental spectral properties include the phonon density of states (phDOS) and the electronic density of states (eDOS), which individually or collectively are the origins of a breadth of materials observables and functions. Building upon the success of graph attention networks for encoding crystalline materials, we introduce a probabilistic embedding generator specifically tailored to the prediction of spectral properties. Coupled with supervised contrastive learning, our materials-to-spectrum (Mat2Spec) model outperforms state-of-the-art methods for predicting ab initio phDOS and eDOS for crystalline materials. We demonstrate Mat2Spec’s ability to identify eDOS gaps below the Fermi energy, validating predictions with ab initio calculations and thereby discovering candidate thermoelectrics and transparent conductors. Mat2Spec is an exemplar framework for predicting spectral properties of materials via strategically incorporated machine learning techniques.

• Research Organization: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
• Sponsoring Organization: Toyota Research Institute; USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES)
• Grant/Contract Number: AC02-05CH11231; SC0020383
• OSTI ID: 1845605
• Journal Information: Nature Communications, Journal Name: Nature Communications Journal Issue: 1 Vol. 13; ISSN 2041-1723
• Publisher: Nature Publishing GroupCopyright Statement
• Country of Publication: United Kingdom
• Language: English