Machine learning properties of ordered and disordered materials

Our paper on “Learning properties of ordered and disordered materials from multi-fidelity data” has just been published in the inaugural issue of Nature Computational Science! In this work, we address two major impediments to ML for materials science. The first impediment is that valuable accurate data is much more expensive to obtain than less accurate data. Using multi-fidelity materials graph networks (MEGNet), we show that we can use the lower quality data to improve underlying structural representations in models, and in the process significantly improve predictions on smaller, more valuable data (e.g., experimental measurements). The second impediment is that making predictions on disordered materials, which is the vast majority of known materials, is much more difficult than on ordered materials. We show that the elemental representations (embeddings) learned by our MEGNet models can be used to directly model disordered materials. The article is available here. For an independent perspective on the findings, check out the Nature News & Views article. All data and code are available from http://crystals.ai and the Github repository.

Ensemble learning of X-ray Absorption Spectra

Chen’s paper on “Automated generation and ensemble-learned matching of X-ray absorption spectra” has been published in npj Computational Materials. In this work, we developed XASdb, a large database of computed reference X-ray absorption spectra (XAS), and a novel Ensemble-Learned Spectra IdEntification (ELSIE) algorithm for the matching of spectra. XASdb currently hosts more than 800,000 K-edge X-ray absorption near-edge spectra (XANES) for over 40,000 materials from the open-science Materials Project database. We will demonstrate that the ELSIE algorithm, which combines 33 weak “learners” comprising a set of preprocessing steps and a similarity metric, can achieve up to 84.2% accuracy in identifying the correct oxidation state and coordination environment. The XASdb with the ELSIE algorithm has been integrated into a web application in the Materials Project, providing an important new public resource for the analysis of XAS to all materials researchers. Finally, the ELSIE algorithm itself has been made available as part of Veidt, an open source machine learning library for materials science.

Predicting Crystal Volumes

Iek-Heng Chu’s paper on “Predicting the Volumes of Crystals” has been published in Computational Materials Science. In this collaborative work with the Hacking Materials group, we developed two schemes for predicting crystal volumes. Accurate crystal volume estimates are immensely useful for further experimental analysis, or to generate initial guesses for electronic structure optimizations. The volume prediction algorithms are implemented in the open-source pymatgen software.