Exploring materials dataspaces by combining supervised and unsupervised machine learning

Artificial intelligence (AI) can provide disruptive technology in various social and scientific areas. In materials science, a main pillar for meaningful AI applications is the creation of characterized datasets, on which much of current efforts are concentrated [1, 2]. In this talk, we discuss a rarely addressed topic - the development of automatic tools to explore the available materials-science data. In particular, we go beyond purely predictive, supervised learning by combining unsupervised analysis with a recently developed crystal-structure recognition method that is based on Bayesian deep learning [3]. This neural-network (NN) model automatically learns data representations that contain information on structurally diverse crystal geometries. Using state-of-the-art clustering, physically meaningful subgroups can be identified in the NN latent space, which are shown, e.g., to correspond to distinct, experimentally verified grain-boundary phases [4]. Moreover, dimension-reduction analysis allows us to create low-dimensional, interpretable materials charts that visualize complex (i.e., single-, poly-, quasi-crystalline and amorphous) structural data from both theoretical and experimental origin [4, 5].

[1] M. Wilkinson et al. Sci. Data. 3, 160018 (2016)

[2] C. Draxl, M. Scheffler, MRS Bull. 43, 676-682 (2018)

[3] A. Leitherer, A. Ziletti and L. M. Ghiringhelli. Nat. Commun. 12, 6234 (2021)

[4] T. Meiners, T. Frolov, R.E. Rudd, et al. Nature 579, 375–378 (2020)

[5] Y. Yang et al. Nature 592, 60 (2021)