Rapid Exploration of Crystal Chemical Space

Traditional materials modelling workflows, even in the form of high-throughput approaches, are limited to small numbers of compositions and structures. I will present progress in materials informatics solutions for navigating a larger crystal chemical space. This includes techniques for compositional screening based on elemental features and mapping from chemical formulae to three-dimensional crystal structures [1,2]. A focus will be placed on hand-built chemical filters to reduce the magnitude of the search space and filters that are learned from data in the form of deep learning models based on crystal graphs. The performance of data-driven and domain knowledge-inspired approaches will be compared. Outstanding challenges in the field including robust synthesisability metrics [4] and generative artificial intelligence models for sampling new materials will also be discussed.<br/><br/>1. D. W. Davies et al, "Computational Screening of all Stoichiometric Inorganic Materials", Chem 1, 617 (2016); https://doi.org/10.1016/j.chempr.2016.09.010<br/><br/>2. A. Onwuli et al, "Element Similarity in High-Dimensional Materials Representations", Digital Discovery 2, 1558 (2023); https://doi.org/10.1039/D3DD00121K<br/><br/>3. H. Park et al, "Mapping Inorganic Crystal Chemical Space", Faraday Discussions (2024); https://doi.org/10.1039/D4FD00063C<br/><br/>4. K. Tolborg et al, "Free Energy Predictions for Crystal Stability and Synthesisability", Digital Discovery 1, 586 (2022); https://doi.org/10.1039/D2DD00050D