Element selection for crystalline inorganic solid discovery guided by unsupervised machine learning of experimentally explored chemistry



Vasylenko, Andrij, Gamon, Jacinthe, Duff, Benjamin B, Gusev, Vladimir V, Daniels, Luke M, Zanella, Marco, Shin, J Felix, Sharp, Paul M, Morscher, Alexandra, Chen, Ruiyong
et al (show 7 more authors) (2021) Element selection for crystalline inorganic solid discovery guided by unsupervised machine learning of experimentally explored chemistry. NATURE COMMUNICATIONS, 12 (1). 5561-.

Access the full-text of this item by clicking on the Open Access link.

Abstract

The selection of the elements to combine delimits the possible outcomes of synthetic chemistry because it determines the range of compositions and structures, and thus properties, that can arise. For example, in the solid state, the elemental components of a phase field will determine the likelihood of finding a new crystalline material. Researchers make these choices based on their understanding of chemical structure and bonding. Extensive data are available on those element combinations that produce synthetically isolable materials, but it is difficult to assimilate the scale of this information to guide selection from the diversity of potential new chemistries. Here, we show that unsupervised machine learning captures the complex patterns of similarity between element combinations that afford reported crystalline inorganic materials. This model guides prioritisation of quaternary phase fields containing two anions for synthetic exploration to identify lithium solid electrolytes in a collaborative workflow that leads to the discovery of Li<sub>3.3</sub>SnS<sub>3.3</sub>Cl<sub>0.7.</sub> The interstitial site occupancy combination in this defect stuffed wurtzite enables a low-barrier ion transport pathway in hexagonal close-packing.

Item Type: Article
Uncontrolled Keywords: 3403 Macromolecular and Materials Chemistry, 34 Chemical Sciences, Machine Learning and Artificial Intelligence
Divisions: Faculty of Science and Engineering > School of Physical Sciences
Depositing User: Symplectic Admin
Date Deposited: 29 Sep 2021 13:27
Last Modified: 20 Jun 2024 16:41
DOI: 10.1038/s41467-021-25343-7
Open Access URL: https://doi.org/10.1038/s41467-021-25343-7
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3138698