Self-supervised learning of materials concepts from crystal structures via deep neural networks
Open Access
- 1 December 2022
- journal article
- research article
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 3 (4) , 045034
Abstract
Material development involves laborious processes to explore the vast materials space. The key to accelerating these processes is understanding the structure-functionality relationships of materials. Machine learning has enabled large-scale analysis of underlying relationships between materials via their vector representations, or embeddings. However, the learning of material embeddings spanning most known inorganic materials has remained largely unexplored due to the expert knowledge and efforts required to annotate large-scale materials data. Here we show that our self-supervised deep learning approach can successfully learn material embeddings from crystal structures of over 120 000 materials, without any annotations, to capture the structure-functionality relationships among materials. These embeddings revealed the profound similarity between materials, or ‘materials concepts’, such as cuprate superconductors and lithium-ion battery materials from the unannotated structural data. Consequently, our results enable us to both draw a large-scale map of the materials space, capturing various materials concepts, and measure the functionality-aware similarities between materials. Our findings will enable more strategic approaches to material development.Keywords
Funding Information
- Japan Science and Technology Agency (JPMJMI19G1)
This publication has 39 references indexed in Scilit:
- Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical SpaceThe Journal of Physical Chemistry Letters, 2015
- Crystal structure representations for machine learning models of formation energiesInternational Journal of Quantum Chemistry, 2015
- Materials Cartography: Representing and Mining Materials Space Using Structural and Electronic FingerprintsChemistry of Materials, 2015
- On representing chemical environmentsPhysical Review B, 2013
- Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysisComputational Materials Science, 2013
- Fast and Accurate Modeling of Molecular Atomization Energies with Machine LearningPhysical Review Letters, 2012
- VESTA 3for three-dimensional visualization of crystal, volumetric and morphology dataJournal of Applied Crystallography, 2011
- Superconductivity above 130 K in the Hg–Ba–Ca–Cu–O systemNature, 1993
- New Classification Method for Layered Copper Oxide Compounds and Its Application to Design of New High Tc SuperconductorsJapanese Journal of Applied Physics, 1990
- A new high-Tc TlBa2Ca3Cu4O11 superconductor with Tc >120KNature, 1988