Discovery of sustainable energy materials via the machine-learned material space

TL;DR

This paper demonstrates that a graph attention network can learn an interpretable and chemically meaningful representation of the material space, enabling the discovery of sustainable energy materials and providing insights into their properties.

Contribution

The study shows that machine learning models can capture a nuanced understanding of the material space, facilitating the discovery of sustainable energy materials through interpretability of learned embeddings.

Findings

The OptiMate model's embeddings reflect chemical and physical principles.

Clustering of 10,000 materials based on learned representations.

Identification of sustainable alternatives to critical energy materials.

Abstract

Does a machine learning model actually gain an understanding of the material space? We answer this question in the affirmative on the example of the OptiMate model, a graph attention network trained to predict the optical properties of semiconductors and insulators. By applying the UMAP dimensionality reduction technique to its latent embeddings, we demonstrate that the model captures a nuanced and interpretable representation of the materials space, reflecting chemical and physical principles, without any user-induced bias. This enables clustering of almost 10,000 materials based on optical properties and chemical similarities. Beyond this understanding, we demonstrate how the learned material space can be used to identify more sustainable alternatives to critical materials in energy-related technologies, such as photovoltaics. These findings demonstrate the dual utility of machine learning models in materials science: Accurately predicting material properties while providing insights into the underlying materials space. The approach demonstrates the broader potential of leveraging learned materials spaces for the discovery and design of materials for diverse applications, and is easily applicable to any state-of-the-art machine learning model.