Speaker
Description
Does a machine learning (ML) model capture the intrinsic structure of the material space? The example of the OptiMate model, a graph attention network trained to predict the optical properties of semiconductors and insulators, provides an affirmative answer. By applying the UMAP dimensionality reduction technique to its latent embeddings, it is demonstrated 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. Furthermore, it is shown 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 ML 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 ML model.
M. Grunert, M. Grossmann, E. Runge: Nat. Commun. 16, 8142 (2025), Small 22, 2412519 (2026), Appl. Phys. Lett. 128, 053302 (2026)