Multimodal Foundation Models for Material Property Prediction and Discovery

TL;DR

This paper introduces MultiMat, a multimodal foundation model for materials science that improves property prediction, enables novel material discovery, and provides interpretable features, leveraging diverse data sources.

Contribution

MultiMat is a novel self-supervised multimodal foundation model that advances material property prediction and discovery by integrating diverse datasets and properties.

Findings

Achieves state-of-the-art performance in property prediction

Enables accurate screening for stable materials with desired properties

Encodes interpretable features offering scientific insights

Abstract

Artificial intelligence is transforming computational materials science, improving the prediction of material properties, and accelerating the discovery of novel materials. Recently, publicly available material data repositories have grown rapidly. This growth encompasses not only more materials but also a greater variety and quantity of their associated properties. Existing machine learning efforts in materials science focus primarily on single-modality tasks, i.e. relationships between materials and a single physical property, thus not taking advantage of the rich and multimodal set of material properties. Here, we introduce Multimodal Learning for Materials (MultiMat), which enables self-supervised multi-modality training of foundation models for materials. We demonstrate our framework's potential using data from the Materials Project database on multiple axes: (i) MultiMat achieves state-of-the-art performance for challenging material property prediction tasks; (ii) MultiMat enables novel and accurate material discovery via latent space similarity, enabling screening for stable materials with desired properties; and (iii) MultiMat encodes interpretable emergent features that may provide novel scientific insights.