PolyMicros: Bootstrapping a Foundation Model for Polycrystalline Material Structure

TL;DR

PolyMicros introduces a physics-driven data augmentation method that enables foundation models to learn from very limited data, specifically for polycrystalline materials, advancing materials discovery and analysis.

Contribution

It presents a novel data augmentation scheme using local generative models and diversity curation to build foundation models from sparse data in complex scientific domains.

Findings

Successfully trained PolyMicros with as few as five observations.

Demonstrated zero-shot solutions to longstanding microscopy challenges.

Made models and datasets openly accessible to researchers.

Abstract

Recent advances in Foundation Models for Materials Science are poised to revolutionize the discovery, manufacture, and design of novel materials with tailored properties and responses. Although great strides have been made, successes have been restricted to materials classes where multi-million sample data repositories can be readily curated (e.g., atomistic structures). Unfortunately, for many structural and functional materials (e.g., mesoscale structured metal alloys), such datasets are too costly or prohibitive to construct; instead, datasets are limited to very few examples. To address this challenge, we introduce a novel machine learning approach for learning from hyper-sparse, complex spatial data in scientific domains. Our core contribution is a physics-driven data augmentation scheme that leverages an ensemble of local generative models, trained on as few as five experimental observations, and coordinates them through a novel diversity curation strategy to generate a large-scale, physically diverse dataset. We utilize this framework to construct PolyMicros, the first Foundation Model for polycrystalline materials (a structural material class important across a broad range of industrial and scientific applications). We demonstrate the utility of PolyMicros by zero-shot solving several long standing challenges related to accelerating 3D experimental microscopy. Finally, we make both our models and datasets openly available to the community.