Foundation Models for Atomistic Simulation of Chemistry and Materials

TL;DR

This paper explores the development of large-scale, pre-trained foundation models for atomistic simulations in chemistry and materials, aiming for more efficient, transferable, and robust models compared to traditional methods.

Contribution

It proposes a pathway to create large, pre-trained machine learning interatomic potential models for chemistry and materials sciences.

Findings

Scaling datasets and architectures improves model transferability.

Pre-training enhances robustness to out-of-distribution data.

Foundation models can be fine-tuned for various atomic simulation tasks.

Abstract

Given the power of large language and large vision models, it is of profound and fundamental interest to ask if a foundational model based on data and parameter scaling laws and pre-training strategies is possible for learned simulations of chemistry and materials. The scaling of large and diverse datasets and highly expressive architectures for chemical and materials sciences should result in a foundation model that is more efficient and broadly transferable, robust to out-of-distribution challenges, and easily fine-tuned to a variety of downstream observables, when compared to specific training from scratch on targeted applications in atomistic simulation. In this Perspective we aim to cover the rapidly advancing field of machine learned interatomic potentials (MLIP), and to illustrate a path to create chemistry and materials MLIP foundation models at larger scale.