Global Universal Scaling and Ultra-Small Parameterization in Machine Learning Interatomic Potentials with Super-Linearity

TL;DR

This paper introduces SUS2-MLIP, a physics-informed, super-linear machine learning interatomic potential that achieves high expressiveness and scalability with fewer parameters, improving generalizability and efficiency in materials simulations.

Contribution

The paper develops SUS2-MLIP, a novel MLIP model that incorporates universal scaling laws and nonlinear interaction functions for enhanced efficiency and physical scalability.

Findings

SUS2-MLIP has significantly fewer parameters than traditional models.

It outperforms state-of-the-art MLIPs in computational efficiency.

The model demonstrates strong generalizability across different material systems.

Abstract

Using machine learning (ML) to construct interatomic interactions and thus potential energy surface (PES) has become a common strategy for materials design and simulations. However, those current models of machine learning interatomic potential (MLIP) provide no relevant physical constrains, and thus may owe intrinsic out-of-domain difficulty which underlies the challenges of model generalizability and physical scalability. Here, by incorporating physics-informed Universal-Scaling law and nonlinearity-embedded interaction function, we develop a Super-linear MLIP with both Ultra-Small parameterization and greatly expanded expressive capability, named SUS2-MLIP. Due to the global scaling rooting in universal equation of state (UEOS), SUS2-MLIP not only has significantly-reduced parameters by decoupling the element space from coordinate space, but also naturally outcomes the out-of-domain difficulty and endows the potentials with inherent generalizability and scalability even with relatively small training dataset. The nonlinearity-enbeding transformation for interaction function expands the expressive capability and make the potentials super-linear. The SUS2-MLIP outperforms the state-of-the-art MLIP models with its exceptional computational efficiency especially for multiple-element materials and physical scalability in property prediction. This work not only presents a highly-efficient universal MLIP model but also sheds light on incorporating physical constraints into artificial-intelligence-aided materials simulation.