Universal Machine Learning Potentials under Pressure

TL;DR

This paper evaluates the performance of universal machine learning interatomic potentials under high-pressure conditions, revealing limitations at extreme pressures and demonstrating that targeted fine-tuning can enhance their robustness.

Contribution

It systematically investigates uMLIPs under pressure, identifies their performance decline at high pressures, and shows fine-tuning can improve their accuracy in extreme regimes.

Findings

Performance drops at pressures above 0 GPa

Limitations stem from training data gaps

Fine-tuning improves high-pressure accuracy

Abstract

Universal machine learning interatomic potentials (uMLIPs) represent arguably the most successful application of machine learning to materials science, demonstrating remarkable performance across diverse applications. However, critical blind spots in their reliability persist. Here, we address one such significant gap by systematically investigating the accuracy of uMLIPs under extreme pressure conditions from 0 to 150 GPa. Our benchmark reveals that while these models excel at standard pressure, their predictive accuracy deteriorates considerably as pressure increases. This decline in performance originates from fundamental limitations in the training data rather than in algorithmic constraints. In fact, we show that through targeted fine-tuning on high-pressure configurations, the robustness of the models can be easily increased. These findings underscore the importance of identifying and addressing overlooked regimes in the development of the next generation of truly universal interatomic potentials.