Hessian-informed machine learning interatomic potential towards bridging theory and experiments

2026-03-26

AI Summary

Traditional machine learning interatomic potentials struggle to accurately capture the local curvature of potential energy surfaces, limiting their predictive capability for key thermodynamic and kinetic properties. This work proposes a Hessian-informed machine learning interatomic potential (Hi-MLIP) and introduces an efficient training framework, HINT, which integrates Hessian pretraining, configuration sampling, curriculum learning, and stochastic projection loss. By leveraging these strategies, Hi-MLIP achieves chemical accuracy while drastically reducing the need for expensive Hessian labels. The method excels under data-scarce conditions, accurately capturing strong anharmonic effects, reproducing experimental superconducting critical temperatures, and significantly improving the accuracy of transition state searches and Gibbs free energy predictions.

Technology Category

• Machine Learning: Kernel Methods
• Humans and AI: Human-in-the-loop Machine Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Local curvature of potential energy surfaces is critical for predicting certain experimental observables of molecules and materials from first principles, yet it remains far beyond reach for complex systems. In this work, we introduce a Hessian-informed Machine Learning Interatomic Potential (Hi-MLIP) that captures such curvature reliably, thereby enabling accurate analysis of associated thermodynamic and kinetic phenomena. To make Hessian supervision practically viable, we develop a highly efficient training protocol, termed Hessian INformed Training (HINT), achieving two to four orders of magnitude reduction for the requirement of expensive Hessian labels. HINT integrates critical techniques, including Hessian pre-training, configuration sampling, curriculum learning and stochastic projection Hessian loss. Enabled by HINT, Hi-MLIP significantly improves transition-state search and brings Gibbs free-energy predictions close to chemical accuracy especially in data-scarce regimes. Our framework also enables accurate treatment of strongly anharmonic hydrides, reproducing phonon renormalization and superconducting critical temperatures in close agreement with experiment while bypassing the computational bottleneck of anharmonic calculations. These results establish a practical route to enhancing curvature awareness of machine learning interatomic potentials, bridging simulation and experimental observables across a wide range of systems.

Problem

• Hessian
• interatomic potential
• potential energy surface curvature
• anharmonicity
• machine learning

Innovation

• Hessian-informed
• machine learning interatomic potential
• anharmonic phonons
• transition-state search
• curriculum learning