Hessian-informed machine learning interatomic potential towards bridging theory and experiments
This work addresses the problem of bridging theory and experiments for complex molecular and material systems by enhancing curvature awareness in interatomic potentials, though it appears incremental as it builds on existing machine learning methods with specific optimizations.
The authors tackled the challenge of accurately predicting experimental observables from potential energy surfaces by introducing a Hessian-informed Machine Learning Interatomic Potential (Hi-MLIP) that captures curvature reliably, enabling accurate analysis of thermodynamic and kinetic phenomena with improvements such as two to four orders of magnitude reduction in Hessian label requirements and close agreement with experimental data for hydrides.
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.