Ultra-fast interpretable machine-learning potentials

Abstract

All-atom dynamics simulations are an indispensable quantitative tool in physics, chemistry, and materials science, but large systems and long simulation times remain challenging due to the trade-off between computational efficiency and predictive accuracy. To address this challenge, we combine effective two- and three-body potentials in a cubic B-spline basis with regularized linear regression to obtain machine-learning potentials that are physically interpretable, sufficiently accurate for applications, as fast as the fastest traditional empirical potentials, and two to four orders of magnitude faster than state-of-the-art machine-learning potentials. For data from empirical potentials, we demonstrate exact retrieval of the potential. For data from density functional theory, the predicted energies, forces, and derived properties, including phonon spectra, elastic constants, and melting points, closely match those of the reference method. The introduced potentials might contribute towards accurate all-atom dynamics simulations of large atomistic systems over long time scales.

References in corpus (5)

• Machine Learning Force Fields
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Physics-inspired structural representations for molecules and materials
• Classical potential describes martensitic phase transformations between the $\alpha$, $\beta$ and $\omega$ titanium phases
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations

Cited by in corpus (14)

• A practical guide to machine learning interatomic potentials -- Status and future
• Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces
• Deep Coarse-grained Potentials via Relative Entropy Minimization
• On the design space between molecular mechanics and machine learning force fields
• Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
• Machine Learned Interatomic Potentials for Ternary Carbides trained on the AFLOW Database
• Accelerating superconductor discovery through tempered deep learning of the electron-phonon spectral function
• Machine Learning Potentials for Hydrogen Absorption in TiCr${}_2$ Laves Phases
• Machine-learning potentials for structurally and chemically complex MAB phases: strain hardening and ripplocation-mediated plasticity
• Application-specific machine-learned interatomic potentials: exploring the trade-off between DFT convergence, MLIP expressivity, and computational cost
• Machine-Learned Interatomic Potential for Predictive Simulation of MoS2 Epitaxy
• Interpretation of Crystal Energy Landscapes with Kolmogorov-Arnold Networks
• Self-consistency error correction for accurate machine learning potentials from variational Monte Carlo
• Reactive Coarse Grained Force Field for Metal-Organic Frameworks applied to Modeling ZIF-8 Self-Assembly