How to validate machine-learned interatomic potentials

Abstract

Machine learning (ML) approaches enable large-scale atomistic simulations with near-quantum-mechanical accuracy. With the growing availability of these methods there arises a need for careful validation, particularly for physically agnostic models - that is, for potentials which extract the nature of atomic interactions from reference data. Here, we review the basic principles behind ML potentials and their validation for atomic-scale materials modeling. We discuss best practice in defining error metrics based on numerical performance as well as physically guided validation. We give specific recommendations that we hope will be useful for the wider community, including those researchers who intend to use ML potentials for materials "off the shelf".

References in corpus (9)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Machine learning for molecular simulation
• High-pressure phases of silane
• Machine-learning based interatomic potential for amorphous carbon
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• An Accurate and Transferable Machine Learning Potential for Carbon
• Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations
• Combining phonon accuracy with high transferability in Gaussian approximation potential models

Cited by in corpus (17)

• 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
• Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
• Tutorial: How to Train a Neural Network Potential
• Machine learned Force-Fields for an ab-initio Quality Description of Metal-Organic Frameworks
• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• PhysNet Meets CHARMM: A Framework for Routine Machine Learning / Molecular Mechanics Simulations
• Data efficiency and extrapolation trends in neural network interatomic potentials
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Physics-informed active learning for accelerating quantum chemical simulations
• Beam induced heating in electron microscopy modeled with machine learning interatomic potentials
• Enhanced sampling of robust molecular datasets with uncertainty-based collective variables
• Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2
• Accelerated lignocellulosic molecule adsorption structure determination
• Slowly Quenched, High Pressure Glassy B${}_2$O${}_3$ at DFT Accuracy
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Accelerating point defect simulations using data-driven and machine learning approaches