A learning scheme to predict atomic forces and accelerate materials simulations

Abstract

The behavior of an atom in a molecule, liquid or solid is governed by the force it experiences. If the dependence of this vectorial force on the atomic chemical environment can be $learned$ efficiently with high-fidelity from benchmark reference results-using "big data" techniques, i.e., without resorting to actual functional forms-then this capability can be harnessed to enormously speed up $insilico$ materials simulations. The present contribution provides several examples of how such a $force$ field for Al can be used to go far beyond the length-scale and time-scale regimes accessible presently using quantum mechanical methods. It is argued that pathways are available to systematically and continuously improve the predictive capability of such a learned force field in an adaptive manner, and that this concept can be generalized to include multiple elements.

5pages, 3 figures

References in corpus (2)

• Big Data of Materials Science - Critical Role of the Descriptor
• mlpy: Machine Learning Python

Cited by in corpus (57)

• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Comparing molecules and solids across structural and alchemical space
• Active learning of linearly parametrized interatomic potentials
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine-learning based interatomic potential for amorphous carbon
• Physics-inspired structural representations for molecules and materials
• Machine learning a general purpose interatomic potential for silicon
• Machine-learning interatomic potentials for materials science
• FCHL revisited: faster and more accurate quantum machine learning
• Physically-informed artificial neural networks for atomistic modeling of materials
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Perspective on integrating machine learning into computational chemistry and materials science
• Efficient nonparametric $n$-body force fields from machine learning
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Gaussian approximation potential modeling of lithium intercalation in carbon nanostructures
• Deep Learning of Accurate Force Field of Ferroelectric HfO${}_2$
• Stratified construction of neural network based interatomic models for multicomponent materials
• Deep learning inter-atomic potential model for accurate irradiation damage simulations
• Compositional optimization of hard-magnetic phases with machine-learning models
• Transferable and extensible machine learning derived atomic charges for modeling hybrid nanoporous materials
• Discrepancies and Error Evaluation Metrics for Machine Learning Interatomic Potentials
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
• Automated Calculation of Thermal Rate Coefficients using Ring Polymer Molecular Dynamics and Machine-Learning Interatomic Potentials with Active Learning
• Unsupervised machine learning for detection of phase transitions in off-lattice systems II. Applications
• On Machine Learning Force Fields for Metallic Nanoparticles
• Development of a general-purpose machine-learning interatomic potential for aluminum by the physically-informed neural network method
• Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
• Self-Parametrizing System-Focused Atomistic Models
• Development of a physically-informed neural network interatomic potential for tantalum
• Unsupervised learning of atomic environments from simple features
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Machine Learning for Atomic Forces in a Crystalline Solid: Transferability to Various Temperatures
• An Atomistic Fingerprint Algorithm for Learning Ab Initio Molecular Force Fields
• Machine learning electron correlation in a disordered medium
• In operando active learning of interatomic interaction during large-scale simulations
• Sampling algorithms for validation of supervised learning models for Ising-like systems
• Parametrization of Non-Bonded Force Field Terms for Metal-Organic Frameworks Using Machine Learning Approach
• A transferable artificial neural network model for atomic forces in nanoparticles
• Validation Workflow for Machine Learning Interatomic Potentials for Complex Ceramics
• Transferable empirical pseudopotenials from machine learning
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
• Building nonparametric $n$-body force fields using Gaussian process regression
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• Machine Learning and Materials Informatics: Recent Applications and Prospects
• Machine learning at the atomic-scale
• Neural-networks model for force prediction in multi-principal-element alloys
• Role of long-range dipolar interactions in the simulation of the properties of polar crystals using effective atomic potentials
• Mimicking complex dislocation dynamics by interaction networks
• Machine-Learned Potentials for Solvation Modeling
• Recent advances in accelerated discovery through machine learning and statistical inference
• Dynamically polarisable force-fields for surface simulations via multi-output classification Neural Networks
• ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks
• Improving accuracy of interatomic potentials: more physics or more data? A case study of silica