A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials

Abstract

We present a new interatomic potential for solids and liquids called Spectral Neighbor Analysis Potential (SNAP). The SNAP potential has a very general form and uses machine-learning techniques to reproduce the energies, forces, and stress tensors of a large set of small configurations of atoms, which are obtained using high-accuracy quantum electronic structure (QM) calculations. The local environment of each atom is characterized by a set of bispectrum components of the local neighbor density projected on to a basis of hyperspherical harmonics in four dimensions. The bispectrum components are the same bond-orientational order parameters employed by the GAP potential [arXiv:0910.1019]. The SNAP potential, unlike GAP, assumes a linear relationship between atom energy and bispectrum components. The linear SNAP coefficients are determined using weighted least-squares linear regression against the full QM training set. This allows the SNAP potential to be fit in a robust, automated manner to large QM data sets using many bispectrum coefficients.

Cited by in corpus (42)

• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• A deep potential model with long-range electrostatic interactions
• Accurate Force Field for Molybdenum by Machine Learning Large Materials Data
• Machine Learning for Predicting Thermal Transport Properties of Solids
• Gaussian approximation potentials for body-centered-cubic transition metals
• Deep learning inter-atomic potential model for accurate irradiation damage simulations
• Tutorial: How to Train a Neural Network Potential
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Data-driven Material Models for Atomistic Simulation
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Predicting tensorial molecular properties with equivariant machine-learning models
• An assessment of the structural resolution of various fingerprints commonly used in machine learning
• Efficient implementation of atom-density representations
• Combining phonon accuracy with high transferability in Gaussian approximation potential models
• Extending the limit of molecular dynamics with ab initio accuracy to 10 billion atoms
• Transferability of neural network potentials for varying stoichiometry: phonons and thermal conductivity of Mn${}_x$Ge${}_y$ compounds
• Thermophysical properties of FLiBe using moment tensor potentials
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• AENET-LAMMPS and AENET-TINKER: Interfaces for Accurate and Efficient Molecular Dynamics Simulations with Machine Learning Potentials
• Enabling particle applications for exascale computing platforms
• High Pressure and Temperature Neural Network Reactive Force Field for Energetic Materials
• Efficacy of the Radial Pair Potential Approximation for Molecular Dynamics Simulations of Dense Plasmas
• Hydrogen-induced degradation dynamics in silicon heterojunction solar cells via machine learning
• Atomistic simulations of magnetoelastic effects on sound velocity
• Machine-learning of atomic-scale properties based on physical principles
• Ab initio Canonical Sampling based on Variational Inference
• A Hessian-Based Assessment of Atomic Forces for Training Machine Learning Interatomic Potentials
• Spectral Neural Network Potentials for Binary Alloys
• Machine learning potentials for complex aqueous systems made simple
• Machine learning at the atomic-scale
• Machine Learning and Materials Informatics: Recent Applications and Prospects
• AI-accelerated Materials Informatics Method for the Discovery of Ductile Alloys
• Modeling refractory high-entropy alloys with efficient machine-learned interatomic potentials: defects and segregation
• Accessing negative Poisson`s ratio of graphene by machine learning interatomic potentials
• Rapid Exploration of Optimization Strategies on Advanced Architectures using TestSNAP and LAMMPS
• An Electrostatic Spectral Neighbor Analysis Potential (eSNAP) for Lithium Nitride
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations
• Efficient Data Selection Methods for the Development of Machine Learned Potentials
• Surfing multiple conformation-property landscapes via machine learning: Designing magnetic anisotropy
• Superheated solid state induced by a single collision event
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems