Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species

Abstract

Machine-learning potentials (MLPs) for atomistic simulations are a promising alternative to conventional classical potentials. Current approaches rely on descriptors of the local atomic environment with dimensions that increase quadratically with the number of chemical species. In this article, we demonstrate that such a scaling can be avoided in practice. We show that a mathematically simple and computationally efficient descriptor with constant complexity is sufficient to represent transition-metal oxide compositions and biomolecules containing 11 chemical species with a precision of around 3 meV/atom. This insight removes a perceived bound on the utility of MLPs and paves the way to investigate the physics of previously inaccessible materials with more than ten chemical species.

References in corpus (10)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Comparing molecules and solids across structural and alchemical space
• How van der Waals interactions determine the unique properties of water
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Generating derivative structures: Algorithm and applications
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Metrics for measuring distances in configuration spaces

Cited by in corpus (95)

• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Machine Learning Force Fields
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport
• Physics-inspired structural representations for molecules and materials
• Opportunities and Challenges for Machine Learning in Materials Science
• Machine learning a general purpose interatomic potential for silicon
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Machine learning for electronically excited states of molecules
• Machine-learning interatomic potentials for materials science
• Hierarchical modeling of molecular energies using a deep neural network
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• General-purpose machine-learned potential for 16 elemental metals and their alloys
• A practical guide to machine learning interatomic potentials -- Status and future
• Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science
• Committee neural network potentials control generalization errors and enable active learning
• Atom-Density Representations for Machine Learning
• Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm
• Improving the accuracy of the neuroevolution machine learning potential for multi-component systems
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Quantum-Accurate Spectral Neighbor Analysis Potential Models for Ni-Mo Binary Alloys and FCC Metals
• Deep Potential generation scheme and simulation protocol for the Li10GeP2S12-type superionic conductors
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
• Machine Learning for Predicting Thermal Transport Properties of Solids
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Chemical diversity in molecular orbital energy predictions with kernel ridge regression
• Analytic continuation via domain-knowledge free machine learning
• Machine-learning based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• Simple machine-learned interatomic potentials for complex alloys
• Compositional optimization of hard-magnetic phases with machine-learning models
• Neural networks and kernel ridge regression for excited states dynamics of CH${}_2$NH${}_2^{+}$: From single-state to multi-state representations and multi-property machine learning models
• Efficient Training of ANN Potentials by Including Atomic Forces via Taylor Expansion and Application to Water and a Transition-Metal Oxide
• Machine learning and excited-state molecular dynamics
• Graph Neural Networks Accelerated Molecular Dynamics
• High-Dimensional Potential Energy Surfaces for Molecular Simulations
• Application of machine learning potentials to predict grain boundary properties in fcc elemental metals
• 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
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Convolutional neural networks for atomistic systems
• Lifelong Machine Learning Potentials
• On Machine Learning Force Fields for Metallic Nanoparticles
• Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
• Machine learning potentials for multicomponent systems: The Ti-Al binary system
• Tensor-reduced atomic density representations
• Development of a general-purpose machine-learning interatomic potential for aluminum by the physically-informed neural network method
• Self-learning Hybrid Monte Carlo: A First-principles Approach
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• Simulating lattice thermal conductivity in semiconducting materials using high-dimensional neural network potential
• Reliable machine learning potentials based on artificial neural network for graphene
• Unsupervised learning of atomic environments from simple features
• Transferability of machine learning potentials: Protonated water neural network potential applied to the protonated water hexamer
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Self-learning Monte Carlo method with Behler-Parrinello neural networks
• Atomistic Mechanism Underlying the Si(111)-(7\times7) Surface Reconstruction Revealed by Artificial Neural-network Potential
• AENET-LAMMPS and AENET-TINKER: Interfaces for Accurate and Efficient Molecular Dynamics Simulations with Machine Learning Potentials
• Formula graph self-attention network for representation-domain independent materials discovery
• Machine learning the DFT potential energy surface for inorganic halide perovskite CsPbBr${}_3$
• A Physically-informed Graph-based Order Parameter for the Universal Characterization of Atomic Structures
• TimeSOAP: Tracking high-dimensional fluctuations in complex molecular systems via time-variations of SOAP spectra
• Compact atomic descriptors enable accurate predictions via linear models
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• Constructing and evaluating machine-learned interatomic potentials for Li-based disordered rocksalts
• A transferable artificial neural network model for atomic forces in nanoparticles
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Self-learning hybrid Monte Carlo method for isothermal-isobaric ensemble: Application to liquid silica
• Mean-Field Density Matrix Decompositions
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
• Facilitating {\it ab initio} configurational sampling of multicomponent solids using an on-lattice neural network model and active learning
• Predicting the black hole mass and correlations in X-ray reverberating AGN using neural networks
• Probing the state of hydrogen in $\delta$-AlOOH at mantle conditions with machine learning potential
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• Machine learning at the atomic-scale
• Machine learning for accuracy in density functional approximations
• Machine Learning Framework for Modeling Exciton-Polaritons in Molecular Materials
• Two-dimensional electronic spectroscopy in the condensed phase using equivariant transformer accelerated molecular dynamics simulations
• Fortnet, a software package for training Behler-Parrinello neural networks
• Electronic Descriptors for Supervised Spectroscopic Predictions
• Theoretical analysis of zirconium oxynitride/water interface using neural network potential
• Predictive power of polynomial machine learning potentials for liquid states in 22 elemental systems
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Equivariant Tensor Network Potentials
• Construction of Machine-Learning Interatomic Potential Under Heat Flux Regularization and Its Application to Power Spectrum Analysis for Silver Chalcogenides
• The Homunculus Brain and Categorical Logic
• Artificial neural network molecular mechanics of iron grain boundaries
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations
• Scalable Training of Neural Network Potentials for Complex Interfaces Through Data Augmentation
• Compressing local atomic neighbourhood descriptors
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Systematic global structure search of bismuth-based binary systems under pressure using machine learning potentials