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 (2)

• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• How van der Waals interactions determine the unique properties of water

Cited by in corpus (16)

• Opportunities and Challenges for Machine Learning in Materials Science
• 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
• Graph Neural Networks Accelerated Molecular Dynamics
• 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
• Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
• 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
• Self-learning hybrid Monte Carlo method for isothermal-isobaric ensemble: Application to liquid silica
• Predicting the black hole mass and correlations in X-ray reverberating AGN using neural networks
• Machine learning at the atomic-scale
• 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
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems