Data-driven learning of total and local energies in elemental boron

Abstract

The allotropes of boron continue to challenge structural elucidation and solid-state theory. Here we use machine learning combined with random structure searching (RSS) algorithms to systematically construct an interatomic potential for boron. Starting from ensembles of randomized atomic configurations, we use alternating single-point quantum-mechanical energy and force computations, Gaussian approximation potential (GAP) fitting, and GAP-driven RSS to iteratively generate a representation of the element's potential-energy surface. Beyond the total energies of the very different boron allotropes, our model readily provides atom-resolved, local energies and thus deepened insight into the frustrated $\beta$-rhombohedral boron structure. Our results open the door for the efficient and automated generation of GAPs and other machine-learning-based interatomic potentials, and suggest their usefulness as a tool for materials discovery.

References in corpus (5)

• High-pressure phases of silane
• Active learning of linearly parametrized interatomic potentials
• Machine-learning based interatomic potential for amorphous carbon
• Symmetry-broken crystal structure of elemental boron at low temperature
• Stratified construction of neural network based interatomic models for multicomponent materials

Cited by in corpus (70)

• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Physics-inspired structural representations for molecules and materials
• Machine learning a general purpose interatomic potential for silicon
• Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning
• Machine learning for electronically excited states of molecules
• Machine-learning interatomic potentials for materials science
• An Accurate and Transferable Machine Learning Potential for Carbon
• De novo exploration and self-guided learning of potential-energy surfaces
• Towards high-throughput superconductor discovery via machine learning
• Committee neural network potentials control generalization errors and enable active learning
• Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
• Efficient global structure optimization with a machine learned surrogate model
• Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures
• PyXtal: a Python Library for Crystal Structure Generation and Symmetry Analysis
• Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground
• How to validate machine-learned interatomic potentials
• Crystal Diffusion Variational Autoencoder for Periodic Material Generation
• Automated discovery of a robust interatomic potential for aluminum
• Gaussian approximation potentials for body-centered-cubic transition metals
• Tuning Chemical Precompression: Theoretical Design and Crystal Chemistry of Novel Hydrides in the Quest for Warm and Light Superconductivity at Ambient Pressures
• Ephemeral data derived potentials for random structure search
• Global optimization of atomistic structure enhanced by machine learning
• Machine-learning based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies
• Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks
• Equation of state of fluid methane from first principles with machine learning potentials
• Application of machine learning potentials to predict grain boundary properties in fcc elemental metals
• MAISE: Construction of neural network interatomic models and evolutionary structure optimization
• Quantifying Chemical Structure and Atomic Energies in Amorphous Silicon Networks
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Automated Calculation of Thermal Rate Coefficients using Ring Polymer Molecular Dynamics and Machine-Learning Interatomic Potentials with Active Learning
• Machine learning enhanced global optimization by clustering local environments to enable bundled atomic energies
• Enhancing Crystal Structure Prediction by decomposition methods based on graph theory
• Developments and Further Applications of Ephemeral Data Derived Potentials
• Atomistic structure learning
• Machine learning potentials for multicomponent systems: The Ti-Al binary system
• Training machine-learning potentials for crystal structure prediction using disordered structures
• Development of a general-purpose machine-learning interatomic potential for aluminum by the physically-informed neural network method
• Accelerated identification of equilibrium structures of multicomponent inorganic crystals using machine learning potentials
• PyXtal FF: a Python Library for Automated Force Field Generation
• Atomistic Structure Learning Algorithm with surrogate energy model relaxation
• Robustness of Local Predictions in Atomistic Machine Learning Models
• Materials under high pressure: A chemical perspective
• Development of a physically-informed neural network interatomic potential for tantalum
• Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials
• Multi-Fidelity Machine Learning for Excited State Energies of Molecules
• Hyperspatial optimisation of structures
• Exploring the configurational space of amorphous graphene with machine-learned atomic energies
• Prediction of stable Li-Sn compounds: boosting ab initio searches with neural network potentials
• Accelerating Cathode Material Discovery through Ab Initio Random Structure Searching
• Machine Learning with bond information for local structure optimizations in surface science
• Machine Learned Interatomic Potentials for Ternary Carbides trained on the AFLOW Database
• Quantum chemical roots of machine-learning molecular similarity descriptors
• Benchmarking van der Waals-treated DFT: The case of hexagonal boron nitride and graphene on Ir(111)
• Neural Networks Potential from the Bispectrum Component: A Case Study on Crystalline Silicon
• Machine-learning of atomic-scale properties based on physical principles
• Prediction rigidities for data-driven chemistry
• Machine learning potentials for complex aqueous systems made simple
• Structural Motifs and Bonding in Two Families of Boron Structures Predicted at Megabar Pressures
• Machine learning at the atomic-scale
• Fast proper orthogonal descriptors for many-body interatomic potentials
• Generative Adversarial Networks for Crystal Structure Prediction
• Physics-guided descriptors for prediction of structural polymorphs
• Investigating 3D Atomic Environments for Enhanced QSAR
• Entropy-driven electron density and effective model Hamiltonian for boron systems
• Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
• Active Δ-learning with universal potentials for global structure optimization
• Improving accuracy of interatomic potentials: more physics or more data? A case study of silica
• Systematic global structure search of bismuth-based binary systems under pressure using machine learning potentials