Global optimization of atomistic structure enhanced by machine learning

Abstract

Global Optimization with First-principles Energy Expressions (GOFEE) is an efficient method for identifying low energy structures in computationally expensive energy landscapes such as the ones described by density functional theory (DFT), van der Waals-enabled DFT, or even methods beyond DFT. GOFEE relies on a machine learned surrogate model of energies and forces, trained on-the-fly, to explore configuration space, eliminating the need for expensive relaxations of all candidate structures using first-principles methods. In this paper we elaborate on the importance of the use of a Gaussian kernel with two length scales in the Gaussian Process Regression (GPR) surrogate model. We further explore the role of the use in GOFEE of the lower confidence bound for relaxation and selection of candidate structures. In addition, we present two improvements to the method: 1) the population generation now relies on a clustering of all low-energy structures evaluated with DFT, with the lowest energy member of each cluster making up the population. 2) the very final relaxations in well-sampled basins of the energy landscape, the final exploitation steps, are now performed as continued relaxation paths within the first-principles method, to allow for arbitrarily fine relaxations of the best structures, independently of the predictive resolution of the surrogate model. The versatility of the GOFEE method is demonstrated by applying it to identify the low-energy structures of gas-phase fullerene-type 24-atom carbon clusters and of dome-shaped 18-atom carbon clusters supported on Ir(111).

References in corpus (33)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms
• CALYPSO: a method for crystal structure prediction
• Crystal Structure Prediction via Particle Swarm Optimization
• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• Grains and grain boundaries in highly crystalline monolayer molybdenum disulfide
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Ab initio Random Structure Searching
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Less is more: sampling chemical space with active learning
• Active learning of linearly parametrized interatomic potentials
• On-the-fly machine learning force field generation: Application to melting points
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Data-driven learning of total and local energies in elemental boron
• Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model
• Committee neural network potentials control generalization errors and enable active learning
• Efficient global structure optimization with a machine learned surrogate model
• Machine learning of molecular properties: locality and active learning
• Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
• Gaussian Process Regression for Geometry Optimization
• Nudged elastic band calculations accelerated with Gaussian process regression
• Efficient Bayesian Inference of Atomistic Structure in Complex Functional Materials
• Accelerating CALYPSO Structure Prediction by Data-driven Learning of Potential Energy Surface
• Atomistic Mechanisms of Nonlinear Graphene Growth on Ir Surface
• A local Bayesian optimizer for atomic structures
• Steps on Rutile TiO2(110): Active Sites for Water and Methanol Dissociation
• Automated Calculation of Thermal Rate Coefficients using Ring Polymer Molecular Dynamics and Machine-Learning Interatomic Potentials with Active Learning
• Global optimization of atomic structures with gradient-enhanced Gaussian process regression
• Structure of Si(114) determined by global optimization methods
• What Is Armchair-Zigzag Grain Boundary Structure in Graphene?
• Atomistic Structure Learning Algorithm with surrogate energy model relaxation
• Atomic structure optimization with machine-learning enabled interpolation between chemical elements

Cited by in corpus (17)

• Updates to the DScribe Library: New Descriptors and Derivatives
• Machine-learning-accelerated simulations to enable automatic surface reconstruction
• Machine learning based approach for solving atomic structures of nanomaterials combining pair distribution functions with density functional theory
• Atomistic structure search using local surrogate mode
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• Augmentation of Universal Potentials for Broad Applications
• Generating candidates in global optimization algorithms using complementary energy landscapes
• Prediction of surface reconstructions using MAGUS
• Cascading symmetry constraint during machine learning-enabled structural search for sulfur induced Cu(111)-$(\sqrt{43}\times \sqrt{43})$ surface reconstruction
• Efficient Implementation of Gaussian Process Regression Accelerated Saddle Point Searches with Application to Molecular Reactions
• Molecular Hessian matrices from a machine learning random forest regression algorithm
• Accelerating structure search using atomistic graph-based classifiers
• Machine-Learning Surrogate Model for Accelerating the Search of Stable Ternary Alloys
• Water Nucleation via Transient Bonds to Oxygen Functionalized Graphite
• RAFFLE: Active learning accelerated interface structure prediction
• Active Δ-learning with universal potentials for global structure optimization
• Atomistic Global Optimization X: A Python package for optimization of atomistic structures