Global optimization of atomic structures with gradient-enhanced Gaussian process regression

Abstract

Determination of atomic structures is a key challenge in the fields of computational physics and materials science, as a large variety of mechanical, chemical, electronic, and optical properties depend sensitively on structure. Here, we present a global optimization scheme where energy and force information from density functional theory (DFT) calculations is transferred to a probabilistic surrogate model to estimate both the potential energy surface (PES) and the associated uncertainties. The local minima in the surrogate PES are then used to guide the search for the global minimum in the DFT potential. We find that adding the gradients in most cases improves the efficiency of the search significantly. The method is applied to global optimization of [Ta${}_2$O${}_5$]${}_x$ clusters with $x=1,2,3$, and the surface structure of oxidized ZrN.

References in corpus (20)

• 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
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Ab initio Random Structure Searching
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Machine-learning based interatomic potential for amorphous carbon
• FCHL revisited: faster and more accurate quantum machine learning
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Efficient global structure optimization with a machine learned surrogate model
• Nudged elastic band calculations accelerated with Gaussian process regression
• Efficient Bayesian Inference of Atomistic Structure in Complex Functional Materials
• Gaussian Process Regression for Transition State Search
• A local Bayesian optimizer for atomic structures
• An assessment of the structural resolution of various fingerprints commonly used in machine learning
• Prediction of New Ground State Crystal Structure of Ta2O5
• Atomistic Structure Learning Algorithm with surrogate energy model relaxation
• Ab initio simulation of $\mathrm{T}{\mathrm{a}}_2{\mathrm{O}}_5$: A high symmetry ground state phase with application to interface calculation
• SGO: An ultrafast engine for ab initio atomic structure global optimization by differential evolution

Cited by in corpus (16)

• GPAW: An open Python package for electronic-structure calculations
• Global optimization of atomistic structure enhanced by machine learning
• Developments and Further Applications of Ephemeral Data Derived Potentials
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Atomistic structure search using local surrogate mode
• Atomic structure optimization with machine-learning enabled interpolation between chemical elements
• Donors, Acceptors, and a Bit of Aromatics: Electronic Interactions of Molecular Adsorbates on hBN and MoS${}_2$ Monolayers
• Accurate Memory Kernel Extraction from Discretized Time Series Data
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• Generating candidates in global optimization algorithms using complementary energy landscapes
• Machine-learning enabled optimization of atomic structures using atoms with fractional existence
• Efficient ensemble uncertainty estimation in Gaussian Processes Regression
• RAFFLE: Active learning accelerated interface structure prediction
• Atomistic Global Optimization X: A Python package for optimization of atomistic structures
• Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence
• Atoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering