Atomistic structure search using local surrogate mode

Abstract

We describe a local surrogate model for use in conjunction with global structure search methods. The model follows the Gaussian approximation potential (GAP) formalism and is based on a the smooth overlap of atomic positions descriptor with sparsification in terms of a reduced number of local environments using mini-batch $k$-means. The model is implemented in the Atomistic Global Optimization X framework and used as a partial replacement of the local relaxations in basin hopping structure search. The approach is shown to be robust for a wide range of atomistic system including molecules, nano-particles, surface supported clusters and surface thin films. The benefits in a structure search context of a local surrogate model are demonstrated. This includes the ability to transfer learning from smaller systems as well as the possibility to perform concurrent multi-stoichiometry searches.

12 pages, 11 figures

References in corpus (11)

• Machine Learning Unifies the Modelling of Materials and Molecules
• On-the-fly machine learning force field generation: Application to melting points
• Machine-learning based interatomic potential for amorphous carbon
• Physics-inspired structural representations for molecules and materials
• Inverse design of 3d molecular structures with conditional generative neural networks
• Experimental and theoretical study of oxygen adsorption structures on Ag(111)
• Global optimization of atomistic structure enhanced by machine learning
• Machine-learning accelerated geometry optimization in molecular simulation
• Global optimization of atomic structures with gradient-enhanced Gaussian process regression
• Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
• Atomistic Structure Learning Algorithm with surrogate energy model relaxation

Cited by in corpus (11)

• Machine-learning-accelerated simulations to enable automatic surface reconstruction
• Generative diffusion model for surface structure discovery
• Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• Augmentation of Universal Potentials for Broad Applications
• Surface Phase Diagrams from Nested Sampling
• Cascading symmetry constraint during machine learning-enabled structural search for sulfur induced Cu(111)-$(\sqrt{43}\times \sqrt{43})$ surface reconstruction
• Efficient ensemble uncertainty estimation in Gaussian Processes Regression
• Accelerating structure search using atomistic graph-based classifiers
• Anharmonic infrared spectra of cationic pyrene and superhydrogenated derivatives
• Active Δ-learning with universal potentials for global structure optimization