Nudged elastic band calculations accelerated with Gaussian process regression

Abstract

Minimum energy paths for transitions such as atomic and/or spin rearrangements in thermalized systems are the transition paths of largest statistical weight. Such paths are frequently calculated using the nudged elastic band method, where an initial path is iteratively shifted to the nearest minimum energy path. The computational effort can be large, especially when ab initio or electron density functional calculations are used to evaluate the energy and atomic forces. Here, we show how the number of such evaluations can be reduced by an order of magnitude using a Gaussian process regression approach where an approximate energy surface is generated and refined in each iteration. When the goal is to evaluate the transition rate within harmonic transition state theory, the evaluation of the Hessian matrix at the initial and final state minima can be carried out beforehand and used as input in the minimum energy path calculation, thereby improving stability and reducing the number of iterations needed for convergence. A Gaussian process model also provides an uncertainty estimate for the approximate energy surface, and this can be used to focus the calculations on the lesser-known part of the path, thereby reducing the number of needed energy and force evaluations to a half in the present calculations. The methodology is illustrated using the two-dimensional Müller-Brown potential surface and performance assessed on an established benchmark involving 13 rearrangement transitions of a heptamer island on a solid surface.

References in corpus (6)

• Reversible Work Transiton State Theory: Application to Dissociative Adsorption of Hydrogen
• Improved initial guess for minimum energy path calculations
• Global transition path search for dislocation formation in Ge on Si(001)
• Method for finding mechanism and activation energy of magnetic transitions, applied to skyrmion and antivortex annihilation
• Calculations of magnetic states and minimum energy paths of transitions using a noncollinear extension of the Alexander-Anderson model and a magnetic force theorem
• Speeding up the binary Gaussian process classification

Cited by in corpus (28)

• GPAW: An open Python package for electronic-structure calculations
• Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model
• Perspective on integrating machine learning into computational chemistry and materials science
• Efficient global structure optimization with a machine learned surrogate model
• Gaussian Process Regression for Geometry Optimization
• Predicting the Activity and Selectivity of Bimetallic Metal Catalysts for Ethanol Reforming using Machine Learning
• Gaussian Process Regression for Transition State Search
• A local Bayesian optimizer for atomic structures
• Global optimization of atomistic structure enhanced by machine learning
• Scaled and Dynamic Optimizations of Nudged Elastic Bands
• Machine-learning accelerated geometry optimization in molecular simulation
• Machine learning enhanced global optimization by clustering local environments to enable bundled atomic energies
• Global optimization of atomic structures with gradient-enhanced Gaussian process regression
• Atomistic Structure Learning Algorithm with surrogate energy model relaxation
• Detecting stable adsorbates of (1S)-camphor on Cu(111) with Bayesian optimization
• Potential energy surface interpolation with neural networks for instanton rate calculations
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Atomic structure optimization with machine-learning enabled interpolation between chemical elements
• Machine Learning with bond information for local structure optimizations in surface science
• Electrochemical oxidation of CO on Cu single crystals under alkaline conditions
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• Efficient Implementation of Gaussian Process Regression Accelerated Saddle Point Searches with Application to Molecular Reactions
• GPR_calculator: An On-the-Fly Surrogate Model to Accelerate Massive Nudged Elastic Band Calculations
• Symmetry- and Gradient-enhanced Gaussian Process Regression for the Active Learning of Potential Energy Surfaces in Porous Materials
• The Ridge Integration Method and its Application to Molecular Sieving, Demonstrated for Gas Purification via Graphdiyne Membranes
• Enhancing ab initio diffusion calculations in materials through Gaussian process regression
• Estimating Reaction Barriers with Deep Reinforcement Learning
• Direct Deoxygenation of Phenol over Fe-based Bimetallic Surfaces using On-the-fly Surrogate Models