Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Machine learning with bond information for local structure optimizations in surface science

Journal Article · · Journal of Chemical Physics
DOI:https://doi.org/10.1063/5.0033778· OSTI ID:1768006
 [1];  [1];  [2];  [3];  [1]
  1. Technical Univ. of Denmark, Lyngby (Denmark)
  2. Stanford Univ., CA (United States). SUNCAT Center for Interface Science and Catalysis; SLAC National Accelerator Lab., Menlo Park, CA (United States); Columbia Univ., New York, NY (United States). Columbia Electrochemical Energy Center
  3. Stanford Univ., CA (United States). SUNCAT Center for Interface Science and Catalysis; Technical Univ. of Denmark, Lyngby (Denmark)
+ Show Author Affiliations
Local optimization of adsorption systems inherently involves different scales: within the substrate, within the molecule, and between the molecule and the substrate. In this work, we show how the explicit modeling of different characteristics of the bonds in these systems improves the performance of machine learning methods for optimization. Furthermore, we introduce an anisotropic kernel in the Gaussian process regression framework that guides the search for the local minimum, and we show its overall good performance across different types of atomic systems. The method shows a speed-up of up to a factor of two compared with the fastest standard optimization methods on adsorption systems. Additionally, we show that a limited memory approach is not only beneficial in terms of overall computational resources but can also result in a further reduction of energy and force calculations.
Research Organization:
SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)
Sponsoring Organization:
USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES); VILLUM Fonden
Grant/Contract Number:
AC02-76SF00515
OSTI ID:
1768006
Alternate ID(s):
OSTI ID: 1970570
Journal Information:
Journal of Chemical Physics, Journal Name: Journal of Chemical Physics Journal Issue: 23 Vol. 153; ISSN 0021-9606
Publisher:
American Institute of Physics (AIP)Copyright Statement
Country of Publication:
United States
Language:
English

References (52)

Gaussian Process Regression for Transition State Search journal October 2018
Assessment of Gaussian-2 and density functional theories for the computation of enthalpies of formation journal January 1997
Electronic structure calculations with GPAW: a real-space implementation of the projector augmented-wave method journal June 2010
Atomistic structure learning algorithm with surrogate energy model relaxation journal August 2020
Data-Driven Learning of Total and Local Energies in Elemental Boron journal April 2018
Machine learning of accurate energy-conserving molecular force fields text January 2017
Research data supporting "Machine learning based interatomic potential for amorphous carbon" dataset January 2017
Bayesian Optimization with Gradients text January 2017
Efficient Cysteine Conformer Search with Bayesian Optimization preprint January 2020
On the role of gradients for machine learning of molecular energies and forces preprint January 2020
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space text January 2015
The potential of atomistic simulations and the knowledgebase of interatomic models journal July 2011
On the use of a Hessian model function in molecular geometry optimizations journal July 1995
Active learning of linearly parametrized interatomic potentials journal December 2017
Accelerating high-throughput searches for new alloys with active learning of interatomic potentials journal January 2019
DScribe: Library of descriptors for machine learning in materials science journal February 2020
Hessian Matrix Update Scheme for Transition State Search Based on Gaussian Process Regression journal July 2020
Nudged Elastic Band Calculations Accelerated with Gaussian Process Regression Based on Inverse Interatomic Distances journal October 2019
Exploration versus Exploitation in Global Atomistic Structure Optimization journal January 2018
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space journal June 2015
Machine learning hydrogen adsorption on nanoclusters through structural descriptors journal July 2018
Bayesian inference of atomistic structure in functional materials journal March 2019
Preconditioners for the geometry optimisation and saddle point search of molecular systems journal September 2018
Covalent radii revisited journal January 2008
A cartography of the van der Waals territories journal January 2013
Quasi-Newton parallel geometry optimization methods journal July 2010
A universal preconditioner for simulating condensed phase materials journal April 2016
Acceleration of saddle-point searches with machine learning journal August 2016
Nudged elastic band calculations accelerated with Gaussian process regression journal October 2017
Gaussian process regression to accelerate geometry optimizations relying on numerical differentiation journal June 2018
Gaussian process regression for geometry optimization journal March 2018
A preconditioning scheme for minimum energy path finding methods journal March 2019
Geometry optimization using Gaussian process regression in internal coordinate systems journal February 2020
The atomic simulation environment—a Python library for working with atoms journal June 2017
On the role of gradients for machine learning of molecular energies and forces journal October 2020
Inhomogeneous Electron Gas journal November 1964
Self-Consistent Equations Including Exchange and Correlation Effects journal November 1965
Local Bayesian optimizer for atomic structures journal September 2019
From ultrasoft pseudopotentials to the projector augmented-wave method journal January 1999
Improved adsorption energetics within density-functional theory using revised Perdew-Burke-Ernzerhof functionals journal March 1999
Publisher’s Note: On representing chemical environments [Phys. Rev. B 87 , 184115 (2013)] journal June 2013
Machine learning based interatomic potential for amorphous carbon journal March 2017
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons journal April 2010
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning journal January 2012
Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model journal April 2019
Efficient Global Structure Optimization with a Machine-Learned Surrogate Model journal February 2020
Structural Relaxation Made Simple journal October 2006
Crystal structure prediction accelerated by Bayesian optimization journal January 2018
Machine learning of accurate energy-conserving molecular force fields journal May 2017
A Limited Memory Algorithm for Bound Constrained Optimization journal September 1995
Bayesian Inference of Atomistic Structure in Functional Materials dataset January 2019
Bayesian Inference of Atomistic Structure in Functional Materials dataset January 2019

Cited By (1)

Perspective on integrating machine learning into computational chemistry and materials science journal June 2021

Similar Records

Modeling plasticity-mediated void growth at the single crystal scale: A physics-informed machine learning approach
Journal Article · Mon Sep 09 20:00:00 EDT 2024 · Mechanics of Materials · OSTI ID:2440686
Machine Learning-Guided Approach for Studying Solvation Environments
Journal Article · Thu Dec 05 19:00:00 EST 2019 · Journal of Chemical Theory and Computation · OSTI ID:1770792

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
Gaussian processes
adsorption
atomic structure
density functional theory
machine learning
optimization algorithms
potential energy surfaces
surface science