DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model

Abstract

We present the incorporation of a surrogate Gaussian process regression (GPR) atomistic model to greatly accelerate the rate of convergence of classical nudged elastic band (NEB) calculations. In our surrogate model approach, the cost of converging the elastic band no longer scales with the number of moving images on the path. This provides a far more efficient and robust transition state search. In contrast to a conventional NEB calculation, the algorithm presented here eliminates any need for manipulating the number of images to obtain a converged result. This is achieved by inventing a new convergence criteria that exploits the probabilistic nature of the GPR to use uncertainty estimates of all images in combination with the force in the saddle point in the target model potential. In conclusion, our method is an order of magnitude faster in terms of function evaluations than the conventional NEB method with no accuracy loss for the converged energy barrier values.

Authors:
 [1];  [1];  [1];  [1];  [2]
  1. Stanford Univ., Stanford, CA (United States); SLAC National Accelerator Lab., Menlo Park, CA (United States)
  2. SLAC National Accelerator Lab., Menlo Park, CA (United States)
Publication Date:
Research Org.:
SLAC National Accelerator Lab., Menlo Park, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES)
OSTI Identifier:
1526444
Alternate Identifier(s):
OSTI ID: 1507189
Grant/Contract Number:  
AC02-76SF00515
Resource Type:
Accepted Manuscript
Journal Name:
Physical Review Letters
Additional Journal Information:
Journal Volume: 122; Journal Issue: 15; Journal ID: ISSN 0031-9007
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND SUPERFLUIDITY; 97 MATHEMATICS AND COMPUTING

Citation Formats

Garrido Torres, José A., Jennings, Paul C., Hansen, Martin H., Boes, Jacob R., and Bligaard, Thomas. Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model. United States: N. p., 2019. Web. doi:10.1103/physrevlett.122.156001.
Garrido Torres, José A., Jennings, Paul C., Hansen, Martin H., Boes, Jacob R., & Bligaard, Thomas. Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model. United States. https://doi.org/10.1103/physrevlett.122.156001
Garrido Torres, José A., Jennings, Paul C., Hansen, Martin H., Boes, Jacob R., and Bligaard, Thomas. Mon . "Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model". United States. https://doi.org/10.1103/physrevlett.122.156001. https://www.osti.gov/servlets/purl/1526444.
@article{osti_1526444,
title = {Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model},
author = {Garrido Torres, José A. and Jennings, Paul C. and Hansen, Martin H. and Boes, Jacob R. and Bligaard, Thomas},
abstractNote = {We present the incorporation of a surrogate Gaussian process regression (GPR) atomistic model to greatly accelerate the rate of convergence of classical nudged elastic band (NEB) calculations. In our surrogate model approach, the cost of converging the elastic band no longer scales with the number of moving images on the path. This provides a far more efficient and robust transition state search. In contrast to a conventional NEB calculation, the algorithm presented here eliminates any need for manipulating the number of images to obtain a converged result. This is achieved by inventing a new convergence criteria that exploits the probabilistic nature of the GPR to use uncertainty estimates of all images in combination with the force in the saddle point in the target model potential. In conclusion, our method is an order of magnitude faster in terms of function evaluations than the conventional NEB method with no accuracy loss for the converged energy barrier values.},
doi = {10.1103/physrevlett.122.156001},
journal = {Physical Review Letters},
number = 15,
volume = 122,
place = {United States},
year = {Mon Apr 15 00:00:00 EDT 2019},
month = {Mon Apr 15 00:00:00 EDT 2019}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 77 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Effect of the damping function in dispersion corrected density functional theory
journal, March 2011

  • Grimme, Stefan; Ehrlich, Stephan; Goerigk, Lars
  • Journal of Computational Chemistry, Vol. 32, Issue 7
  • DOI: 10.1002/jcc.21759

A doubly nudged elastic band method for finding transition states
journal, February 2004

  • Trygubenko, Semen A.; Wales, David J.
  • The Journal of Chemical Physics, Vol. 120, Issue 5
  • DOI: 10.1063/1.1636455

Generalized Gradient Approximation Made Simple
journal, October 1996

  • Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias
  • Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868
  • DOI: 10.1103/PhysRevLett.77.3865

On the limited memory BFGS method for large scale optimization
journal, August 1989

  • Liu, Dong C.; Nocedal, Jorge
  • Mathematical Programming, Vol. 45, Issue 1-3
  • DOI: 10.1007/BF01589116

Projector augmented-wave method
journal, December 1994


Nudged elastic band method for finding minimum energy paths of transitions
conference, November 2011

  • JÓNsson, Hannes; Mills, Greg; Jacobsen, Karsten W.
  • Proceedings of the International School of Physics, Classical and Quantum Dynamics in Condensed Phase Simulations
  • DOI: 10.1142/9789812839664_0016

Atomic Energies from a Convolutional Neural Network
journal, May 2018

  • Chen, Xin; Jørgensen, Mathias S.; Li, Jun
  • Journal of Chemical Theory and Computation, Vol. 14, Issue 7
  • DOI: 10.1021/acs.jctc.8b00149

Amp: A modular approach to machine learning in atomistic simulations
journal, October 2016


Exploration versus Exploitation in Global Atomistic Structure Optimization
journal, January 2018

  • Jørgensen, Mathias S.; Larsen, Uffe F.; Jacobsen, Karsten W.
  • The Journal of Physical Chemistry A, Vol. 122, Issue 5
  • DOI: 10.1021/acs.jpca.8b00160

Structural Relaxation Made Simple
journal, October 2006


Nudged elastic band calculations accelerated with Gaussian process regression
journal, October 2017

  • Koistinen, Olli-Pekka; Dagbjartsdóttir, Freyja B.; Ásgeirsson, Vilhjálmur
  • The Journal of Chemical Physics, Vol. 147, Issue 15
  • DOI: 10.1063/1.4986787

QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials
journal, September 2009

  • Giannozzi, Paolo; Baroni, Stefano; Bonini, Nicola
  • Journal of Physics: Condensed Matter, Vol. 21, Issue 39, Article No. 395502
  • DOI: 10.1088/0953-8984/21/39/395502

An automated nudged elastic band method
journal, September 2016

  • Kolsbjerg, Esben L.; Groves, Michael N.; Hammer, Bjørk
  • The Journal of Chemical Physics, Vol. 145, Issue 9
  • DOI: 10.1063/1.4961868

The atomic simulation environment—a Python library for working with atoms
journal, June 2017

  • Hjorth Larsen, Ask; Jørgen Mortensen, Jens; Blomqvist, Jakob
  • Journal of Physics: Condensed Matter, Vol. 29, Issue 27
  • DOI: 10.1088/1361-648X/aa680e

The SIESTA method for ab initio order- N materials simulation
journal, March 2002

  • Soler, José M.; Artacho, Emilio; Gale, Julian D.
  • Journal of Physics: Condensed Matter, Vol. 14, Issue 11
  • DOI: 10.1088/0953-8984/14/11/302

Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
journal, October 1996


Searching for Saddle Points by Using the Nudged Elastic Band Method:  An Implementation for Gas-Phase Systems
journal, May 2006

  • González-García, Núria; Pu, Jingzhi; González-Lafont, Àngels
  • Journal of Chemical Theory and Computation, Vol. 2, Issue 4
  • DOI: 10.1021/ct060032y

From ultrasoft pseudopotentials to the projector augmented-wave method
journal, January 1999


First-principles simulation: ideas, illustrations and the CASTEP code
journal, March 2002

  • Segall, M. D.; Lindan, Philip J. D.; Probert, M. J.
  • Journal of Physics: Condensed Matter, Vol. 14, Issue 11
  • DOI: 10.1088/0953-8984/14/11/301

Interatomic interactions in the effective-medium theory
journal, May 1987


Inhomogeneous Electron Gas
journal, November 1964


Electronic structure calculations with GPAW: a real-space implementation of the projector augmented-wave method
journal, June 2010


Paths to which the nudged elastic band converges
journal, February 2011

  • Sheppard, Daniel; Henkelman, Graeme
  • Journal of Computational Chemistry, Vol. 32, Issue 8
  • DOI: 10.1002/jcc.21748

Adaptive nudged elastic band approach for transition state calculation
journal, September 2002

  • Maragakis, P.; Andreev, Stefan A.; Brumer, Yisroel
  • The Journal of Chemical Physics, Vol. 117, Issue 10
  • DOI: 10.1063/1.1495401

Acceleration of saddle-point searches with machine learning
journal, August 2016

  • Peterson, Andrew A.
  • The Journal of Chemical Physics, Vol. 145, Issue 7
  • DOI: 10.1063/1.4960708

A climbing image nudged elastic band method for finding saddle points and minimum energy paths
journal, December 2000

  • Henkelman, Graeme; Uberuaga, Blas P.; Jónsson, Hannes
  • The Journal of Chemical Physics, Vol. 113, Issue 22, p. 9901-9904
  • DOI: 10.1063/1.1329672

A super-linear minimization scheme for the nudged elastic band method
journal, December 2003

  • Chu, Jhih-Wei; Trout, Bernhardt L.; Brooks, Bernard R.
  • The Journal of Chemical Physics, Vol. 119, Issue 24
  • DOI: 10.1063/1.1627754

Improved tangent estimate in the nudged elastic band method for finding minimum energy paths and saddle points
journal, December 2000

  • Henkelman, Graeme; Jónsson, Hannes
  • The Journal of Chemical Physics, Vol. 113, Issue 22
  • DOI: 10.1063/1.1323224

A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu
journal, April 2010

  • Grimme, Stefan; Antony, Jens; Ehrlich, Stephan
  • The Journal of Chemical Physics, Vol. 132, Issue 15
  • DOI: 10.1063/1.3382344

A generalized solid-state nudged elastic band method
journal, February 2012

  • Sheppard, Daniel; Xiao, Penghao; Chemelewski, William
  • The Journal of Chemical Physics, Vol. 136, Issue 7
  • DOI: 10.1063/1.3684549

A growing string method for determining transition states: Comparison to the nudged elastic band and string methods
journal, May 2004

  • Peters, Baron; Heyden, Andreas; Bell, Alexis T.
  • The Journal of Chemical Physics, Vol. 120, Issue 17
  • DOI: 10.1063/1.1691018

Self-Consistent Equations Including Exchange and Correlation Effects
journal, November 1965


Tuning the activities of cuprous oxide nanostructures via the oxide-metal interaction
journal, May 2020


Reducing Dzyaloshinskii-Moriya interaction and field-free spin-orbit torque switching in synthetic antiferromagnets
journal, May 2021


Electronic structure of AlFeN films exhibiting crystallographic orientation change from c- to a-axis with Fe concentrations and annealing effect
journal, February 2020


Nudged elastic band calculations accelerated with Gaussian process regression
text, January 2017


A Doubly Nudged Elastic Band Method for Finding Transition States
text, January 2004


Works referencing / citing this record:

Catalysis-Hub.org, an open electronic structure database for surface reactions
journal, May 2019


Predicting metal–metal interactions. I. The influence of strain on nanoparticle and metal adlayer stabilities
journal, March 2020

  • Streibel, Verena; Choksi, Tej S.; Abild-Pedersen, Frank
  • The Journal of Chemical Physics, Vol. 152, Issue 9
  • DOI: 10.1063/1.5130566

Constructing convex energy landscapes for atomistic structure optimization
journal, December 2019


A local Bayesian optimizer for atomic structures
text, January 2018