Genetic algorithms for computational materials discovery accelerated by machine learning

Jennings, Paul C.; Lysgaard, Steen; Hummelshøj, Jens Strabo; Vegge, Tejs; Bligaard, Thomas

doi:10.1038/s41524-019-0181-4

Title: Genetic algorithms for computational materials discovery accelerated by machine learning

Journal Article · Wed Apr 10 00:00:00 EDT 2019 · npj Computational Materials

DOI:https://doi.org/10.1038/s41524-019-0181-4· OSTI ID:1511649

Jennings, Paul C. ^[1];

^[2]; Hummelshøj, Jens Strabo ^[3];

^[2]; Bligaard, Thomas ^[1]

Stanford Univ., Stanford, CA (United States); SLAC National Accelerator Lab., Menlo Park, CA (United States)
Technical Univ. of Denmark, Lyngby (Denmark)
Toyota Research Institute, Los Altos, CA (United States)

Materials discovery is increasingly being impelled by machine learning methods that rely on pre-existing datasets. Where datasets are lacking, unbiased data generation can be achieved with genetic algorithms. Here a machine learning model is trained on-the-fly as a computationally inexpensive energy predictor before analyzing how to augment convergence in genetic algorithm-based approaches by using the model as a surrogate. This leads to a machine learning accelerated genetic algorithm combining robust qualities of the genetic algorithm with rapid machine learning. The approach is used to search for stable, compositionally variant, geometrically similar nanoparticle alloys to illustrate its capability for accelerated materials discovery, e.g., nanoalloy catalysts. The machine learning accelerated approach, in this case, yields a 50-fold reduction in the number of required energy calculations compared to a traditional “brute force” genetic algorithm. This makes searching through the space of all homotops and compositions of a binary alloy particle in a given structure feasible, using density functional theory calculations.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC02-76SF0051

OSTI ID:: 1511649

Journal Information:: npj Computational Materials, Vol. 5, Issue 1; ISSN 2057-3960

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United States

Language:: English

Citation Metrics:

Cited by: 103 works

Citation information provided by
Web of Science

References (50)

Structural motifs, mixing, and segregation effects in 38-atom binary clusters Paz-Borbón, Lauro Oliver; Johnston, Roy L.; Barcaro, Giovanni The Journal of Chemical Physics, Vol. 128, Issue 13 https://doi.org/10.1063/1.2897435	journal	April 2008
Genetic Algorithm Procreation Operators for Alloy Nanoparticle Catalysts Lysgaard, Steen; Landis, David D.; Bligaard, Thomas Topics in Catalysis, Vol. 57, Issue 1-4 https://doi.org/10.1007/s11244-013-0160-9	journal	October 2013
Global optimization of clusters using electronic structure methods Heiles, Sven; Johnston, Roy L. International Journal of Quantum Chemistry, Vol. 113, Issue 18 https://doi.org/10.1002/qua.24462	journal	May 2013
Lattice relaxation at a metal surface Gupta, Raju P. Physical Review B, Vol. 23, Issue 12 https://doi.org/10.1103/PhysRevB.23.6265	journal	June 1981
Amp: A modular approach to machine learning in atomistic simulations Khorshidi, Alireza; Peterson, Andrew A. Computer Physics Communications, Vol. 207 https://doi.org/10.1016/j.cpc.2016.05.010	journal	October 2016
Localized atomic basis set in the projector augmented wave method Larsen, A. H.; Vanin, M.; Mortensen, J. J. Physical Review B, Vol. 80, Issue 19 https://doi.org/10.1103/PhysRevB.80.195112	journal	November 2009
Influence of the composition of core–shell Au–Pt nanoparticle electrocatalysts for the oxygen reduction reaction Li, Xiaowei; Liu, Juanying; He, Wei Journal of Colloid and Interface Science, Vol. 344, Issue 1 https://doi.org/10.1016/j.jcis.2009.12.019	journal	April 2010
Structural Relaxation Made Simple Bitzek, Erik; Koskinen, Pekka; Gähler, Franz Physical Review Letters, Vol. 97, Issue 17 https://doi.org/10.1103/PhysRevLett.97.170201	journal	October 2006
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias Journal of Chemical Theory and Computation, Vol. 11, Issue 5 https://doi.org/10.1021/acs.jctc.5b00099	journal	April 2015
Exploration versus Exploitation in Global Atomistic Structure Optimization Jørgensen, Mathias S.; Larsen, Uffe F.; Jacobsen, Karsten W. The Journal of Physical Chemistry A, Vol. 122, Issue 5 https://doi.org/10.1021/acs.jpca.8b00160	journal	January 2018
Dopant-induced 2D–3D transition in small Au-containing clusters: DFT-global optimisation of 8-atom Au–Ag nanoalloys Heiles, Sven; Logsdail, Andrew J.; Schäfer, Rolf Nanoscale, Vol. 4, Issue 4 https://doi.org/10.1039/C1NR11053E	journal	January 2012
Combined Electronic Structure and Evolutionary Search Approach to Materials Design Jóhannesson, G. H.; Bligaard, T.; Ruban, A. V. Physical Review Letters, Vol. 88, Issue 25 https://doi.org/10.1103/PhysRevLett.88.255506	journal	June 2002
Interplay of Electronic Structure and Atomic Mobility in Nanoalloys of Au and Pt Leppert, L.; Albuquerque, R. Q.; Foster, A. S. The Journal of Physical Chemistry C, Vol. 117, Issue 33 https://doi.org/10.1021/jp404341v	journal	August 2013
The atomic simulation environment—a Python library for working with atoms Hjorth Larsen, Ask; Jørgen Mortensen, Jens; Blomqvist, Jakob Journal of Physics: Condensed Matter, Vol. 29, Issue 27 https://doi.org/10.1088/1361-648X/aa680e	journal	June 2017
Fitness sharing and niching methods revisited Sareni, B.; Krahenbuhl, L. IEEE Transactions on Evolutionary Computation, Vol. 2, Issue 3 https://doi.org/10.1109/4235.735432	journal	January 1998
Structures and Stabilities of Platinum–Gold Nanoclusters Logsdail, Andrew; Paz-Borbón, Lauro Oliver; Johnston, Roy L. Journal of Computational and Theoretical Nanoscience, Vol. 6, Issue 4 https://doi.org/10.1166/jctn.2009.1118	journal	April 2009
Controlling Structural Transitions in AuAg Nanoparticles through Precise Compositional Design Gould, Anna L.; Rossi, Kevin; Catlow, C. Richard A. The Journal of Physical Chemistry Letters, Vol. 7, Issue 21 https://doi.org/10.1021/acs.jpclett.6b02181	journal	October 2016
Interatomic interactions in the effective-medium theory Jacobsen, K. W.; Norskov, J. K.; Puska, M. J. Physical Review B, Vol. 35, Issue 14 https://doi.org/10.1103/PhysRevB.35.7423	journal	May 1987
Improved adsorption energetics within density-functional theory using revised Perdew-Burke-Ernzerhof functionals Hammer, B.; Hansen, L. B.; Nørskov, J. K. Physical Review B, Vol. 59, Issue 11 https://doi.org/10.1103/PhysRevB.59.7413	journal	March 1999
Steps on rutile TiO $_{2}$ (110): Active sites for water and methanol dissociation Martinez, Umberto; Vilhelmsen, Lasse B.; Kristoffersen, Henrik H. Physical Review B, Vol. 84, Issue 20 https://doi.org/10.1103/PhysRevB.84.205434	journal	November 2011
Octahedral PtNi Nanoparticle Catalysts Exceptional Oxygen Reduction Activity by Tuning the Alloy Particle Surface Composition Cui, Chunhua; Gan, Lin; Li, Hui-Hui Nano Letters, Vol. 12, Issue 11, p. 5885-5889 https://doi.org/10.1021/nl3032795	journal	October 2012
Competition between structural motifs in gold–platinum nanoalloys Bochicchio, D.; Negro, F.; Ferrando, R. Computational and Theoretical Chemistry, Vol. 1021 https://doi.org/10.1016/j.comptc.2013.07.017	journal	October 2013
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces Behler, Jörg; Parrinello, Michele Physical Review Letters, Vol. 98, Issue 14 https://doi.org/10.1103/PhysRevLett.98.146401	journal	April 2007
Symmetry breaking and morphological instabilities in core-shell metallic nanoparticles Ferrando, Riccardo Journal of Physics: Condensed Matter, Vol. 27, Issue 1 https://doi.org/10.1088/0953-8984/27/1/013003	journal	December 2014
Electronic structure calculations with GPAW: a real-space implementation of the projector augmented-wave method Enkovaara, J.; Rostgaard, C.; Mortensen, J. J. Journal of Physics: Condensed Matter, Vol. 22, Issue 25 https://doi.org/10.1088/0953-8984/22/25/253202	journal	June 2010
Optical absorption spectra and structures of Ag 6 + and Ag 8 + Shayeghi, A.; Götz, D. A.; Johnston, R. L. The European Physical Journal D, Vol. 69, Issue 6 https://doi.org/10.1140/epjd/e2015-60188-2	journal	June 2015
Molecular Geometry Optimization with a Genetic Algorithm Deaven, D. M.; Ho, K. M. Physical Review Letters, Vol. 75, Issue 2 https://doi.org/10.1103/PhysRevLett.75.288	journal	July 1995
Potential energy functions for atomic solids Murrell, John N.; Mottram, Rachel E. Molecular Physics, Vol. 69, Issue 3 https://doi.org/10.1080/00268979000100411	journal	February 1990
A DFT-based genetic algorithm search for AuCu nanoalloy electrocatalysts for CO ₂ reduction Lysgaard, Steen; Mýrdal, Jón S. G.; Hansen, Heine A. Physical Chemistry Chemical Physics, Vol. 17, Issue 42 https://doi.org/10.1039/C5CP00298B	journal	January 2015
Long-range Finnis–Sinclair potentials Sutton, A. P.; Chen, J. Philosophical Magazine Letters, Vol. 61, Issue 3 https://doi.org/10.1080/09500839008206493	journal	March 1990
Neural-Network-Biased Genetic Algorithms for Materials Design: Evolutionary Algorithms That Learn Patra, Tarak K.; Meenakshisundaram, Venkatesh; Hung, Jui-Hsiang ACS Combinatorial Science, Vol. 19, Issue 2 https://doi.org/10.1021/acscombsci.6b00136	journal	January 2017
Optimizing core-shell nanoparticle catalysts with a genetic algorithm Froemming, Nathan S.; Henkelman, Graeme The Journal of Chemical Physics, Vol. 131, Issue 23 https://doi.org/10.1063/1.3272274	journal	December 2009
Structures of small Ti- and V-doped Pt clusters: A GA-DFT study Jennings, P. C.; Johnston, R. L. Computational and Theoretical Chemistry, Vol. 1021 https://doi.org/10.1016/j.comptc.2013.06.033	journal	October 2013
An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2 Artrith, Nongnuch; Urban, Alexander Computational Materials Science, Vol. 114 https://doi.org/10.1016/j.commatsci.2015.11.047	journal	March 2016
An Introduction to Support Vector Machines and Other Kernel-based Learning Methods Cristianini, Nello; Shawe-Taylor, John https://doi.org/10.1017/CBO9780511801389	book	January 2013
A density functional global optimisation study of neutral 8-atom Cu-Ag and Cu-Au clusters Heard, Christopher J.; Johnston, Roy L. The European Physical Journal D, Vol. 67, Issue 2 https://doi.org/10.1140/epjd/e2012-30601-7	journal	February 2013
Magic Numbers for Sphere Packings: Experimental Verification in Free Xenon Clusters Echt, O.; Sattler, K.; Recknagel, E. Physical Review Letters, Vol. 47, Issue 16 https://doi.org/10.1103/PhysRevLett.47.1121	journal	October 1981
Nanoalloys: From Theory to Applications of Alloy Clusters and Nanoparticles Ferrando, Riccardo; Jellinek, Julius; Johnston, Roy L. Chemical Reviews, Vol. 108, Issue 3, p. 845-910 https://doi.org/10.1021/cr040090g	journal	March 2008
Amorphization Mechanism of Icosahedral Metal Nanoclusters Aprà, E.; Baletto, F.; Ferrando, R. Physical Review Letters, Vol. 93, Issue 6 https://doi.org/10.1103/PhysRevLett.93.065502	journal	August 2004
SchNetPack: A Deep Learning Toolbox For Atomistic Systems Schütt, K. T.; Kessel, P.; Gastegger, M. Journal of Chemical Theory and Computation, Vol. 15, Issue 1 https://doi.org/10.1021/acs.jctc.8b00908	journal	November 2018
The Birmingham parallel genetic algorithm and its application to the direct DFT global optimisation of Ir _N (N = 10–20) clusters Davis, Jack B. A.; Shayeghi, Armin; Horswell, Sarah L. Nanoscale, Vol. 7, Issue 33 https://doi.org/10.1039/C5NR03774C	journal	January 2015
Evolving better nanoparticles: Genetic algorithms for optimising cluster geometries Johnston, Roy L. Dalton Transactions, Issue 22 https://doi.org/10.1039/b305686d	journal	January 2003
Systematic Study of ${Au}_{6}$ to ${Au}_{12}$ Gold Clusters on MgO(100) $F$ Centers Using Density-Functional Theory Vilhelmsen, Lasse B.; Hammer, Bjørk Physical Review Letters, Vol. 108, Issue 12, Article No. 126101 https://doi.org/10.1103/PhysRevLett.108.126101	journal	March 2012
Structural evolution of Pt–Au nanoalloys during heating process: comparison of random and core-shell orderings Yang, Zhen; Yang, Xiaoning; Xu, Zhijun Physical Chemistry Chemical Physics, Vol. 11, Issue 29 https://doi.org/10.1039/b821328c	journal	January 2009
Gaussian Processes for Machine Learning Rasmussen, Carl Edward; Williams, Christopher K. I. The MIT Press https://doi.org/10.7551/mitpress/3206.001.0001	book	January 2005
Tuning the activities of cuprous oxide nanostructures via the oxide-metal interaction Huang, Wugen; Liu, Qingfei; Zhou, Zhiwen Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-15965-8	journal	May 2020
Potential energy functions for atomic solids: II. Potential functions for diamond-like structures Murrell, John N.; Rodriguez-Ruiz, Juan A. Molecular Physics, Vol. 71, Issue 4 https://doi.org/10.1080/00268979000102131	journal	November 1990
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias American Chemical Society https://doi.org/10.5451/unibas-ep43348	text	January 2015
Steps on Rutile TiO2(110): Active Sites for Water and Methanol Dissociation Martinez, Umberto; Vilhelmsen, Lasse B.; Kristoffersen, Henrik H. arXiv https://doi.org/10.48550/arxiv.1111.0428	text	January 2011
Localized atomic basis set in the projector augmented wave method Larsen, Ask Hjorth; Vanin, Marco; Mortensen, Jens Jørgen arXiv https://doi.org/10.48550/arxiv.1303.0348	text	January 2013

Cited By (4)

Identification of stable adsorption sites and diffusion paths on nanocluster surfaces: an automated scanning algorithm Szilvási, Tibor; Chen, Benjamin W. J.; Mavrikakis, Manos npj Computational Materials, Vol. 5, Issue 1 https://doi.org/10.1038/s41524-019-0240-x	journal	October 2019
Computational discovery of molecular C60 encapsulants with an evolutionary algorithm Miklitz, Marcin; Turcani, Lukas; Greenaway, Rebecca L. Communications Chemistry, Vol. 3, Issue 1 https://doi.org/10.1038/s42004-020-0255-8	journal	January 2020
Machine learning for interatomic potential models Mueller, Tim; Hernandez, Alberto; Wang, Chuhong The Journal of Chemical Physics, Vol. 152, Issue 5 https://doi.org/10.1063/1.5126336	journal	February 2020
Review: Deep Learning in Electron Microscopy Ede, Jeffrey M. arXiv https://doi.org/10.48550/arxiv.2009.08328	text	January 2020