Atom-centered neural network (ANN) potentials have shown promise in computational simulations and are recognized as both efficient and sufficiently accurate to describe systems involving bond formation and breaking. A key step in the development of ANN potentials is to represent atomic coordinates as suitable inputs for a neural network, commonly described as fingerprints. The accuracy and efficiency of the ANN potentials depend strongly on the selection of these fingerprints. Here, we propose an optimization strategy of atomic fingerprints to improve the performance of ANN potentials. Specifically, a set of fingerprints is optimized to fit a set of pre-selected template functions in the f*g space, where f and g are the fingerprint and the pair distribution function for each type of interatomic interaction (e.g., a pair or 3-body). With such an optimization strategy, we have developed an ANN potential for the Pd13H2 nanoparticle system that exhibits a significant improvement to the one based upon standard template functions. We further demonstrate that the ANN potential can be used with the adaptive kinetic Monte Carlo method, which has strict requirements for the smoothness of the potential. The algorithm proposed here facilitates the development of better ANN potentials, which can broaden their application in computational simulations.
REFERENCES
1.
F.
Brockherde
, L.
Vogt
, L.
Li
, M. E.
Tuckerman
, K.
Burke
, and K. R.
Muller
, “Bypassing the Kohn-Sham equations with machine learning
,” Nat. Commun.
8
, 872
(2017
).2.
J. C.
Snyder
, M.
Rupp
, K.
Hansen
, K. R.
Muller
, and K.
Burke
, “Finding density functionals with machine learning
,” Phys. Rev. Lett.
108
(25
), 253002
(2012
).3.
Z. W.
Li
, J. R.
Kermode
, and A.
De Vita
, “Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces
,” Phys. Rev. Lett.
114
(9
), 096405
(2015
).4.
T. L.
Jacobsen
, M. S.
Jorgensen
, and B.
Hammer
, “On-the-fly machine learning of atomic potential in density functional theory structure optimization
,” Phys. Rev. Lett.
120
(2
), 026102
(2018
).5.
S.
Chiriki
, S.
Jindal
, and S. S.
Bulusu
, “Neural network potentials for dynamics and thermodynamics of gold nanoparticles
,” J. Chem. Phys.
146
(8
), 084314
(2017
).6.
S.
Jindal
, S.
Chiriki
, and S. S.
Bulusu
, “Spherical harmonics based descriptor for neural network potentials: Structure and dynamics of Au147 nanocluster
,” J. Chem. Phys.
146
(20
), 204301
(2017
).7.
R.
Ouyang
, Y.
Xie
, and D.-e.
Jiang
, “Global minimization of gold clusters by combining neural network potentials and the basin-hopping method
,” Nanoscale
7
(36
), 14817
–14821
(2015
).8.
A. A.
Peterson
, R.
Christensen
, and A.
Khorshidi
, “Addressing uncertainty in atomistic machine learning
,” Phys. Chem. Chem. Phys.
19
(18
), 10978
–10985
(2017
).9.
F. A.
Faber
, L.
Hutchison
, B.
Huang
, J.
Gilmer
, S. S.
Schoenholz
, G. E.
Dahl
, O.
Vinyals
, S.
Kearnes
, P. F.
Riley
, and O. A.
von Lilienfeld
, “Prediction errors of molecular machine learning models lower than hybrid DFT error
,” J. Chem. Theory Comput.
13
(11
), 5255
–5264
(2017
).10.
A. A.
Peterson
, “Acceleration of saddle-point searches with machine learning
,” J. Chem. Phys.
145
(7
), 074106
(2016
).11.
J.
Behler
and M.
Parrinello
, “Generalized neural-network representation of high-dimensional potential-energy surfaces
,” Phys. Rev. Lett.
98
(14
), 146401
(2007
).12.
J.
Behler
, “Atom-centered symmetry functions for constructing high-dimensional neural network potentials
,” J. Chem. Phys.
134
(7
), 074106
(2011
).13.
M.
Gastegger
and P.
Marquetand
, “High-dimensional neural network potentials for organic reactions and an improved training algorithm
,” J. Chem. Theory Comput.
11
(5
), 2187
–2198
(2015
).14.
L.
Shen
, J.
Wu
, and W.
Yang
, “Multiscale quantum mechanics/molecular mechanics simulations with neural networks
,” J. Chem. Theory Comput.
12
(10
), 4934
–4946
(2016
).15.
K. T.
Schutt
, F.
Arbabzadah
, S.
Chmiela
, K. R.
Muller
, and A.
Tkatchenko
, “Quantum-chemical insights from deep tensor neural networks
,” Nat. Commun.
8
, 13890
(2017
).16.
J. S.
Smith
, O.
Isayev
, and A. E.
Roitberg
, “ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
,” Chem. Sci.
8
(4
), 3192
–3203
(2017
).17.
S.
Chmiela
, H. E.
Sauceda
, K. R.
Muller
, and A.
Tkatchenko
, “Towards exact molecular dynamics simulations with machine-learned force fields
,” Nat. Commun.
9
(1
), 3887
(2018
).18.
O. T.
Unke
and M.
Meuwly
, “Toolkit for the construction of reproducing kernel-based representations of data: Application to multidimensional potential energy surfaces
,” J. Chem. Inf. Model.
57
(8
), 1923
–1931
(2017
).19.
D.
Hu
, Y.
Xie
, X.
Li
, L.
Li
, and Z.
Lan
, “Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation
,” J. Phys. Chem. Lett.
9
(11
), 2725
–2732
(2018
).20.
A. P.
Bartok
, M. C.
Payne
, R.
Kondor
, and G.
Csanyi
, “Gaussian approximation potentials: The accuracy of quantum mechanics, without the electrons
,” Phys. Rev. Lett.
104
(13
), 136403
(2010
).21.
S. T.
John
and G.
Csányi
, “Many-body coarse-grained interactions using Gaussian approximation potentials
,” J. Phys. Chem. B
121
(48
), 10934
–10949
(2017
).22.
O.-P.
Koistinen
, F. B.
Dagbjartsdóttir
, V.
Ásgeirsson
, A.
Vehtari
, and H.
Jónsson
, “Nudged elastic band calculations accelerated with Gaussian process regression
,” J. Chem. Phys.
147
(15
), 152720
(2017
).23.
A. P.
Bartok
, R.
Kondor
, and G.
Csanyi
, “On representing chemical environments
,” Phys. Rev. B
87
(18
), 184115
(2013
).24.
M.
Novotni
and R.
Klein
, “Shape retrieval using 3D Zernike descriptors
,” Comput. - Aided Des.
36
(11
), 1047
–1062
(2004
).25.
M.
Yamauchi
, H.
Kobayashi
, and H.
Kitagawa
, “Hydrogen storage mediated by Pd and Pt nanoparticles
,” ChemPhysChem
10
(15
), 2566
–2576
(2009
).26.
Y. E.
Cheon
and M. P.
Suh
, “Enhanced hydrogen storage by palladium nanoparticles fabricated in a redox-active metal-organic framework
,” Angew. Chem., Int. Ed.
48
(16
), 2899
–2903
(2009
).27.
P.
Kamakoti
, B. D.
Morreale
, M. V.
Ciocco
, B. H.
Howard
, R. P.
Killmeyer
, A. V.
Cugini
, and D. S.
Sholl
, “Prediction of hydrogen flux through sulfur-tolerant binary alloy membranes
,” Science
307
, 569
–573
(2005
).28.
D.
Teschner
, J.
Borsodi
, A.
Wootsch
, Z.
Revay
, M.
Havecker
, A.
Knop-Gericke
, S. D.
Jackson
, and R.
Schlogl
, “The roles of subsurface carbon and hydrogen in palladium-catalyzed alkyne hydrogenation
,” Science
320
(5872
), 86
–89
(2008
).29.
D.
Teschner
, Z.
Révay
, J.
Borsodi
, M.
Hävecker
, A.
Knop-Gericke
, R.
Schlögl
, D.
Milroy
, S. D.
Jackson
, D.
Torres
, and P.
Sautet
, “Understanding palladium hydrogenation catalysts: When the nature of the reactive molecule controls the nature of the catalyst active phase
,” Angew. Chem., Int. Ed.
47
(48
), 9274
–9278
(2008
).30.
Y.
Chin
, R.
Dagle
, J.
Hu
, A. C.
Dohnalkova
, and Y.
Wang
, “Steam reforming of methanol over highly active Pd/ZnO catalyst
,” Catal. Today
77
(1
), 79
–88
(2002
).31.
M. A.
Goula
, S. K.
Kontou
, and P. E.
Tsiakaras
, “Hydrogen production by ethanol steam reforming over a commercial Pd/γ-Al2O3 catalyst
,” Appl. Catal., B
49
(2
), 135
–144
(2004
).32.
L.
Xu
and G.
Henkelman
, “Adaptive kinetic Monte Carlo for first-principles accelerated dynamics
,” J. Chem. Phys.
129
(11
), 114104
(2008
).33.
G.
Henkelman
and H.
Jónsson
, “Long time scale kinetic Monte Carlo simulations without lattice approximation and predefined event table
,” J. Chem. Phys.
115
(21
), 9657
(2001
).34.
A.
Khorshidi
and A. A.
Peterson
, “Amp: A modular approach to machine learning in atomistic simulations
,” Comput. Phys. Commun.
207
, 310
–324
(2016
).35.
E. B.
Tadmor
, R. S.
Elliott
, J. P.
Sethna
, R. E.
Miller
, and C. A.
Becker
, “The potential of atomistic simulations and the knowledgebase of interatomic models
,” JOM
63
(17
), 17
(2011
).36.
A.
Heyden
, A. T.
Bell
, and F. J.
Keil
, “Efficient methods for finding transition states in chemical reactions: Comparison of improved dimer method and partitioned rational function optimization method
,” J. Chem. Phys.
123
(22
), 224101
(2005
).37.
J.
Kästner
and P.
Sherwood
, “Superlinearly converging dimer method for transition state search
,” J. Chem. Phys.
128
(1
), 014106
(2008
).38.
G.
Henkelman
and H.
Jónsson
, “A dimer method for finding saddle points on high dimensional potential surfaces using only first derivatives
,” J. Chem. Phys.
111
(15
), 7010
–7022
(1999
).39.
J.
Hutter
, M.
Iannuzzi
, F.
Schiffmann
, and J.
VandeVondele
, “cp2k: Atomistic simulations of condensed matter systems
,” Wiley Interdiscip. Rev.: Comput. Mol. Sci.
4
(1
), 15
–25
(2014
).40.
J.
VandeVondele
and J.
Hutter
, “Gaussian basis sets for accurate calculations on molecular systems in gas and condensed phases
,” J. Chem. Phys.
127
(11
), 114105
(2007
).41.
S.
Goedecker
, M.
Teter
, and J.
Hutter
, “Separable dual-space Gaussian pseudopotentials
,” Phys. Rev. B
54
(3
), 1703
–1710
(1996
).42.
A.
Hjorth Larsen
, J.
Jørgen Mortensen
, J.
Blomqvist
, I. E.
Castelli
, R.
Christensen
, M.
Dułak
, J.
Friis
, M. N.
Groves
, B.
Hammer
, C.
Hargus
, E. D.
Hermes
, P. C.
Jennings
, P.
Bjerre Jensen
, J.
Kermode
, J. R.
Kitchin
, E.
Leonhard Kolsbjerg
, J.
Kubal
, K.
Kaasbjerg
, S.
Lysgaard
, J.
Bergmann Maronsson
, T.
Maxson
, T.
Olsen
, L.
Pastewka
, A.
Peterson
, C.
Rostgaard
, J.
Schiøtz
, O.
Schütt
, M.
Strange
, K. S.
Thygesen
, T.
Vegge
, L.
Vilhelmsen
, M.
Walter
, Z.
Zeng
, and K. W.
Jacobsen
, “The atomic simulation environment–A Python library for working with atoms
,” J. Phys.: Condens. Matter
29
(27
), 273002
(2017
).43.
G.
Kresse
and J.
Furthmüller
, “Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set
,” Comput. Mater. Sci.
6
(1
), 15
–50
(1996
).44.
G.
Kresse
and J.
Furthmüller
, “Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
,” Phys. Rev. B
54
(16
), 11169
–11186
(1996
).45.
P. E.
Blöchl
, “Projector augmented-wave method
,” Phys. Rev. B
50
(24
), 17953
–17979
(1994
).46.
J. P.
Perdew
, K.
Burke
, and M.
Ernzerhof
, “Generalized gradient approximation made simple
,” Phys. Rev. Lett.
77
(18
), 3865
–3868
(1996
).47.
See https://github.com/pele-python/pele for Pele.
48.
L.
Li
, X.
Li
, Z.
Duan
, R. J.
Meyer
, R.
Carr
, S.
Raman
, L.
Koziol
, and G.
Henkelman
, “Adaptive kinetic Monte Carlo simulations of surface segregation in PdAu nanoparticles
,” Nanoscale
11
(21
), 10524
–10535
(2019
).49.
S. T.
Chill
, M.
Welborn
, R.
Terrell
, L.
Zhang
, J.-C.
Berthet
, A.
Pedersen
, H.
Jónsson
, and G.
Henkelman
, “EON: Software for long time simulations of atomic scale systems
,” Modell. Simul. Mater. Sci. Eng.
22
(5
), 055002
(2014
).© 2020 Author(s).
2020
Author(s)
You do not currently have access to this content.
