An accurate determination of the potential energy is the crucial step in computer simulations of chemical processes, but using electronic structure methods on-the-fly in molecular dynamics (MD) is computationally too demanding for many systems. Constructing more efficient interatomic potentials becomes intricate with increasing dimensionality of the potential-energy surface (PES), and for numerous systems the accuracy that can be achieved is still not satisfying and far from the reliability of first-principles calculations. Feed-forward neural networks (NNs) have a very flexible functional form, and in recent years they have been shown to be an accurate tool to construct efficient PESs. High-dimensional NN potentials based on environment-dependent atomic energy contributions have been presented for a number of materials. Still, these potentials may be improved by a more detailed structural description, e.g., in form of atom pairs, which directly reflect the atomic interactions and take the chemical environment into account. We present an implementation of an NN method based on atom pairs, and its accuracy and performance are compared to the atom-based NN approach using two very different systems, the methanol molecule and metallic copper. We find that both types of NN potentials provide an excellent description of both PESs, with the pair-based method yielding a slightly higher accuracy making it a competitive alternative for addressing complex systems in MD simulations.

1.
R.
Car
and
M.
Parrinello
,
Phys. Rev. Lett.
55
,
2471
(
1985
).
2.
D.
Marx
and
J.
Hutter
,
Ab initio Molecular Dynamics: Basic Theory and Advanced Methods
(
Cambridge University Press
,
Cambridge
,
2009
).
3.
N. L.
Allinger
,
Y. H.
Yuh
, and
J.-H.
Lii
,
J. Am. Chem. Soc.
111
,
8551
(
1989
).
4.
S. L.
Mayo
,
B. D.
Olafson
, and
W. A.
Goddard
 III
,
J. Phys. Chem.
94
,
8897
(
1990
).
5.
B. R.
Brooks
,
R. E.
Bruccoleri
,
B. D.
Olafson
,
D. J.
States
,
S.
Swaminathan
, and
M.
Karplus
,
J. Comput. Chem.
4
,
187
(
1983
).
6.
M. S.
Daw
and
M. I.
Baskes
,
Phys. Rev. B
29
,
6443
(
1984
).
8.
M. W.
Finnis
,
Prog. Mater. Sci.
52
,
133
(
2007
).
9.
F. H.
Stillinger
and
T. A.
Weber
,
Phys. Rev. B
31
,
5262
(
1985
).
10.
R.
Drautz
,
D. A.
Murdick
,
D.
Nguyen-Manh
,
X.
Zhou
,
H. N. G.
Wadley
, and
D. G.
Pettifor
,
Phys. Rev. B
72
,
144105
(
2005
).
11.
J.
Tersoff
,
Phys. Rev. Lett.
56
,
632
(
1986
).
12.
J.
Tersoff
,
Phys. Rev. B
38
,
9902
(
1988
).
13.
W. H.
Press
,
S. A.
Teukolsky
,
W. T.
Vetterling
, and
B. P.
Flannery
,
Numerical Recipes - The Art of Scientific Computing
(
Cambridge University Press
,
Cambridge
,
2007
).
14.
X.
Huang
,
B. J.
Braams
, and
J. M.
Bowman
,
J. Chem. Phys.
122
,
044302
(
2005
).
15.
J.
Ischtwan
and
M. A.
Collins
,
J. Chem. Phys.
100
,
8080
(
1994
).
16.
D. E.
Makarov
and
H.
Metiu
,
J. Chem. Phys.
108
,
590
(
1998
).
17.
G. G.
Maisuradze
,
D. L.
Thompson
,
A. F.
Wagner
, and
M.
Minkoff
,
J. Chem. Phys.
119
,
10002
(
2003
).
18.
A. P.
Bartok
,
M. C.
Payne
,
R.
Kondor
, and
G.
Csanyi
,
Phys. Rev. Lett.
104
,
136403
(
2010
).
19.
M. J. L.
Mills
and
P. L. A.
Popelier
,
Comp. Theor. Chem.
975
,
42
(
2011
).
20.
M. J. L.
Mills
and
P. L. A.
Popelier
,
Theor. Chem. Acc.
131
,
1137
(
2012
).
21.
C. M.
Handley
,
G. I.
Hawe
,
D. B.
Kell
, and
P. L. A.
Popelier
,
Phys. Chem. Chem. Phys.
11
,
6365
(
2009
).
22.
C. M.
Bishop
,
Neural Networks for Pattern Recognition
(
Oxford University Press
,
Oxford
,
1995
).
23.
K.
Hornik
,
M.
Stinchcombe
, and
H.
White
,
Neural Networks
2
,
359
(
1989
).
24.
G.
Cybenko
,
Math. Control, Signals, Syst.
2
,
303
(
1989
).
25.
C. M.
Handley
and
P. L. A.
Popelier
,
J. Phys. Chem. A
114
,
3371
(
2010
).
26.
J.
Behler
,
Chem. Modell.
7
,
1
(
2010
).
27.
J.
Behler
,
Phys. Chem. Chem. Phys.
13
,
17930
(
2011
).
28.
D. F. R.
Brown
,
M. N.
Gibbs
, and
D. C.
Clary
,
J. Chem. Phys.
105
,
7597
(
1996
).
29.
K. T.
No
,
B. H.
Chang
,
S. Y.
Kim
,
M. S.
Jhon
, and
H. A.
Scheraga
,
Chem. Phys. Lett.
271
,
152
(
1997
).
30.
F. V.
Prudente
and
J. J. S.
Neto
,
Chem. Phys. Lett.
287
,
585
(
1998
).
31.
S.
Manzhos
,
X.
Wang
,
R.
Dawes
, and
T.
Carrington
 Jr.
,
J. Phys. Chem. A
110
,
5295
(
2006
).
32.
L. M.
Raff
,
M.
Malshe
,
M.
Hagan
,
D. I.
Doughan
,
M. G.
Rockley
, and
R.
Komanduri
,
J. Chem. Phys.
122
,
084104
(
2005
).
33.
M.
Malshe
,
L. M.
Raff
,
M. G.
Rockley
, and
M.
Hagan
,
J. Chem. Phys.
127
,
134105
(
2007
).
34.
S.
Hobday
,
R.
Smith
, and
J.
Belbruno
,
Modell. Simul. Mater. Sci. Eng.
7
,
397
(
1999
).
35.
S.
Hobday
,
R.
Smith
, and
J.
BelBruno
,
Nucl. Instrum. Methods Phys. Res. B
153
,
247
(
1999
).
36.
A.
Bholoa
,
S. D.
Kenny
, and
R.
Smith
,
Nucl. Instrum. Methods Phys. Res. B
255
,
1
(
2006
).
37.
E.
Sanville
,
A.
Bholoa
,
R.
Smith
, and
S. D.
Kenny
,
J. Phys.: Condens. Matter
20
,
285219
(
2008
).
38.
R. Z.
Khaliullin
,
H.
Eshet
,
T. D.
Kühne
,
J.
Behler
, and
M.
Parrinello
,
Phys. Rev. B
81
,
100103
(
2010
).
39.
H.
Eshet
,
R. Z.
Khaliullin
,
T. D.
Kühne
,
J.
Behler
, and
M.
Parrinello
,
Phys. Rev. B
81
,
184107
(
2010
).
40.
R. Z.
Khaliullin
,
H.
Eshet
,
T. D.
Kühne
,
J.
Behler
, and
M.
Parrinello
,
Nature Mater.
10
,
693
(
2011
).
41.
J.
Behler
,
R.
Martoňàk
,
D.
Donadio
, and
M.
Parrinello
,
Phys. Rev. Lett.
100
,
185501
(
2008
).
42.
J.
Behler
,
R.
Martoňàk
,
D.
Donadio
, and
M.
Parrinello
,
Phys. Status Solidi B
245
,
2618
(
2008
).
43.
J.
Behler
and
M.
Parrinello
,
Phys. Rev. Lett.
98
,
146401
(
2007
).
44.
J.
Behler
,
J. Chem. Phys.
134
,
074106
(
2011
).
45.
T. B.
Blank
,
S. D.
Brown
,
A. W.
Calhoun
, and
D. J.
Doren
,
J. Chem. Phys.
103
,
4129
(
1995
).
46.
S.
Lorenz
,
A.
Groß
, and
M.
Scheffler
,
Chem. Phys. Lett.
395
,
210
(
2004
).
47.
S.
Lorenz
,
M.
Scheffler
, and
A.
Groß
,
Phys. Rev. B
73
,
115431
(
2006
).
48.
J.
Behler
,
B.
Delley
,
S.
Lorenz
,
K.
Reuter
, and
M.
Scheffler
,
Phys. Rev. Lett.
94
,
036104
(
2005
).
49.
J.
Behler
,
S.
Lorenz
, and
K.
Reuter
,
J. Chem. Phys.
127
,
014705
(
2007
).
50.
J.
Behler
,
K.
Reuter
, and
M.
Scheffler
,
Phys. Rev. B
77
,
115421
(
2008
).
51.
C.
Carbogno
,
J.
Behler
,
A.
Groß
, and
K.
Reuter
,
Phys. Rev. Lett.
101
,
096104
(
2008
).
52.
C.
Carbogno
,
J.
Behler
,
K.
Reuter
, and
A.
Groß
,
Phys. Rev. B
81
,
035410
(
2010
).
53.
J.
Ludwig
and
D. G.
Vlachos
,
J. Chem. Phys.
127
,
154716
(
2007
).
54.
D. A. R. S.
Latino
,
R. P. S.
Fartaria
,
F. F. M.
Freitas
,
J.
Aires-de-Sousa
, and
F. M. S. S.
Fernandes
,
J. Electroanal. Chem.
624
,
109
(
2008
).
55.
H.
Gassner
,
M.
Probst
,
A.
Lauenstein
, and
K.
Hermansson
,
J. Phys. Chem. A
102
,
4596
(
1998
).
56.
F. V.
Prudente
,
P. H.
Acioli
, and
J. J. S.
Neto
,
J. Chem. Phys.
109
,
8801
(
1998
).
57.
S.
Manzhos
and
T.
Carrington
 Jr.
,
J. Chem. Phys.
125
,
84109
(
2006
).
58.
S.
Manzhos
and
T.
Carrington
 Jr.
,
J. Chem. Phys.
127
,
014103
(
2007
).
59.
S.
Manzhos
and
T.
Carrington
 Jr.
,
J. Chem. Phys.
129
,
224104
(
2008
).
60.
M.
Malshe
,
R.
Narulkar
,
L. M.
Raff
,
M.
Hagan
,
S.
Bukkapatnam
,
P. M.
Agrawal
, and
R.
Komanduri
,
J. Chem. Phys.
130
,
184102
(
2009
).
61.
N.
Artrith
and
J.
Behler
,
Phys. Rev. B
85
,
045439
(
2012
).
62.
S.
Houlding
,
S. Y.
Liem
, and
P. L. A.
Popelier
,
Int. J. Quantum. Chem.
107
,
2817
(
2007
).
63.
M. G.
Darley
,
C. M.
Handley
, and
P. L. A.
Popelier
,
J. Chem. Theory Comput.
4
,
1435
(
2008
).
64.
N.
Artrith
,
T.
Morawietz
, and
J.
Behler
,
Phys. Rev. B
83
,
153101
(
2011
).
65.
P. P.
Ewald
,
Ann. Phys.
64
,
253
(
1921
).
66.
T.
Morawietz
,
V.
Sharma
, and
J.
Behler
,
J. Chem. Phys.
136
,
064103
(
2012
).
67.
C. A.
Coulson
,
Proc. R. Soc. London Ser. A
169
,
413
(
1939
).
68.
R. E.
Kalman
,
J. Basic Eng.
82
,
35
(
1960
).
69.
T. B.
Blank
and
S. D.
Brown
,
J. Chemom.
8
,
391
(
1994
).
70.
RuNNer: A Neural Network Code for High-Dimensional Potential-Energy Surfaces, Jörg Behler, Lehrstuhl für Theoretische Chemie, Ruhr-Universität Bochum, Germany.
71.
TINKER, Version 5.1, Software Tools for Molecular Design, J. W. Ponder, Biochemistry and Molecular Physics, Washington University, St. Louis, USA.
72.
V.
Blum
 et al,
Comput. Phys. Commun.
180
,
2175
(
2009
).
73.
J. P.
Perdew
,
K.
Burke
, and
M.
Ernzerhof
,
Phys. Rev. Lett.
77
,
3865
(
1996
).
74.
See supplemental material at http://dx.doi.org/10.1063/1.4712397 for the specific symmetry functions and their parameters used in this work.

Supplementary Material

You do not currently have access to this content.