We present a method for optimizing transition state theory dividing surfaces with support vector machines. The resulting dividing surfaces require no a priori information or intuition about reaction mechanisms. To generate optimal dividing surfaces, we apply a cycle of machine-learning and refinement of the surface by molecular dynamics sampling. We demonstrate that the machine-learned surfaces contain the relevant low-energy saddle points. The mechanisms of reactions may be extracted from the machine-learned surfaces in order to identify unexpected chemically relevant processes. Furthermore, we show that the machine-learned surfaces significantly increase the transmission coefficient for an adatom exchange involving many coupled degrees of freedom on a (100) surface when compared to a distance-based dividing surface.

1.
H.
Eyring
,
J. Chem. Phys.
3
,
107
(
1935
).
2.
E.
Wigner
,
Trans. Faraday Soc.
34
,
29
(
1938
).
3.
J. C.
Keck
,
Adv. Chem. Phys.
13
,
85
(
1967
).
4.
G.
Henkelman
and
H.
Jónsson
,
Phys. Rev. Lett.
90
,
116101
(
2003
).
5.
L.
Xu
,
G.
Henkelman
,
C. T.
Campbell
, and
H.
Jónsson
,
Phys. Rev. Lett.
95
,
146103
(
2005
).
6.
G.
Henkelman
and
H.
Jónsson
,
J. Chem. Phys.
115
,
9657
(
2001
).
7.
E. P.
Wigner
,
J. Chem. Phys.
5
,
720
(
1937
).
8.
T.
Komatsuzaki
and
R. S.
Berry
,
J. Mol. Struct.: THEOCHEM
506
,
55
(
2000
).
9.
S.
Wiggins
,
L.
Wiesenfeld
,
C.
Jaffé
, and
T.
Uzer
,
Phys. Rev. Lett.
86
,
5478
(
2001
).
10.
T.
Uzer
,
C.
Jaffé
,
J.
Palacian
,
P.
Yanguas
, and
S.
Wiggins
,
Nonlinearity
15
,
957
(
2002
).
11.
H.
Waalkens
and
S.
Wiggins
,
J. Phys. A
37
,
L435
(
2004
).
12.
C.
Jaffé
,
D.
Farrelly
, and
T.
Uzer
,
Phys. Rev. A
60
,
3833
(
1999
).
13.
R.
Hernandez
,
T.
Uzer
, and
T.
Bartsch
,
Chem. Phys.
370
,
270
(
2010
).
14.
H.
Waalkens
,
A.
Burbanks
, and
S.
Wiggins
,
Phys. Rev. Lett.
95
,
084301
(
2005
).
15.
K.-R.
Müller
,
S.
Mika
,
G.
Rätsch
,
K.
Tsuda
, and
B.
Schölkopf
,
IEEE Trans. Neural Netw.
12
,
181
(
2001
).
16.
B.
Schölkopf
and
A. J.
Smola
,
Learning with Kernels
(
MIT
,
Cambridge
,
2002
).
17.
O.
Ivanciuc
, “
Applications of support vector machines in chemistry
,” in
Reviews in Computational Chemistry
(
Wiley-VCH
,
2007
), Chap. 6, pp.
291
400
.
18.
C.
Cortes
and
V.
Vapnik
,
Mach. Learn.
20
,
273
(
1995
).
19.
B.
Schölkopf
,
A.
Smola
, and
K.-R.
Müller
,
Neural Comput.
10
,
1299
(
1998
).
20.
A.
Smola
,
B.
Schölkopf
, and
K.-R.
Müller
,
Neural Networks
11
,
637
(
1998
).
21.
See http://scikit-learn.sourceforge.net for scikits.learn python module,
2007
.
22.
C.-C.
Chang
and
C.-J.
Lin
, LIBSVM: A library for support vector machines (
2001
), see http://www.csie.ntu.edu.tw/~cjlin/libsvm.
23.
T.
Hastie
,
R.
Tibshirani
, and
J.
Friedman
,
The Elements of Statistical Learning: Data Mining, Inference and Prediction
,
Springer Series in Statistics
(
Springer
,
New York
,
2001
).
24.
G.
Bussi
,
D.
Donadio
, and
M.
Parrinello
,
J. Chem. Phys.
126
,
014101
(
2007
).
25.
D.
Baehrens
,
T.
Schroeter
,
S.
Harmeling
,
M.
Kawanabe
,
K.
Hansen
, and
K.-R.
Müller
,
J. Mach. Learn. Res.
11
,
1803
(
2010
).
26.
A. F.
Voter
,
J. Chem. Phys.
106
,
4665
(
1997
).
27.
A. F.
Voter
and
S. P.
Chen
,
Mater. Res. Soc. Symp. Proc.
82
,
175
(
1987
).
28.
C.-Y.
Lu
,
D. E.
Makarov
, and
G.
Henkelman
,
J. Chem. Phys.
133
,
201101
(
2010
).
29.
R. A.
Miron
and
K. A.
Fichthorn
,
J. Chem. Phys.
119
,
6210
(
2003
).
You do not currently have access to this content.