Many problems in computational materials science and chemistry require the evaluation of expensive functions with locally rapid changes, such as the turn-over frequency of first principles kinetic Monte Carlo models for heterogeneous catalysis. Because of the high computational cost, it is often desirable to replace the original with a surrogate model, e.g., for use in coupled multiscale simulations. The construction of surrogates becomes particularly challenging in high-dimensions. Here, we present a novel version of the modified Shepard interpolation method which can overcome the curse of dimensionality for such functions to give faithful reconstructions even from very modest numbers of function evaluations. The introduction of local metrics allows us to take advantage of the fact that, on a local scale, rapid variation often occurs only across a small number of directions. Furthermore, we use local error estimates to weigh different local approximations, which helps avoid artificial oscillations. Finally, we test our approach on a number of challenging analytic functions as well as a realistic kinetic Monte Carlo model. Our method not only outperforms existing isotropic metric Shepard methods but also state-of-the-art Gaussian process regression.

1.
J.
Behler
,
J. Phys.: Condens. Matter
26
,
183001
(
2014
).
2.
A. P.
Bartók
,
M. C.
Payne
,
R.
Kondor
, and
G.
Csányi
,
Phys. Rev. Lett.
104
,
136403
(
2010
).
3.
T.
Stecher
,
N.
Bernstein
, and
G.
Csányi
,
J. Chem. Theory Comput.
10
,
4079
(
2014
).
4.
L.
Mones
,
N.
Bernstein
, and
G.
Csányi
,
J. Chem. Theory Comput.
12
,
5100
(
2016
).
5.
H. F.
Busnengo
,
A.
Salin
, and
W.
Dong
,
J. Chem. Phys.
112
,
7641
(
2000
).
6.
D.
Strobusch
and
C.
Scheurer
,
J. Chem. Phys.
140
,
074111
(
2014
).
7.
M. A.
Collins
,
Theor. Chem. Acc.
108
,
313
(
2002
).
8.
S.
Matera
and
K.
Reuter
,
Catal. Lett.
133
,
156
(
2009
).
9.
S.
Matera
and
K.
Reuter
,
Phys. Rev. B
82
,
085446
(
2010
).
10.
S.
Matera
,
M.
Maestri
,
A.
Cuoci
, and
K.
Reuter
,
ACS Catal.
4
,
4081
(
2014
).
11.
S.
Matera
,
S.
Blomberg
,
M. J.
Hoffmann
,
J.
Zetterberg
,
J.
Gustafson
,
E.
Lundgren
, and
K.
Reuter
,
ACS Catal.
5
,
4514
(
2015
).
12.
M.
Votsmeier
,
Chem. Eng. Sci.
64
,
1384
(
2009
).
13.
M.
Votsmeier
,
A.
Scheuer
,
A.
Drochner
,
H.
Vogel
, and
J.
Gieshoff
,
Catal. Today
151
,
271
(
2010
).
14.
S.
Pope
,
Combust. Theory Modell.
1
,
41
(
1997
).
15.
A.
Varshney
and
A.
Armaou
,
Chem. Eng. Sci.
60
,
6780
(
2005
).
16.
A.
Varshney
and
A.
Armaou
,
Comput. Chem. Eng.
32
,
2136
(
2008
).
17.
K.
Reuter
,
D.
Frenkel
, and
M.
Scheffler
,
Phys. Rev. Lett.
93
,
116105
(
2004
).
18.
K.
Reuter
,
Catal. Lett.
146
,
541
(
2016
).
19.
J. M.
Lorenzi
,
S.
Matera
, and
K.
Reuter
,
ACS Catal.
6
,
5191
(
2016
).
20.
R. J.
Renka
,
ACM Trans. Math. Software
14
,
139
(
1988
).
21.
S.
Vijayakumar
,
A.
D’souza
, and
S.
Schaal
,
Neural Comput.
17
,
2602
(
2005
).
22.
C.
Zuppa
,
Appl. Numer. Math.
49
,
245
(
2004
).
23.
M.
Maestri
and
A.
Cuoci
,
Chem. Eng. Sci.
96
,
106
(
2013
).
24.
D.
Shepard
, in
Proceedings of the 1968 23rd ACM National Conference, ACM ’68
(
ACM
,
New York, NY, USA
,
1968
), pp.
517
524
.
25.
R.
Franke
and
G.
Nielson
,
Int. J. Numer. Methods Eng.
15
,
1691
(
1980
).
26.
S.
Bochkanov
, “ALGLIB,” www.alglib.net.
27.
J. W.
Demmel
,
Applied Numerical Linear Algebra
(
SIAM
,
Philadelphia, PA, USA
,
1997
).
28.
Python Software Foundation, “Python 2.7,” http://www.python.org/.
29.
See http://www.swig.org for SWIG: Simplified wrapper and interface generator.
30.
L. S.
Blackford
,
J.
Demmel
,
J.
Dongarra
,
I.
Duff
,
S.
Hammarling
,
G.
Henry
,
M.
Heroux
,
L.
Kaufman
,
A.
Lumsdaine
,
A.
Petitet
,
R.
Pozo
,
K.
Remington
, and
R. C.
Whaley
,
ACM Trans. Math. Software
28
,
135
(
2002
).
31.
E.
Anderson
,
Z.
Bai
,
C.
Bischof
,
S.
Blackford
,
J.
Demmel
,
J.
Dongarra
,
J.
Du Croz
,
A.
Greenbaum
,
S.
Hammarling
,
A.
McKenney
, and
D.
Sorensen
,
LAPACK Users’ Guide
, 3rd ed. (
SIAM
,
Philadelphia, PA
,
1999
).
32.
S. G.
Johnson
, “The NLopt nonlinear-optimization package,” http://ab-initio.mit.edu/nlopt.
33.
M. J. D.
Powell
, in
Advances in Optimization and Numerical Analysis
, edited by
S.
Gomez
and
J.-P.
Hennart
(
Kluwer Academic
,
Dordrecht
,
1994
), pp.
51
67
;
M.
Powell
,
Acta Numer.
7
,
287
(
1998
).
34.
K.
Svanberg
,
SIAM J. Optim.
12
,
555
(
2002
).
35.
I.
Sobol
,
USSR Comput. Math. Math. Phys.
7
,
86
(
1967
).
36.
P.
L’Ecuyer
and
C.
Lemieux
, in
Modeling Uncertainty: An Examination of Stochastic Theory, Methods, and Applications
, edited by
M.
Dror
,
P.
L’Ecuyer
, and
F.
Szidarovszky
(
Springer
,
Boston, MA
,
2005
), pp.
419
474
.
37.
C. E.
Rasmussen
and
C. K. I.
Williams
,
Gaussian Processes for Machine Learning
, Adaptive Computation and Machine Learning Series (
MIT Press
,
2005
).
38.
D. J. C.
Mackay
,
Information Theory, Inference and Learning Algorithms
, 1st ed. (
Cambridge University Press
,
2003
).
39.
GPy
, “GPy: A gaussian process framework in python,” http://github.com/SheffieldML/GPy, since 2012.
40.
K.
Reuter
and
M.
Scheffler
,
Phys. Rev. B
73
,
045433
(
2006
).
41.
P.
Gelß
,
S.
Matera
, and
C.
Schütte
,
J. Comput. Phys.
314
,
489
(
2016
).
42.
H.
Meskine
,
S.
Matera
,
M.
Scheffler
,
K.
Reuter
, and
H.
Metiu
,
Surf. Sci.
603
,
1724
(
2009
).
43.
S.
Döpking
and
S.
Matera
,
Chem. Phys. Lett.
674
,
28
(
2017
).
44.
M. J.
Hoffmann
,
F.
Engelmann
, and
S.
Matera
,
J. Chem. Phys.
146
,
044118
(
2017
).
45.
J. E.
Sutton
,
W.
Guo
,
M. A.
Katsoulakis
, and
D. G.
Vlachos
,
Nat. Chem.
8
,
331
(
2016
).
46.
B.
Temel
,
H.
Meskine
,
K.
Reuter
,
M.
Scheffler
, and
H.
Metiu
,
J. Chem. Phys.
126
,
204711
(
2007
).
47.
S.
Matera
,
H.
Meskine
, and
K.
Reuter
,
J. Chem. Phys.
134
,
064713
(
2011
).
48.
D.-J.
Liu
and
J. W.
Evans
,
J. Chem. Phys.
142
,
134703
(
2015
).
49.
G. J.
Herschlag
,
S.
Mitran
, and
G.
Lin
,
J. Chem. Phys.
142
,
234703
(
2015
).
50.
M. J.
Hoffmann
,
S.
Matera
, and
K.
Reuter
,
Comput. Phys. Commun.
185
,
2138
(
2014
).
51.
R.
Kee
,
M.
Coltrin
, and
P.
Glarborg
,
Chemically Reacting Flow, Theory and Practice
(
Wiley
,
Hoboken, NJ
,
2003
).
52.
J.
Zetterberg
,
S.
Blomberg
,
J.
Gustafson
,
Z. W.
Sun
,
Z. S.
Li
,
E.
Lundgren
, and
M.
Aldén
,
Rev. Sci. Instrum.
83
,
053104
(
2012
).

Supplementary Material

You do not currently have access to this content.