Multifidelity modeling is a technique for fusing the information from two or more datasets into one model. It is particularly advantageous when one dataset contains few accurate results and the other contains many less accurate results. Within the context of modeling potential energy surfaces, the low-fidelity dataset can be made up of a large number of inexpensive energy computations that provide adequate coverage of the N-dimensional space spanned by the molecular internal coordinates. The high-fidelity dataset can provide fewer but more accurate electronic energies for the molecule in question. Here, we compare the performance of several neural network-based approaches to multifidelity modeling. We show that the four methods (dual, Δ-learning, weight transfer, and Meng–Karniadakis neural networks) outperform a traditional implementation of a neural network, given the same amount of training data. We also show that the Δ-learning approach is the most practical and tends to provide the most accurate model.
REFERENCES
1.
F.
London
, Z. Electrochem.
35
, 552
(1929
).2.
A. M.
Cooper
, P. P.
Hallmen
, and J.
Kästner
, “Potential energy surface interpolation with neural networks for instanton rate calculations
,” J. Chem. Phys.
148
, 094106
(2018
).3.
B.
Kolb
, P.
Marshall
, B.
Zhao
, B.
Jiang
, and H.
Guo
, “Representing global reactive potential energy surfaces using Gaussian processes
,” J. Phys. Chem. A
121
, 2552
–2557
(2017
).4.
C.
Qu
, P. L.
Houston
, R.
Conte
, A.
Nandi
, and J. M.
Bowman
, “Breaking the coupled cluster barrier for machine-learned potentials of large molecules: The case of 15-atom acetylacetone
,” J. Phys. Chem. Lett.
12
, 4902
–4909
(2021
).5.
H.
Sugisawa
, T.
Ida
, and R. V.
Krems
, “Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
,” J. Chem. Phys.
153
, 114101
(2020
).6.
A.
Kushwaha
, Ritika
, P.
Chahal
, and T. J.
Dhilip Kumar
, “Rotational excitation of NCCN by p-H2(jc = 0) at low temperatures
,” ACS Earth Space Chem.
7
, 515
–522
(2023
).7.
K.
Saito
, Y.
Hashimoto
, and T.
Takayanagi
, “Ring-polymer molecular dynamics calculations of thermal rate coefficients and branching ratios for the interstellar + CO H2 + HCO+/HOC+ reaction and its deuterated analogue
,” J. Phys. Chem. A
125
, 10750
–10756
(2021
).8.
J.-K.
Ha
, K.
Kim
, and S. K.
Min
, “Machine learning-assisted excited state molecular dynamics with the state-interaction state-averaged spin-restricted ensemble-referenced Kohn–Sham approach
,” J. Chem. Theory Comput.
17
, 694
–702
(2021
).9.
B.
Jiang
, J.
Li
, and H.
Guo
, “High-fidelity potential energy surfaces for gas-phase and gas–surface scattering processes from machine learning
,” J. Phys. Chem. Lett.
11
, 5120
–5131
(2020
).10.
A.
Kushwaha
and T. J.
Dhilip Kumar
, “Benchmarking PES-learn’s machine learning models predicting accurate potential energy surface for quantum scattering
,” Int. J. Quantum Chem.
123
, e27007
(2023
).11.
E.
Quintas-Sánchez
and R.
Dawes
, “Spectroscopy and scattering studies using interpolated ab initio potentials
,” Annu. Rev. Phys. Chem.
72
, 399
–421
(2021
).12.
M. M.
Davis
, J. D.
Weidman
, A. S.
Abbott
, G. E.
Douberly
, J. M.
Turney
, and H. F.
Schaefer
III, “Characterization of the 2-methylvinoxy radical + O2 reaction: A focal point analysis and composite multireference study
,” J. Chem. Phys.
151
, 124302
(2019
).13.
J. N.
Murrell
, S.
Carter
, S. C.
Farantos
, P.
Huxley
, and A. J. C.
Varandas
, Molecular Potential Energy Functions
(John Wiley and Sons Ltd.
, 1984
).14.
15.
L. M.
Raff
, M.
Malshe
, M.
Hagan
, D. I.
Doughan
, M. G.
Rockley
, and R.
Komanduri
, “Ab initio potential-energy surfaces for complex, multichannel systems using modified novelty sampling and feedforward neural networks
,” J. Chem. Phys.
122
, 084104
(2005
).16.
S.
Manzhos
and T.
Carrington
, “A random-sampling high dimensional model representation neural network for building potential energy surfaces
,” J. Chem. Phys.
125
, 084109
(2006
).17.
S.
Manzhos
, X.
Wang
, R.
Dawes
, and T.
Carrington
, “A nested molecule-independent neural network approach for high-quality potential fits
,” J. Phys. Chem. A
110
, 5295
–5304
(2006
).18.
S.
Manzhos
, R.
Dawes
, and T.
Carrington
, “Neural network-based approaches for building high dimensional and quantum dynamics-friendly potential energy surfaces
,” Int. J. Quantum Chem.
115
, 1012
–1020
(2015
).19.
S.
Manzhos
and T.
Carrington
, “Neural network potential energy surfaces for small molecules and reactions
,” Chem. Rev.
121
, 10187
–10217
(2020
).20.
G.
Schmitz
, I. H.
Godtliebsen
, and O.
Christiansen
, “Machine learning for potential energy surfaces: An extensive database and assessment of methods
,” J. Chem. Phys.
150
, 244113
(2019
).21.
A.
Kamath
, R. A.
Vargas-Hernández
, R. V.
Krems
, T.
Carrington
, and S.
Manzhos
, “Neural networks vs Gaussian process regression for representing potential energy surfaces: A comparative study of fit quality and vibrational spectrum accuracy
,” J. Chem. Phys.
148
, 241702
(2018
).22.
C. E.
Rasmussen
and C. K. I.
Williams
, Gaussian Processes for Machine Learning (The MIT Press, 2005).23.
S. J.
Pan
and Q.
Yang
, “A survey on transfer learning
,” IEEE Trans. Knowl. Data Eng.
22
, 1345
–1359
(2010
).24.
P.
Perdikaris
, M.
Raissi
, A.
Damianou
, N. D.
Lawrence
, and G. E.
Karniadakis
, “Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling
,” Proc. R. Soc. A
473
, 20160751
(2017
).25.
R.
Batra
, G.
Pilania
, B. P.
Uberuaga
, and R.
Ramprasad
, “Multifidelity information fusion with machine learning: A case study of dopant formation energies in Hafnia
,” ACS Appl. Mater. Interfaces
11
, 24906
–24918
(2019
).26.
A. E.
Wiens
, A. V.
Copan
, and H. F.
Schaefer
, “Multi-fidelity Gaussian process modeling for chemical energy surfaces
,” Chem. Phys. Lett.: X
737
, 100022
(2019
).27.
M.
Malshe
, A.
Pukrittayakamee
, L. M.
Raff
, M.
Hagan
, S.
Bukkapatnam
, and R.
Komanduri
, “Accurate prediction of higher-level electronic structure energies for large databases using neural networks, Hartree–Fock energies, and small subsets of the database
,” J. Chem. Phys.
131
, 124127
(2009
).28.
J. S.
Smith
, B. T.
Nebgen
, R.
Zubatyuk
, N.
Lubbers
, C.
Devereux
, K.
Barros
, S.
Tretiak
, O.
Isayev
, and A. E.
Roitberg
, “Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning
,” Nat. Commun.
10
, 2903
(2019
).29.
R.
Ramakrishnan
, P. O.
Dral
, M.
Rupp
, and O. A.
von Lilienfeld
, “Big data meets quantum chemistry approximations: The Δ-machine learning approach
,” J. Chem. Theory Comput.
11
, 2087
–2096
(2015
).30.
A.
Nandi
, C.
Qu
, P. L.
Houston
, R.
Conte
, and J. M.
Bowman
, “Δ-Machine learning for potential energy surfaces: A PIP approach to bring a DFT-based PES to CCSD(T) level of theory
,” J. Chem. Phys.
154
, 051102
(2021
).31.
X.
Meng
and G. E.
Karniadakis
, “A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems
,” J. Comput. Phys.
401
, 109020
(2020
).32.
A. S.
Abbott
, J. M.
Turney
, B.
Zhang
, D. G. A.
Smith
, D.
Altarawy
, and H. F.
Schaefer
, “PES-learn: An open-source software package for the automated generation of machine learning models of molecular potential energy surfaces
,” J. Chem. Theory Comput.
15
, 4386
–4398
(2019
).33.
I.
Shavitt
and R. J.
Bartlett
, Many-Body Methods in Chemistry and Physics: MBPT and Coupled-Cluster Theory
(Cambridge University Press
, 2009
).34.
J. F.
Stanton
, “Why CCSD(T) works: A different perspective
,” Chem. Phys. Lett.
281
, 130
–134
(1997
).35.
T. H.
Dunning
, “Gaussian basis sets for use in correlated molecular calculations. I. The atoms boron through neon and hydrogen
,” J. Chem. Phys.
90
, 1007
–1023
(1989
).36.
I. M.
Sobol’
, “On the distribution of points in a cube and the approximate evaluation of integrals
,” USSR Comput. Math. Math. Phys.
7
, 86
–112
(1967
).37.
J.
Matoušek
, “On the L2-discrepancy for anchored boxes
,” Complexity
14
, 527
–556
(1998
).38.
A. B.
Owen
, “Scrambling Sobol’ and Niederreiter–Xing points
,” Complexity
14
, 466
–489
(1998
).39.
S.
Joe
and F. Y.
Kuo
, “Constructing Sobol sequences with better two-dimensional projections
,” SIAM J. Sci. Comput.
30
, 2635
–2654
(2008
).40.
D. G. A.
Smith
, L. A.
Burns
, A. C.
Simmonett
, R. M.
Parrish
, M. C.
Schieber
, R.
Galvelis
, P.
Kraus
, H.
Kruse
, R.
Di Remigio
, A.
Alenaizan
, A. M.
James
, S.
Lehtola
, J. P.
Misiewicz
, M.
Scheurer
, R. A.
Shaw
, J. B.
Schriber
, Y.
Xie
, Z. L.
Glick
, D. A.
Sirianni
, J. S.
O’Brien
, J. M.
Waldrop
, A.
Kumar
, E. G.
Hohenstein
, B. P.
Pritchard
, B. R.
Brooks
, H. F.
Schaefer
III, A. Y.
Sokolov
, K.
Patkowski
, A. E.
DePrince
III, U.
Bozkaya
, R. A.
King
, F. A.
Evangelista
, J. M.
Turney
, T. D.
Crawford
, and C. D.
Sherrill
, “PSI4 1.4: Open-source software for high-throughput quantum chemistry
,” J. Chem. Phys.
152
, 184108
(2020
).41.
B. J.
Braams
and J. M.
Bowman
, “Permutationally invariant potential energy surfaces in high dimensionality
,” Int. Rev. Phys. Chem.
28
, 577
–606
(2009
).42.
Z.
Xie
and J. M.
Bowman
, “Permutationally invariant polynomial basis for molecular energy surface fitting via monomial symmetrization
,” J. Chem. Theory Comput.
6
, 26
–34
(2010
).43.
B.
Jiang
and H.
Guo
, “Permutation invariant polynomial neural network approach to fitting potential energy surfaces
,” J. Chem. Phys.
139
, 054112
(2013
).44.
B.
Jiang
, J.
Li
, and H.
Guo
, “Potential energy surfaces from high fidelity fitting of ab initio points: The permutation invariant polynomial - neural network approach
,” Int. Rev. Phys. Chem.
35
, 479
–506
(2016
).45.
© 2023 Author(s). Published under an exclusive license by AIP Publishing.
2023
Author(s)
You do not currently have access to this content.