The prediction of the thermodynamic and kinetic properties of chemical reactions is increasingly being addressed by machine-learning (ML) methods, such as artificial neural networks (ANNs). While a number of recent studies have reported success in predicting chemical reaction activation energies, less attention has been focused on how the accuracy of ML predictions filters through to predictions of macroscopic observables. Here, we consider the impact of the uncertainty associated with ML prediction of activation energies on observable properties of chemical reaction networks, as given by microkinetics simulations based on ML-predicted reaction rates. After training an ANN to predict activation energies, given standard molecular descriptors for reactants and products alone, we performed microkinetics simulations of three different prototypical reaction networks: formamide decomposition, aldol reactions, and decomposition of 3-hydroperoxypropanal. We find that the kinetic modeling predictions can be in excellent agreement with corresponding simulations performed with ab initio calculations, but this is dependent on the inherent energetic landscape of the networks. We use these simulations to suggest some guidelines for when ML-based activation energies can be reliable and when one should take more care in applications to kinetics modeling.
REFERENCES
1.
C. A.
Class
, M.
Liu
, A. G.
Vandeputte
, and W. H.
Green
, “Automatic mechanism generation for pyrolysis of di-tert-butyl sulfide
,” Phys. Chem. Chem. Phys.
18
, 21651
–21658
(2016
).2.
G. N.
Simm
and M.
Reiher
, “Context-driven exploration of complex chemical reaction networks
,” J. Chem. Theory Comput.
13
, 6108
–6119
(2017
).3.
Y.
Kim
, J. W.
Kim
, Z.
Kim
, and W. Y.
Kim
, “Efficient prediction of reaction paths through molecular graph and reaction network analysis
,” Chem. Sci.
9
, 825
–835
(2018
).4.
G. N.
Simm
, A. C.
Vaucher
, and M.
Reiher
, “Exploration of reaction pathways and chemical transformation networks
,” J. Phys. Chem. A
123
, 385
–399
(2019
).5.
F.
Pietrucci
and A. M.
Saitta
, “Formamide reaction network in gas phase and solution via a unified theoretical approach: Toward a reconciliation of different prebiotic scenarios
,” Proc. Natl. Acad. Sci. U. S. A.
112
, 15030
(2015
).6.
J.
Proppe
and M.
Reiher
, “Mechanism deduction from noisy chemical reaction networks
,” J. Chem. Theory Comput.
15
, 357
–370
(2019
).7.
A. L.
Dewyer
, A. J.
Argüelles
, and P. M.
Zimmerman
, “Methods for exploring reaction space in molecular systems
,” Wiley Interdiscip. Rev.: Comput. Mol. Sci.
8
, e1354
(2018
).8.
C.
Robertson
, I.
Ismail
, and S.
Habershon
, “Traversing dense networks of elementary chemical reactions to predict minimum-energy reaction mechanisms
,” ChemSystemsChem
2
, e1900047
(2020
).9.
C.
Robertson
, R.
Hyland
, A. J. D.
Lacey
, S.
Havens
, and S.
Habershon
, “Identifying barrierless mechanisms for benzene formation in the interstellar medium using permutationally invariant reaction discovery
,” J. Chem. Theory Comput.
17
, 2307
–2322
(2021
).10.
I.
Ismail
, H. B. V. A.
Stuttaford-Fowler
, C.
Ochan Ashok
, C.
Robertson
, and S.
Habershon
, “Automatic proposal of multistep reaction mechanisms using a graph-driven search
,” J. Phys. Chem. A
123
, 3407
–3417
(2019
).11.
C.
Robertson
and S.
Habershon
, “Fast screening of homogeneous catalysis mechanisms using graph-driven searches and approximate quantum chemistry
,” Catal. Sci. Technol.
9
, 6357
–6369
(2019
).12.
S.
Habershon
, “Automated prediction of catalytic mechanism and rate law using graph-based reaction path sampling
,” J. Chem. Theory Comput.
12
, 1786
–1798
(2016
).13.
L. E.
Rush
, P. G.
Pringle
, and J. N.
Harvey
, “Computational kinetics of cobalt-catalyzed hydroformylation
,” Angew. Chem., Int. Ed.
53
, 8672
–8676
(2014
).14.
D. T.
Gillespie
, A.
Hellander
, and L. R.
Petzold
, “Perspective: Stochastic algorithms for chemical kinetics
,” J. Chem. Phys.
138
, 170901
(2013
).15.
J. A.
Miller
and S. J.
Klippenstein
, “Master equation methods in gas phase chemical kinetics
,” J. Phys. Chem. A
110
, 10528
–10544
(2006
).16.
C. J.
Pope
and J. A.
Miller
, “Exploring old and new benzene formation pathways in low-pressure premixed flames of aliphatic fuels
,” Proc. Combust. Inst.
28
, 1519
–1527
(2000
).17.
18.
G. R.
Wittreich
, K.
Alexopoulos
, and D. G.
Vlachos
, “Microkinetic modeling of surface catalysis
,” in Handbook of Materials Modeling: Applications: Current and Emerging Materials
, edited by W.
Andreoni
and S.
Yip
(Springer International Publishing
, Cham
, 2020
), pp. 1377
–1404
.19.
S.
Blau
, H.
Patel
, E.
Spotte-Smith
, X.
Xie
, S.
Dwaraknath
, and K.
Persson
, “A chemically consistent graph architecture for massive reaction metworks applied to solid-electrolyte interphase formation
,” Chem. Sci.
12
(13
), 4931
–4939
(2021
).20.
D. G.
Truhlar
, B. C.
Garrett
, and S. J.
Klippenstein
, “Current status of transition-state theory
,” J. Phys. Chem.
100
, 12771
–12800
(1996
).21.
K. J.
Laidler
and M. C.
King
, “Development of transition-state theory
,” J. Phys. Chem.
87
, 2657
–2664
(1983
).22.
N. E.
Henriksen
and F. Y.
Hansen
, Theories of Molecular Reaction Dynamics: The Microscopic Foundation of Chemical Kinetics
(Oxford University Press
, 2011
).23.
C. F.
Goldsmith
and R. H.
West
, “Automatic generation of microkinetic mechanisms for heterogeneous catalysis
,” J. Phys. Chem. C
121
, 9970
–9981
(2017
).24.
L.
Zhang
, Y.-Q.
Su
, M.-W.
Chang
, I. A. W.
Filot
, and E. J. M.
Hensen
, “Linear activation energy-reaction energy relations for LaBO3 (B = Mn, Fe, Co, Ni) supported single-atom platinum group metal catalysts for CO oxidation
,” J. Phys. Chem. C
123
, 31130
–31141
(2019
).25.
M.
Besora
and F.
Maseras
, “Microkinetic modeling in homogeneous catalysis
,” Wiley Interdiscip. Rev.: Comput. Mol. Sci.
8
, e1372
(2018
).26.
D. T.
Gillespie
, “Stochastic simulation of chemical kinetics
,” Annu. Rev. Phys. Chem.
58
, 35
–55
(2007
).27.
D. T.
Gillespie
, “Exact stochastic simulation of coupled chemical reactions
,” J. Phys. Chem.
81
, 2340
–2361
(1977
).28.
D. T.
Gillespie
, “A general method for numerically simulating the stochastic time evolution of coupled chemical reactions
,” J. Comput. Phys.
22
, 403
–434
(1976
).29.
C. W.
Gao
, J. W.
Allen
, W. H.
Green
, and R. H.
West
, “Reaction Mechanism Generator: Automatic construction of chemical kinetic mechanisms
,” Comput. Phys. Commun.
203
, 212
–225
(2016
).30.
M.
Keçeli
, S. N.
Elliott
, Y.-P.
Li
, M. S.
Johnson
, C.
Cavallotti
, Y.
Georgievskii
, W. H.
Green
, M.
Pelucchi
, J. M.
Wozniak
, A. W.
Jasper
, and S. J.
Klippenstein
, “Automated computational thermochemistry for butane oxidation: A prelude to predictive automated combustion kinetics
,” Proc. Combust. Inst.
37
, 363
–371
(2019
).31.
R. J.
Gillis
and W. H.
Green
, “Thermochemistry prediction and automatic reaction mechanism generation for oxygenated sulfur systems: A case study of dimethyl sulfide oxidation
,” ChemSystemsChem
2
, e1900051
(2020
).32.
C. A.
Grambow
, A.
Jamal
, Y.-P.
Li
, W. H.
Green
, J.
Zádor
, and Y. V.
Suleimanov
, “Unimolecular reaction pathways of a γ-ketohydroperoxide from combined application of automated reaction discovery methods
,” J. Am. Chem. Soc.
140
, 1035
–1048
(2018
).33.
E.
Martínez-Núñez
, “An automated method to find transition states using chemical dynamics simulations
,” J. Comput. Chem.
36
, 222
–234
(2015
).34.
E.
Martínez-Núñez
, “An automated transition state search using classical trajectories initialized at multiple minima
,” Phys. Chem. Chem. Phys.
17
, 14912
–14921
(2015
).35.
J. A.
Varela
, S. A.
Vázquez
, and E.
Martínez-Núñez
, “An automated method to find reaction mechanisms and solve the kinetics in organometallic catalysis
,” Chem. Sci.
8
, 3843
–3851
(2017
).36.
A.
Rodríguez
, R.
Rodríguez‐Fernández
, S. A.
Vázquez
, G. L.
Barnes
, J. J. P.
Stewart
, and E.
Martínez‐Núñez
, “tsscds2018: A code for automated discovery of chemical reaction mechanisms and solving the kinetics
,” J. Comput. Chem.
39
, 1922
–1930
(2018
).37.
S.
Kopec
, E.
Martínez-Núñez
, J.
Soto
, and D.
Peláez
, “vdw-TSSCDS—An automated and global procedure for the computation of stationary points on intermolecular potential energy surfaces
,” Int. J. Quantum Chem.
119
, e26008
(2019
).38.
P. M.
Zimmerman
, “Automated discovery of chemically reasonable elementary reaction steps
,” J. Comput. Chem.
34
, 1385
–1392
(2013
).39.
P.
Zimmerman
, “Reliable transition state searches integrated with the growing string method
,” J. Chem. Theory Comput.
9
, 3043
–3050
(2013
).40.
J. P.
Unsleber
and M.
Reiher
, “The exploration of chemical reaction networks
,” Annu. Rev. Phys. Chem.
71
, 121
(2020
).41.
S.
Maeda
and K.
Ohno
, “Global mapping of equilibrium and transition structures on potential energy surfaces by the scaled hypersphere search method: Applications to ab initio surfaces of formaldehyde and propyne molecules
,” J. Phys. Chem. A
109
, 5742
–5753
(2005
).42.
K.
Ohno
and S.
Maeda
, “Automated exploration of reaction channels
,” Phys. Scr.
78
, 058122
(2008
).43.
S.
Maeda
and K.
Morokuma
, “Finding reaction pathways of type A + B → X: Toward systematic prediction of reaction mechanisms
,” J. Chem. Theory Comput.
7
, 2335
–2345
(2011
).44.
S.
Habershon
, “Sampling reactive pathways with random walks in chemical space: Applications to molecular dissociation and catalysis
,” J. Chem. Phys.
143
, 094106
(2015
).45.
L.-P.
Wang
, A.
Titov
, R.
McGibbon
, F.
Liu
, V. S.
Pande
, and T. J.
Martínez
, “Discovering chemistry with an ab initio nanoreactor
,” Nat. Chem.
6
, 1044
–1048
(2014
).46.
B.
Peters
, A.
Heyden
, A. T.
Bell
, and A.
Chakraborty
, “A growing string method for determining transition states: Comparison to the nudged elastic band and string methods
,” J. Chem. Phys.
120
, 7877
–7886
(2004
).47.
X.
Zhu
, K. C.
Thompson
, and T. J.
Martínez
, “Geodesic interpolation for reaction pathways
,” J. Chem. Phys.
150
, 164103
(2019
).48.
F.
Perini
, E.
Galligani
, and R. D.
Reitz
, “An analytical Jacobian approach to sparse reaction kinetics for computationally efficient combustion modeling with large reaction mechanisms
,” Energy Fuels
26
, 4804
–4822
(2012
).49.
C. K.
Westbrook
, W. J.
Pitz
, O.
Herbinet
, H. J.
Curran
, and E. J.
Silke
, “A comprehensive detailed chemical kinetic reaction mechanism for combustion of n-alkane hydrocarbons from n-octane to n-hexadecane
,” Combust. Flame
156
, 181
–199
(2009
).50.
J. A.
Miller
and C. F.
Melius
, “Kinetic and thermodynamic issues in the formation of aromatic compounds in flames of aliphatic fuels
,” Combust. Flame
91
, 21
–39
(1992
).51.
J.
Zeng
, L.
Cao
, M.
Xu
, T.
Zhu
, and J. Z. H.
Zhang
, “Complex reaction processes in combustion unraveled by neural network-based molecular dynamics simulation
,” Nat. Commun.
11
, 5713
(2020
).52.
S.
Stocker
, G.
Csányi
, K.
Reuter
, and J. T.
Margraf
, “Machine learning in chemical reaction space
,” Nat. Commun.
11
, 5505
(2020
).53.
M. E.
Jenkin
, S. M.
Saunders
, and M. J.
Pilling
, “The tropospheric degradation of volatile organic compounds: A protocol for mechanism development
,” Atmos. Environ.
31
, 81
–104
(1997
).54.
K.
Takahashi
and I.
Miyazato
, “Rapid estimation of activation energy in heterogeneous catalytic reactions via machine learning
,” J. Comput. Chem.
39
, 2405
–2408
(2018
).55.
S.
Choi
, Y.
Kim
, J. W.
Kim
, Z.
Kim
, and W. Y.
Kim
, “Feasibility of activation energy prediction of gas-phase reactions by machine learning
,” Chem. - Eur. J.
24
, 12354
–12358
(2018
).56.
C. A.
Grambow
, L.
Pattanaik
, and W. H.
Green
, “Deep learning of activation energies
,” J. Phys. Chem. Lett.
11
, 2992
–2997
(2020
).57.
Kernel Methods for Activation Energy Prediction.
58.
W.
Jiang
, X.
Xing
, X.
Zhang
, and M.
Mi
, “Prediction of combustion activation energy of NaOH/KOH catalyzed straw pyrolytic carbon based on machine learning
,” Renewable Energy
130
, 1216
–1225
(2019
).59.
J.
Xu
, X.-M.
Cao
, and P.
Hu
, “Improved prediction for the methane activation mechanism on rutile metal oxides by a machine learning model with geometrical descriptors
,” J. Phys. Chem. C
123
, 28802
–28810
(2019
).60.
D. C.
Elton
, Z.
Boukouvalas
, M. S.
Butrico
, M. D.
Fuge
, and P. W.
Chung
, “Applying machine learning techniques to predict the properties of energetic materials
,” Sci. Rep.
8
, 9059
(2018
).61.
C. A.
Grambow
, L.
Pattanaik
, and W. H.
Green
, “Reactants, products, and transition states of elementary chemical reactions based on quantum chemistry
,” Sci. Data
7
, 137
(2020
).62.
J. N.
Bronsted
, “Acid and basic catalysis
,” Chem. Rev.
5
, 231
–338
(1928
).63.
M. G.
Evans
and M.
Polanyi
, “Inertia and driving force of chemical reactions
,” Trans. Faraday Soc.
34
, 11
–24
(1938
).64.
J. E.
Sutton
and D. G.
Vlachos
, “Effect of errors in linear scaling relations and Brønsted–Evans–Polanyi relations on activity and selectivity maps
,” J. Catal.
338
, 273
–283
(2016
).65.
J. K.
Nørskov
, T.
Bligaard
, B.
Hvolbæk
, F.
Abild-Pedersen
, I.
Chorkendorff
, and C. H.
Christensen
, “The nature of the active site in heterogeneous metal catalysis
,” Chem. Soc. Rev.
37
, 2163
–2171
(2008
).66.
J. A.
Kammeraad
, J.
Goetz
, E. A.
Walker
, A.
Tewari
, and P. M.
Zimmerman
, “What does the machine learn? Knowledge representations of chemical reactivity
,” J. Chem. Inf. Model.
60
, 1290
–1301
(2020
).67.
D.
Rogers
and M.
Hahn
, “Extended-connectivity fingerprints
,” J. Chem. Inf. Model.
50
, 742
–754
(2010
).68.
H. L.
Morgan
, “The generation of a unique machine description for chemical structures—A technique developed at chemical abstracts service
,” J. Chem. Doc.
5
, 107
–113
(1965
).69.
P.
Schwaller
, D.
Probst
, A. C.
Vaucher
, V. H.
Nair
, T.
Laino
, and J.-L.
Reymond
, “Data-driven chemical reaction classification, fingerprinting and clustering using attention-based neural networks
,” Nat. Mach. Intell.
3
(2
), 144
–152
(2021
).70.
J. N.
Wei
, D.
Duvenaud
, and A.
Aspuru-Guzik
, “Neural networks for the prediction of organic chemistry reactions
,” ACS Cent. Sci.
2
, 725
–732
(2016
).71.
N.
Schneider
, D. M.
Lowe
, R. A.
Sayle
, and G. A.
Landrum
, “Development of a novel fingerprint for chemical reactions and its application to large-scale reaction classification and similarity
,” J. Chem. Inf. Model.
55
, 39
–53
(2015
).72.
C. E.
Rasmussen
and C. K.
Williams
, Gaussian Processes for Machine Learning
(The MIT Press
, Cambridge, MA
, 2006
).73.
V. S.
Nguyen
, H. L.
Abbott
, M. M.
Dawley
, T. M.
Orlando
, J.
Leszczynski
, and M. T.
Nguyen
, “Theoretical study of formamide decomposition pathways
,” J. Phys. Chem. A
115
, 841
–851
(2011
).74.
A. R.
Singh
, B. A.
Rohr
, J. A.
Gauthier
, and J. K.
Nørskov
, “Predicting chemical reaction barriers with a machine learning model
,” Catal. Lett.
149
, 2347
–2354
(2019
).75.
Q.
Zhao
, M.
Avdeev
, L.
Chen
, and S.
Shi
, “Machine learning prediction of activation energy in cubic Li-argyrodites with hierarchically encoding crystal structure-based (HECS) descriptors
,” Sci. Bull.
66
, 1401
(2021
).76.
C. W.
Coley
, W.
Jin
, L.
Rogers
, T. F.
Jamison
, T. S.
Jaakkola
, W. H.
Green
, R.
Barzilay
, and K. F.
Jensen
, “A graph-convolutional neural network model for the prediction of chemical reactivity
,” Chem. Sci.
10
, 370
–377
(2019
).77.
G.
Landrum
, Rdkit: Open-source cheminformatics software, 2016
.78.
F.
Pedregosa
, G.
Varoquaux
, A.
Gramfort
, V.
Michel
, B.
Thirion
, O.
Grisel
, M.
Blondel
, P.
Prettenhofer
, R.
Weiss
, V.
Dubourg
, J.
Vanderplas
, A.
Passos
, D.
Cournapeau
, M.
Brucher
, M.
Perrot
, and E.
Duchesnay
, “Scikit-learn: Machine learning in Python
,” J. Mach. Learn. Res.
12
, 2825
–2830
(2011
); avaialable at http://jmlr.org/papers/v12/pedregosa11a.html.79.
M.
Stone
, “Cross-validatory choice and assessment of statistical predictions
,” J. R. Stat. Soc. Ser. B
36
, 111
–147
(1974
).80.
A. P.
Bartók
, R.
Kondor
, and G.
Csányi
, “On representing chemical environments
,” Phys. Rev. B
87
, 184115
(2013
).81.
J.
Zádor
and H. N.
Najm
, “Kinbot 1.0: A code for automatic pes exploration
,” Technical Report, Sandia National Laboratories (SNL-CA)
, Livermore, CA
, 2013
.82.
A.
Jalan
, I. M.
Alecu
, R.
Meana-Pañeda
, J.
Aguilera-Iparraguirre
, K. R.
Yang
, S. S.
Merchant
, D. G.
Truhlar
, and W. H.
Green
, “New pathways for formation of acids and carbonyl products in low-temperature oxidation: The Korcek decomposition of γ-ketohydroperoxides
,” J. Am. Chem. Soc.
135
, 11100
(2013
).83.
S.
Ryu
, Y.
Kwon
, and W. Y.
Kim
, “A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification
,” Chem. Sci.
10
, 8438
–8446
(2019
).84.
A. A.
Peterson
, R.
Christensen
, and A.
Khorshidi
, “Addressing uncertainty in atomistic machine learning
,” Phys. Chem. Chem. Phys.
19
, 10978
–10985
(2017
).85.
G.
Scalia
, C. A.
Grambow
, B.
Pernici
, Y.-P.
Li
, and W. H.
Green
, “Evaluating scalable uncertainty estimation methods for deep learning-based molecular property prediction
,” J. Chem. Inf. Model.
60
, 2697
(2020
).© 2022 Author(s). Published under an exclusive license by AIP Publishing.
2022
Author(s)
You do not currently have access to this content.
