Neural network-based machine learning is capable of approximating functions in very high dimension with unprecedented efficiency and accuracy. This has opened up many exciting new possibilities, one of which is to use machine learning algorithms to assist multi-scale modeling. In this review, we use three examples to illustrate the process involved in using machine learning in multi-scale modeling: ab initio molecular dynamics, ab initio meso-scale models, such as Landau models and generalized Langevin equation, and hydrodynamic models for non-Newtonian flows.
REFERENCES
1.
Barducci
, A.
, Bonomi
, M.
, and Parrinello
, M.
, “Metadynamics
,” Wiley Interdiscip. Rev.: Comput. Mol. Sci.
1
(5
), 826
–843
(2011
).2.
Barducci
, A.
, Bussi
, G.
, and Parrinello
, M.
, “Well-tempered metadynamics: A smoothly converging and tunable free-energy method
,” Phys. Rev. Lett.
100
, 020603
(2008
).3.
Behler
, J.
and Parrinello
, M.
, “Generalized neural-network representation of high-dimensional potential-energy surfaces
,” Phys. Rev. Lett.
98
(14
), 146401
(2007
).4.
Berkowitz
, M.
, Morgan
, J. D.
, Kouri
, D. J.
, and McCammon
, J. A.
, “Memory kernels from molecular dynamics
,” J. Chem. Phys.
75
(5
), 2462
–2463
(1981
).5.
Bird
, R. B.
, Bird
, R. B.
, Armstrong
, R. C.
, and Hassager
, O.
, Dynamics of Polymeric Liquids
, Fluid Mechanics Vol. 1
(Wiley
, 1987
).6.
Byron Bird
, R.
, Curtiss
, C. F.
, Armstrong
, R. C.
, and Hassager
, O.
, Dynamics of Polymeric Liquids
, 2nd ed.
, Kinetic Theory Vol. 2
(Wiley
, 1987
).7.
Car
, R.
and Parrinello
, M.
, “Unified approach for molecular dynamics and density-functional theory
,” Phys. Rev. Lett.
55
, 2471
–2474
(1985
).8.
Chandra
, P.
and Littlewood
, P. B.
, “A Landau primer for ferroelectrics
,” in Physics of Ferroelectrics
(Springer
, 2007
), pp. 69
–116
.9.
Chen
, L.-Q.
, “Phase-field models for microstructure evolution
,” Annu. Rev. Mater. Res.
32
(1
), 113
–140
(2002
).10.
Davtyan
, A.
, Dama
, J. F.
, Voth
, G. A.
, and Andersen
, H. C.
, “Dynamic force matching: A method for constructing dynamical coarse-grained models with realistic time dependence
,” J. Chem. Phys.
142
(15
), 154104
(2015
).11.
Doi
, M.
and Edwards
, S. F.
, The Theory of Polymer Dynamics
, International Series of Monographs on Physics
(Clarendon Press
, 1988
).12.
13.
E
, W.
, “A mathematical and scientific perspective of machine learning
,” in Proceedings of the International Congress of Mathematicians
, 2022
.14.
E
, W.
and Engquist
, B.
, “The heterogeneous multi-scale methods
,” Commun. Math. Sci.
1
, 87
(2003
).15.
Eriksson
, O.
, Bergman
, A.
, Bergqvist
, L.
, and Hellsvik
, J.
, Atomistic Spin Dynamics: Foundations and Applications
(Oxford University Press
, 2017
).16.
Fang
, L.
, Ge
, P.
, Zhang
, L.
, E
, W.
, and Lei
, H.
, “DeePN2: A deep learning-based non-Newtonian hydrodynamic model
,” J. Mach. Learn.
1
, 114
–140
(2022
).17.
Fricks
, J.
, Yao
, L.
, Elston
, T. C.
, and Forest
, M. G.
, “Time-domain methods for diffusive transport in soft matter
,” SIAM J. Appl. Math.
69
(5
), 1277
–1308
(2009
).18.
Han
, J.
, Ma
, C.
, Ma
, Z.
, and E
, W.
, “Uniformly accurate machine learning-based hydrodynamic models for kinetic equations
,” Proc. Natl. Acad. Sci. U. S. A.
116
(44
), 21983
–21991
(2019
).19.
Han
, J.
, Zhang
, L.
, Car
, R.
, and E
, W.
, “Deep potential: A general representation of a many-body potential energy surface
,” Commun. Comput. Phys.
23
(3
), 629
–639
(2018
).20.
He
, L.
and Vanderbilt
, D.
, “First-principles study of oxygen-vacancy pinning of domain walls in PbTiO3
,” Phys. Rev. B
68
, 134103
(2003
).21.
Hohenberg
, P. C.
and Halperin
, B. I.
, “Theory of dynamic critical phenomena
,” Rev. Mod. Phys.
49
(3
), 435
(1977
).22.
Horenko
, I.
, Hartmann
, C.
, Schütte
, C.
, and Noe
, F.
, “Data-based parameter estimation of generalized multidimensional Langevin processes
,” Phys. Rev. E
76
, 016706
(2007
).23.
Íñiguez
, J.
, Ivantchev
, S.
, Perez-Mato
, J. M.
, and García
, A.
, “Devonshire-Landau free energy of BaTiO3 from first principles
,” Phys. Rev. B
63
, 144103
(2001
).24.
Izvekov
, S.
and Voth
, G. A.
, “A multiscale coarse-graining method for biomolecular systems
,” J. Phys. Chem. B
109
(7
), 2469
–2473
(2005
).25.
Jia
, W.
, Wang
, H.
, Chen
, M.
, Lu
, D.
, Lin
, L.
, Car
, R.
, E
, W.
, and Zhang
, L.
, “Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning
,” in SC20: International Conference for High Performance Computing, Networking, Storage and Analysis
(IEEE
, 2020
), pp. 1
–14
.26.
Kubo
, R.
, “The fluctuation-dissipation theorem
,” Rep. Prog. Phys.
29
(1
), 255
(1966
).27.
Lei
, H.
, Baker
, N. A.
, and Li
, X.
, “Data-driven parameterization of the generalized Langevin equation
,” Proc. Natl. Acad. Sci. U. S. A.
113
(50
), 14183
–14188
(2016
).28.
Lei
, H.
, Wu
, L.
, and E
, W.
, “Machine learning based non-Newtonian fluid model with molecular fidelity
,” Phys. Rev. E
102
, 043309
(2020
).29.
Lifshitz
, E. M.
and Pitaevskii
, L. P.
, Statistical Physics: Theory of the Condensed State
(Elsevier
, 2013
), Vol. 9
.30.
Liu
, S.
, Grinberg
, I.
, and Rappe
, A. M.
, “Intrinsic ferroelectric switching from first principles
,” Nature
534
(7607
), 360
–363
(2016
).31.
Lu
, D.
, Wang
, H.
, Chen
, M.
, Lin
, L.
, Car
, R.
, E
, W.
, Jia
, W.
, and Zhang
, L.
, “86 PFLOPS deep potential molecular dynamics simulation of 100 million atoms with ab initio accuracy
,” Comput. Phys. Commun.
259
, 107624
(2021
).32.
Meyer
, B.
and Vanderbilt
, D.
, “Ab initio study of ferroelectric domain walls in PbTiO3
,” Phys. Rev. B
65
, 104111
(2002
).33.
Oldroyd
, J. G.
and Wilson
, A. H.
, “On the formulation of rheological equations of state
,” Proc. R. Soc. London, Ser. A
200
(1063
), 523
–541
(1950
).34.
Padilla
, J.
, Zhong
, W.
, and Vanderbilt
, D.
, “First-principles investigation of 180° domain walls in BaTiO3
,” Phys. Rev. B
53
, R5969
–R5973
(1996
).35.
Resta
, R.
and Vanderbilt
, D.
, Theory of Polarization: A Modern Approach
(Springer
, Berlin, Heidelberg
, 2007
), pp. 31
–68
.36.
Rouse
, P. E.
, “A theory of the linear viscoelastic properties of dilute solutions of coiling polymers
,” J. Chem. Phys.
21
(7
), 1272
–1280
(1953
).37.
She
, Z.
, Ge
, P.
, and Lei
, H.
, “Data-driven construction of stochastic reduced dynamics encoded with non-Markovian features
,” J. Chem. Phys.
158
(3
), 034102
(2023
).38.
Shin
, Y.-H.
, Grinberg
, I.
, Chen
, I.-W.
, and Rappe
, A. M.
, “Nucleation and growth mechanism of ferroelectric domain-wall motion
,” Nature
449
(7164
), 881
–884
(2007
).39.
Valsson
, O.
and Parrinello
, M.
, “Variational approach to enhanced sampling and free energy calculations
,” Phys. Rev. Lett.
113
, 090601
(2014
).40.
Warner
, H. R.
, “Kinetic theory and rheology of dilute suspensions of finitely extendible dumbbells
,” Ind. Eng. Chem. Fundam.
11
(3
), 379
–387
(1972
).41.
Warshel
, A.
and Levitt
, M.
, “Theoretical studies of enzymic reactions: Dielectric, electrostatic and steric stabilization of the carbonium ion in the reaction of lysozyme
,” J. Mol. Biol.
103
(2
), 227
–249
(1976
).42.
43.
Xie
, P.
, Chen
, Y.
, E
, W.
, and Car
, R.
, “Ab initio multi-scale modeling of ferroelectrics: The case of PbTiO3
,” arXiv:2205.11839 (2022
).44.
Zaremba
, S.
, “Sur une forme perfectionee de la theorie de la relaxation
,” Bull. Int. Acad. Sci. Cracovie
, 594
–614
(1903
).45.
Zhang
, L.
, Chen
, M.
, Wu
, X.
, Wang
, H.
, E
, W.
, and Car
, R.
, “Deep neural network for the dielectric response of insulators
,” Phys. Rev. B
102
, 041121
(2020
).46.
Zhang
, L.
, Han
, J.
, Wang
, H.
, Car
, R.
, and E
, W.
, “Deep potential molecular dynamics: A scalable model with the accuracy of quantum mechanics
,” Phys. Rev. Lett.
120
, 143001
(2018
).47.
Zhang
, L.
, Han
, J.
, Wang
, H.
, Car
, R.
, and E
, W.
, “DeePCG: Constructing coarse-grained models via deep neural networks
,” J. Chem. Phys.
149
(3
), 034101
(2018
).48.
Zhang
, L.
, Han
, J.
, Wang
, H.
, Saidi
, W. A.
, Car
, R.
, and E
, W.
, “End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems
,” in Advances of the Neural Information Processing Systems (NIPS)
, 2018
.49.
Zhang
, L.
, Lin
, D.-Y.
, Wang
, H.
, Car
, R.
, and E
, W.
, “Active learning of uniformly accurate interatomic potentials for materials simulation
,” Phys. Rev. Mater.
3
(2
), 023804
(2019
).50.
Zhang
, Y.
, Sun
, J.
, Perdew
, J. P.
, and Wu
, X.
, “Comparative first-principles studies of prototypical ferroelectric materials by LDA, GGA, and SCAN meta-GGA
,” Phys. Rev. B
96
, 035143
(2017
).51.
© 2023 Author(s). Published under an exclusive license by AIP Publishing.
2023
Author(s)
You do not currently have access to this content.
