1932
0
  1. Home
  2. A-Z Publications
  3. Annual Review of Physical Chemistry
  4. Volume 75, 2024
  5. Article

Annual Review of Physical Chemistry

Volume 75, 2024

Machine Learning of Reactive Potentials

Abstract

In the past two decades, machine learning potentials (MLPs) have driven significant developments in chemical, biological, and material sciences. The construction and training of MLPs enable fast and accurate simulations and analysis of thermodynamic and kinetic properties. This review focuses on the application of MLPs to reaction systems with consideration of bond breaking and formation. We review the development of MLP models, primarily with neural network and kernel-based algorithms, and recent applications of reactive MLPs (RMLPs) to systems at different scales. We show how RMLPs are constructed, how they speed up the calculation of reactive dynamics, and how they facilitate the study of reaction trajectories, reaction rates, free energy calculations, and many other calculations. Different data sampling strategies applied in building RMLPs are also discussed with a focus on how to collect structures for rare events and how to further improve their performance with active learning.

Keyword(s): chemical reactions, computational chemistry, machine learning, neural networks, potential energy surface
Loading

Article metrics loading...

/content/journals/10.1146/annurev-physchem-062123-024417
2024-06-28
2024-10-11
Loading full text...

Full text loading...

/deliver/fulltext/physchem/75/1/annurev-physchem-062123-024417.html?itemId=/content/journals/10.1146/annurev-physchem-062123-024417&mimeType=html&fmt=ahah

Literature Cited

  1. 1.
    van Duin ACT, Dasgupta S, Lorant F, Goddard WA. 2001.. ReaxFF: a reactive force field for hydrocarbons. . J. Phys. Chem. A 105:(41):9396–409
     [Crossref] [Google Scholar]
  2. 2.
    Brenner DW, Shenderova OA, Harrison JA, Stuart SJ, Ni B, Sinnott SB. 2002.. A second-generation reactive empirical bond order (REBO) potential energy expression for hydrocarbons. . J. Phys. Condens. Matter 14:(4):783–802
     [Crossref] [Google Scholar]
  3. 3.
    Shin YK, Shan TR, Liang T, Noordhoek MJ, Sinnott SB, et al. 2012.. Variable charge many-body interatomic potentials. . MRS Bull. 37:(5):504–12
     [Crossref] [Google Scholar]
  4. 4.
    Senn HM, Thiel W. 2009.. QM/MM methods for biomolecular systems. . Angew. Chem. Int. Ed. 48:(7):1198–229
     [Crossref] [Google Scholar]
  5. 5.
    Meuwly M. 2019.. Reactive molecular dynamics: from small molecules to proteins. . WIREs Comput. Mol. Sci. 9:(1):e1386
     [Crossref] [Google Scholar]
  6. 6.
    Warshel A, Weiss RM. 1980.. An empirical valence bond approach for comparing reactions in solutions and in enzymes. . J. Am. Chem. Soc. 102:(6):218–26
     [Google Scholar]
  7. 7.
    Nagy T, Yosa Reyes J, Meuwly M. 2014.. Multisurface adiabatic reactive molecular dynamics. . J. Chem. Theory Comput. 10:(4):1366–75
     [Crossref] [Google Scholar]
  8. 8.
    Manzhos S, Carrington T. 2020.. Neural network potential energy surfaces for small molecules and reactions. . Chem. Rev. 121:(16):10187–217
     [Crossref] [Google Scholar]
  9. 9.
    Gkeka P, Stoltz G, Farimani AB, Belkacemi Z, Ceriotti M, et al. 2020.. Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems. . J. Chem. Theory Comput. 16:(8):4757–75
     [Crossref] [Google Scholar]
  10. 10.
    Deringer VL, Caro MA, Csányi G. 2019.. Machine learning interatomic potentials as emerging tools for materials science. . Adv. Mater. 31:(46):1902765
     [Crossref] [Google Scholar]
  11. 11.
    Xu J, Cao XM, Hu P. 2021.. Perspective on computational reaction prediction using machine learning methods in heterogeneous catalysis. . Phys. Chem. Chem. Phys. 23:(19):11155–79
     [Crossref] [Google Scholar]
  12. 12.
    Meuwly M. 2022.. Atomistic simulations for reactions and vibrational spectroscopy in the era of machine learning–quo vadis?. J. Phys. Chem. B 126:(11):2155–67
     [Crossref] [Google Scholar]
  13. 13.
    Meuwly M. 2021.. Machine learning for chemical reactions. . Chem. Rev. 121:(16):10218–39
     [Crossref] [Google Scholar]
  14. 14.
    Kocer E, Ko TW, Behler J. 2022.. Neural network potentials: a concise overview of methods. . Annu. Rev. Phys. Chem. 73::163–86
     [Crossref] [Google Scholar]
  15. 15.
    Anstine DM, Isayev O. 2023.. Machine learning interatomic potentials and long-range physics. . J. Phys. Chem. A 127:(11):2417–31
     [Crossref] [Google Scholar]
  16. 16.
    Ramakrishnan R, Dral PO, Rupp M, von Lilienfeld OA. 2015.. Big data meets quantum chemistry approximations: the Δ-machine learning approach. . J. Chem. Theory Comput. 11:(5):2087–96
     [Crossref] [Google Scholar]
  17. 17.
    Xue LY, Guo F, Wen YS, Feng SQ, Huang XN, et al. 2021.. ReaxFF-MPNN machine learning potential: a combination of reactive force field and message passing neural networks. . Phys. Chem. Chem. Phys. 23:(35):19457–64
     [Crossref] [Google Scholar]
  18. 18.
    Stoppelman JP, McDaniel JG. 2021.. Physics-based, neural network force fields for reactive molecular dynamics: investigation of carbene formation from [EMIM+][OAc−]. . J. Chem. Phys. 155:(10):104112
     [Crossref] [Google Scholar]
  19. 19.
    Musil F, Grisafi A, Bartók AP, Ortner C, Csányi G, Ceriotti M. 2021.. Physics-inspired structural representations for molecules and materials. . Chem. Rev. 121:(16):9759–815
     [Crossref] [Google Scholar]
  20. 20.
    Unke OT, Chmiela S, Sauceda HE, Gastegger M, Poltavsky I, et al. 2021.. Machine learning force fields. . Chem. Rev. 121:(16):10142–86
     [Crossref] [Google Scholar]
  21. 21.
    Gokcan H, Isayev O. 2022.. Learning molecular potentials with neural networks. . WIREs Comput. Mol. Sci. 12:(2):e1564
     [Crossref] [Google Scholar]
  22. 22.
    Käser S, Vazquez-Salazar LI, Meuwly M, Töpfer K. 2023.. Neural network potentials for chemistry: concepts, applications and prospects. . Digit. Discov. 2:(1):28–58
     [Crossref] [Google Scholar]
  23. 23.
    Yao K, Herr JE, Brown SN, Parkhill J. 2017.. Intrinsic bond energies from a bonds-in-molecules neural network. . J. Phys. Chem. Lett. 8:(12):2689–94
     [Crossref] [Google Scholar]
  24. 24.
    Rasmussen CE, Williams CKI. 2006.. Gaussian Processes for Machine Learning. Cambridge, MA:: MIT Press
     [Google Scholar]
  25. 25.
    Deringer VL, Bartók AP, Bernstein N, Wilkins DM, Ceriotti M, Csányi G. 2021.. Gaussian process regression for materials and molecules. . Chem. Rev. 121:(16):10073–141
     [Crossref] [Google Scholar]
  26. 26.
    Leithead WE, Zhang Y. 2007.. O(N2)-operation approximation of covariance matrix inverse in Gaussian process regression based on quasi-Newton BFGS method. . Commun. Stat. Simul. Comput. 36:(2):367–80
     [Crossref] [Google Scholar]
  27. 27.
    Kamath A, Vargas-Hernández RA, Krems RV, Carrington T, Manzhos S. 2018.. Neural networks versus Gaussian process regression for representing potential energy surfaces: a comparative study of fit quality and vibrational spectrum accuracy. . J. Chem. Phys. 148:(24):241702
     [Crossref] [Google Scholar]
  28. 28.
    Smith JS, Isayev O, Roitberg AE. 2017.. ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost. . Chem. Sci. 8:(4):3192–203
     [Crossref] [Google Scholar]
  29. 29.
    Jiang B, Guo H. 2013.. Permutation invariant polynomial neural network approach to fitting potential energy surfaces. . J. Chem. Phys. 139:(5):054112
     [Crossref] [Google Scholar]
  30. 30.
    Jiang B, Li J, Guo H. 2020.. High-fidelity potential energy surfaces for gas-phase and gas–surface scattering processes from machine learning. . J. Phys. Chem. Lett. 11:(13):5120–31
     [Crossref] [Google Scholar]
  31. 31.
    Shao K, Chen J, Zhao Z, Zhang DH. 2016.. Communication: fitting potential energy surfaces with fundamental invariant neural network. . J. Chem. Phys. 145:(7):071101
     [Crossref] [Google Scholar]
  32. 32.
    Qu C, Bowman JM. 2019.. A fragmented, permutationally invariant polynomial approach for potential energy surfaces of large molecules: application to N-methyl acetamide. . J. Chem. Phys. 150:(14):141101
     [Crossref] [Google Scholar]
  33. 33.
    Behler J, Parrinello M. 2007.. Generalized neural-network representation of high-dimensional potential-energy surfaces. . Phys. Rev. Lett. 98:(14):146401
     [Crossref] [Google Scholar]
  34. 34.
    Yao K, Herr JE, Toth DW, Mckintyre R, Parkhill J. 2018.. The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics. . Chem. Sci. 9:(8):2261–69
     [Crossref] [Google Scholar]
  35. 35.
    Gastegger M, Schwiedrzik L, Bittermann M, Berzsenyi F, Marquetand P. 2018.. wACSF—weighted atom-centered symmetry functions as descriptors in machine learning potentials. . J. Chem. Phys. 148:(24):241709
     [Crossref] [Google Scholar]
  36. 36.
    Liu M, Kitchin JR. 2020.. SingleNN: modified Behler–Parrinello neural network with shared weights for atomistic simulations with transferability. . J. Phys. Chem. C 124:(32):17811–18
     [Crossref] [Google Scholar]
  37. 37.
    Zhang L, Han J, Wang H, Car R, Weinan E. 2018.. Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics. . Phys. Rev. Lett. 120:(14):143001
     [Crossref] [Google Scholar]
  38. 38.
    Zhang L, Han J, Wang H, Saidi W, Car R, et al. 2018.. End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems. . Adv. Neural Inf. Process. Syst. 31::4436–46
     [Google Scholar]
  39. 39.
    Zhang Y, Hu C, Jiang B. 2019.. Embedded atom neural network potentials: efficient and accurate machine learning with a physically inspired representation. . J. Phys. Chem. Lett. 10:(17):4962–67
     [Crossref] [Google Scholar]
  40. 40.
    Jose KV, Artrith N, Behler J. 2012.. Construction of high-dimensional neural network potentials using environment-dependent atom pairs. . J. Chem. Phys. 136:(19):194111
     [Crossref] [Google Scholar]
  41. 41.
    Pozdnyakov SN, Willatt MJ, Bartók AP, Ortner C, Csányi G, Ceriotti M. 2020.. Incompleteness of atomic structure representations. . Phys. Rev. Lett. 125:(16):166001
     [Crossref] [Google Scholar]
  42. 42.
    Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE. 2017.. Neural message passing for quantum chemistry. . Proc. Mach. Learn. Res. 70::1263–72
     [Google Scholar]
  43. 43.
    Schütt KT, Arbabzadah F, Chmiela S, Müller KR, Tkatchenko A. 2017.. Quantum-chemical insights from deep tensor neural networks. . Nat. Commun. 8:(1):13890
     [Crossref] [Google Scholar]
  44. 44.
    Schütt KT, Sauceda HE, Kindermans P-J, Tkatchenko A, Müller K-R. 2018.. SchNet – a deep learning architecture for molecules and materials. . J. Chem. Phys. 148:(24):241722
     [Crossref] [Google Scholar]
  45. 45.
    Unke OT, Meuwly M. 2019.. PhysNet: a neural network for predicting energies, forces, dipole moments, and partial charges. . J. Chem. Theory Comput. 15:(6):3678–93
     [Crossref] [Google Scholar]
  46. 46.
    Zubatyuk R, Smith JS, Leszczynski J, Isayev O. 2019.. Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network. . Sci. Adv. 5:(8):eaav6490
     [Crossref] [Google Scholar]
  47. 47.
    Zubatyuk R, Smith JS, Nebgen BT, Tretiak S, Isayev O. 2021.. Teaching a neural network to attach and detach electrons from molecules. . Nat. Commun. 12:(1):4870
     [Crossref] [Google Scholar]
  48. 48.
    Batzner S, Musaelian A, Sun L, Geiger M, Mailoa JP, et al. 2022.. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. . Nat. Commun. 13:(1):2453
     [Crossref] [Google Scholar]
  49. 49.
    Lubbers N, Smith JS, Barros K. 2018.. Hierarchical modeling of molecular energies using a deep neural network. . J. Chem. Phys. 148:(24):241715
     [Crossref] [Google Scholar]
  50. 50.
    Schütt K, Unke O, Gastegger M. 2021.. Equivariant message passing for the prediction of tensorial properties and molecular spectra. . Proc. Mach. Learn. Res. 139::9377–88
     [Google Scholar]
  51. 51.
    Unke OT, Chmiela S, Gastegger M, Schütt KT, Sauceda HE, Müller K-R. 2021.. SpookyNet: learning force fields with electronic degrees of freedom and nonlocal effects. . Nat. Commun. 12:(1):7273
     [Crossref] [Google Scholar]
  52. 52.
    Bartók AP, Payne MC, Kondor R, Csányi G. 2010.. Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. . Phys. Rev. Lett. 104:(13):136403
     [Crossref] [Google Scholar]
  53. 53.
    Bartók AP, Kondor R, Csányi G. 2013.. On representing chemical environments. . Phys. Rev. B 87:(18):184115
     [Crossref] [Google Scholar]
  54. 54.
    Thompson AP, Swiler LP, Trott CR, Foiles SM, Tucker GJ. 2015.. Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials. . J. Comput. Phys. 285::316–30
     [Crossref] [Google Scholar]
  55. 55.
    Chmiela S, Sauceda HE, Müller K-R, Tkatchenko A. 2018.. Towards exact molecular dynamics simulations with machine-learned force fields. . Nat. Commun. 9:(1):3887
     [Crossref] [Google Scholar]
  56. 56.
    Drautz R. 2019.. Atomic cluster expansion for accurate and transferable interatomic potentials. . Phys. Rev. B 99:(1):014104
     [Crossref] [Google Scholar]
  57. 57.
    Shapeev AV. 2016.. Moment tensor potentials: a class of systematically improvable interatomic potentials. . Multiscale Model. Simul. 14:(3):1153–73
     [Crossref] [Google Scholar]
  58. 58.
    Pham CH, Lindsey RK, Fried LE, Goldman N. 2022.. High-accuracy semiempirical quantum models based on a minimal training set. . J. Phys. Chem. Lett. 13:(13):2934–42
     [Crossref] [Google Scholar]
  59. 59.
    Gastegger M, Schütt KT, Müller KR. 2021.. Machine learning of solvent effects on molecular spectra and reactions. . Chem. Sci. 12:(34):11473–83
     [Crossref] [Google Scholar]
  60. 60.
    Cao L, Zeng J, Wang B, Zhu T, Zhang JZH. 2022.. Ab initio neural network MD simulation of thermal decomposition of a high energy material CL-20/TNT. . Phys. Chem. Chem. Phys. 24:(19):11801–11
     [Crossref] [Google Scholar]
  61. 61.
    Brickel S, Das AK, Unke OT, Turan HT, Meuwly M. 2019.. Reactive molecular dynamics for the [Cl–CH3–Br]− reaction in the gas phase and in solution: a comparative study using empirical and neural network force fields. . Electron. Struct. 1:(2):024002
     [Crossref] [Google Scholar]
  62. 62.
    Rivero U, Unke OT, Meuwly M, Willitsch S. 2019.. Reactive atomistic simulations of Diels-Alder reactions: the importance of molecular rotations. . J. Chem. Phys. 151:(10):104301
     [Crossref] [Google Scholar]
  63. 63.
    Käser S, Unke OT, Meuwly M. 2020.. Reactive dynamics and spectroscopy of hydrogen transfer from neural network-based reactive potential energy surfaces. . New J. Phys. 22:(5):055002
     [Crossref] [Google Scholar]
  64. 64.
    Liu Y, Bai M, Song H, Xie D, Li J. 2019.. Anomalous kinetics of the reaction between OH and HO2 on an accurate triplet state potential energy surface. . Phys. Chem. Chem. Phys. 21:(23):12667–75
     [Crossref] [Google Scholar]
  65. 65.
    Jiang B, Guo H. 2014.. Permutation invariant polynomial neural network approach to fitting potential energy surfaces. III. Molecule-surface interactions. . J. Chem. Phys. 141:(3):034109
     [Crossref] [Google Scholar]
  66. 66.
    Xie C, Zhu X, Yarkony DR, Guo H. 2018.. Permutation invariant polynomial neural network approach to fitting potential energy surfaces. IV. Coupled diabatic potential energy matrices. . J. Chem. Phys. 149:(14):144107
     [Crossref] [Google Scholar]
  67. 67.
    Le HM, Huynh S, Raff LM. 2009.. Molecular dissociation of hydrogen peroxide (HOOH) on a neural network ab initio potential surface with a new configuration sampling method involving gradient fitting. . J. Chem. Phys. 131:(1):014107
     [Crossref] [Google Scholar]
  68. 68.
    Nguyen-Truong HT, Thi CM, Le HM. 2013.. Theoretical investigations of BBS (singlet)→BSB (triplet) transformation on a potential energy surface obtained from neural network fitting. . Chem. Phys. 426::31–37
     [Crossref] [Google Scholar]
  69. 69.
    Liu Y, Li J. 2019.. An accurate potential energy surface and ring polymer molecular dynamics study of the Cl + CH4 → HCl + CH3 reaction. . Phys. Chem. Chem. Phys. 22:(1):344–53
     [Crossref] [Google Scholar]
  70. 70.
    Lu X, Wang X, Fu B, Zhang D. 2019.. Theoretical investigations of rate coefficients of H + H2O2 → OH + H2O on a full-dimensional potential energy surface. . J. Phys. Chem. A 123:(18):3969–76
     [Crossref] [Google Scholar]
  71. 71.
    Zhang Y, Lin Q, Jiang B. 2023.. Atomistic neural network representations for chemical dynamics simulations of molecular, condensed phase, and interfacial systems: efficiency, representability, and generalization. . WIREs Comput. Mol. Sci. 13:(3):e1645
     [Crossref] [Google Scholar]
  72. 72.
    Young TA, Johnston-Wood T, Deringer VL, Duarte F. 2021.. A transferable active-learning strategy for reactive molecular force fields. . Chem. Sci. 12:(32):10944–55
     [Crossref] [Google Scholar]
  73. 73.
    Piskor T, Pinski P, Mast T, Rybkin VV. 2023.. Multi-scale protocol for mechanistic reaction studies using semi-local fitted potential energy surfaces. . arXiv:2304.00942 [physics.chem-ph]
  74. 74.
    Lu X, Li L, Zhang X, Fu B, Xu X, Zhang DH. 2022.. Dynamical effects of SN2 reactivity suppression by microsolvation: dynamics simulations of the F−(H2O) + CH3I reaction on a 21-dimensional potential energy surface. . J. Phys. Chem. 13:(23):5253–59
     [Google Scholar]
  75. 75.
    Lu X, Shang C, Li L, Chen R, Fu B, et al. 2022.. Unexpected steric hindrance failure in the gas phase F− + (CH3)3CI SN2 reaction. . Nat. Commun. 13:(1):4427
     [Crossref] [Google Scholar]
  76. 76.
    Eckhoff M, Reiher M. 2023.. Lifelong machine learning potentials. . J. Chem. Theory Comput. 19:(12):3509–25
     [Crossref] [Google Scholar]
  77. 77.
    Li J, Stein R, Adrion DM, Lopez SA. 2021.. Machine-learning photodynamics simulations uncover the role of substituent effects on the photochemical formation of cubanes. . J. Am. Chem. Soc. 143:(48):20166–75
     [Crossref] [Google Scholar]
  78. 78.
    Gastegger M, Marquetand P. 2015.. High-dimensional neural network potentials for organic reactions and an improved training algorithm. . J. Chem. Theory Comput. 11:(5):2187–98
     [Crossref] [Google Scholar]
  79. 79.
    Young TA, Johnston-Wood T, Zhang H, Duarte F. 2022.. Reaction dynamics of Diels–Alder reactions from machine learned potentials. . Phys. Chem. Chem. Phys. 24:(35):20820–27
     [Crossref] [Google Scholar]
  80. 80.
    Ang SJ, Wang W, Schwalbe-Koda D, Axelrod S, Gómez-Bombarelli R. 2021.. Active learning accelerates ab initio molecular dynamics on reactive energy surfaces. . Chem 7:(3):738–51
     [Crossref] [Google Scholar]
  81. 81.
    Hare SR, Tantillo DJ. 2017.. Post-transition state bifurcations gain momentum – current state of the field. . Pure Appl. Chem. 89:(6):679–98
     [Crossref] [Google Scholar]
  82. 82.
    Zhang J, Zhang H, Qin Z, Kang Y, Hong X, Hou T. 2023.. Quasiclassical trajectory simulation as a protocol to build locally accurate machine learning potentials. . J. Chem. Inf. Model. 63:(4):1133–42
     [Crossref] [Google Scholar]
  83. 83.
    Westermayr J, Marquetand P. 2020.. Machine learning for electronically excited states of molecules. . Chem. Rev. 121:(16):9873–926
     [Crossref] [Google Scholar]
  84. 84.
    Li J, Lopez SA. 2022.. A look inside the black box of machine learning photodynamics simulations. . Acc. Chem. Res. 55:(14):1972–84
     [Crossref] [Google Scholar]
  85. 85.
    Richings GW, Habershon S. 2017.. Direct quantum dynamics using grid-based wave function propagation and machine-learned potential energy surfaces. . J. Chem. Theory Comput. 13:(9):4012–24
     [Crossref] [Google Scholar]
  86. 86.
    Westermayr J, Gastegger M, Marquetand P. 2020.. Combining SchNet and SHARC: the SchNarc machine learning approach for excited-state dynamics. . J. Phys. Chem. Lett. 11:(10):3828–34
     [Crossref] [Google Scholar]
  87. 87.
    Westermayr J, Gastegger M, Vörös D, Panzenboeck L, Joerg F, et al. 2022.. Deep learning study of tyrosine reveals that roaming can lead to photodamage. . Nat. Chem. 14:(8):914–19
     [Crossref] [Google Scholar]
  88. 88.
    Li J, Lopez SA. 2023.. Machine learning accelerated photodynamics simulations. . Chem. Phys. Rev. 4::031309
     [Crossref] [Google Scholar]
  89. 89.
    Li J, Reiser P, Boswell BR, Eberhard A, Burns NZ, et al. 2021.. Automatic discovery of photoisomerization mechanisms with nanosecond machine learning photodynamics simulations. . Chem. Sci. 12:(14):5302–14
     [Crossref] [Google Scholar]
  90. 90.
    Li J, Lopez SA. 2022.. Excited-state distortions promote the photochemical 4π-electrocyclizations of fluorobenzenes via machine learning accelerated photodynamics simulations. . Chem. Eur. J. 28:(38):e202200651
     [Crossref] [Google Scholar]
  91. 91.
    Chen X, Goldsmith CF. 2020.. Accelerating variational transition state theory via artificial neural networks. . J. Phys. Chem. A 124:(5):1038–46
     [Crossref] [Google Scholar]
  92. 92.
    Käser S, Unke OT, Meuwly M. 2020.. Isomerization and decomposition reactions of acetaldehyde relevant to atmospheric processes from dynamics simulations on neural network-based potential energy surfaces. . J. Chem. Phys. 152:(21):214304
     [Crossref] [Google Scholar]
  93. 93.
    Käser S, Richardson JO, Meuwly M. 2022.. Transfer learning for affordable and high-quality tunneling splittings from instanton calculations. . J. Chem. Theory Comput. 18:(11):6840–50
     [Crossref] [Google Scholar]
  94. 94.
    Houston P, Conte R, Qu C, Bowman JM. 2020.. Permutationally invariant polynomial potential energy surfaces for tropolone and H and D atom tunneling dynamics. . J. Chem. Phys. 153:(2):024107
     [Crossref] [Google Scholar]
  95. 95.
    Wang HD, Fu YL, Fu B, Fang W, Zhang DH. 2023.. A highly accurate full-dimensional ab initio potential surface for the rearrangement of methylhydroxycarbene (H3C−C−OH). . Phys. Chem. Chem. Phys. 25:(11):8117–27
     [Crossref] [Google Scholar]
  96. 96.
    Schreiner M, Bhowmik A, Vegge T, Jørgensen PB, Winther O. 2022.. NeuralNEB—Neural networks can find reaction paths fast. . Mach. Learn. Sci. Technol. 3:(4):045022
     [Crossref] [Google Scholar]
  97. 97.
    Schreiner M, Bhowmik A, Vegge T, Busk J, Winther O. 2022.. Transition1x - a dataset for building generalizable reactive machine learning potentials. . Sci. Data 9:(1):779
     [Crossref] [Google Scholar]
  98. 98.
    Reichardt C. 1982.. Solvent effects on chemical reactivity. . Pure Appl. Chem. 54:(10):1867–84
     [Crossref] [Google Scholar]
  99. 99.
    Shen L, Wu J, Yang W. 2016.. Multiscale quantum mechanics/molecular mechanics simulations with neural networks. . J. Chem. Theory Comput. 12:(10):4934–46
     [Crossref] [Google Scholar]
  100. 100.
    Wu J, Shen L, Yang W. 2017.. Internal force corrections with machine learning for quantum mechanics/molecular mechanics simulations. . J. Chem. Phys. 147:(16):161732
     [Crossref] [Google Scholar]
  101. 101.
    Böselt L, Thürlemann M, Riniker S. 2021.. Machine learning in QM/MM molecular dynamics simulations of condensed-phase systems. . J. Chem. Theory Comput. 17:(5):2641–58
     [Crossref] [Google Scholar]
  102. 102.
    Zeng J, Giese TJ, Ekesan S, York DM. 2021.. Development of range-corrected deep learning potentials for fast, accurate quantum mechanical/molecular mechanical simulations of chemical reactions in solution. . J. Chem. Theory Comput. 17:(11):6993–7009
     [Crossref] [Google Scholar]
  103. 103.
    Snyder R, Kim B, Pan X, Shao Y, Pu J. 2022.. Facilitating ab initio QM/MM free energy simulations by Gaussian process regression with derivative observations. . Phys. Chem. Chem. Phys. 24:(41):25134–43
     [Crossref] [Google Scholar]
  104. 104.
    Gómez-Flores CL, Maag D, Kansari M, Vuong VQ, Irle S, et al. 2022.. Accurate free energies for complex condensed-phase reactions using an artificial neural network corrected DFTB/MM methodology. . J. Chem. Theory Comput. 18:(2):1213–26
     [Crossref] [Google Scholar]
  105. 105.
    Pan X, Yang J, Van R, Epifanovsky E, Ho J, et al. 2021.. Machine-learning-assisted free energy simulation of solution-phase and enzyme reactions. . J. Chem. Theory Comput. 17:(9):5745–58
     [Crossref] [Google Scholar]
  106. 106.
    Töpfer K, Käser S, Meuwly M. 2022.. Double proton transfer in hydrated formic acid dimer: interplay of spatial symmetry and solvent-generated force on reactivity. . Phys. Chem. Chem. Phys. 24:(22):13869–82
     [Crossref] [Google Scholar]
  107. 107.
    Zhou B, Zhou Y, Xie D. 2023.. Accelerated quantum mechanics/molecular mechanics simulations via neural networks incorporated with mechanical embedding scheme. . J. Chem. Theory Comput. 19:(4):1157–69
     [Crossref] [Google Scholar]
  108. 108.
    Yang X, Zou J, Wang Y, Xue Y, Yang S. 2019.. Role of water in the reaction mechanism and endo/exo selectivity of 1,3-dipolar cycloadditions elucidated by quantum chemistry and machine learning. . Chem. Eur. J. 25:(35):8289–303
     [Crossref] [Google Scholar]
  109. 109.
    Yang M, Bonati L, Polino D, Parrinello M. 2022.. Using metadynamics to build neural network potentials for reactive events: the case of urea decomposition in water. . Catal. Today 387::143–49
     [Crossref] [Google Scholar]
  110. 110.
    Devergne T, Magrino T, Pietrucci F, Saitta AM. 2022.. Combining machine learning approaches and accurate ab initio enhanced sampling methods for prebiotic chemical reactions in solution. . J. Chem. Theory Comput. 18:(9):5410–21
     [Crossref] [Google Scholar]
  111. 111.
    Khaliullin RZ, Eshet H, Küehne TD, Behler J, Parrinello M. 2010.. Graphite-diamond phase coexistence study employing a neural-network mapping of the ab initio potential energy surface. . Phys. Rev. B 81:(10):100103
     [Crossref] [Google Scholar]
  112. 112.
    Perdew JP, Burke K, Ernzerhof M. 1996.. Generalized gradient approximation made simple. . Phys. Rev. Lett. 77:(18):3865–68
     [Crossref] [Google Scholar]
  113. 113.
    Wang J, Shen H, Yang R, Xie K, Zhang C, et al. 2022.. A deep learning interatomic potential developed for atomistic simulation of carbon materials. . Carbon 186::1–8
     [Crossref] [Google Scholar]
  114. 114.
    Rowe P, Deringer VL, Gasparotto P, Csányi G, Michaelides A. 2020.. An accurate and transferable machine learning potential for carbon. . J. Chem. Phys. 153:(3):034702
     [Crossref] [Google Scholar]
  115. 115.
    Mortazavi B, Rajabpour A, Zhuang X, Rabczuk T, Shapeev AV. 2022.. Exploring thermal expansion of carbon-based nanosheets by machine-learning interatomic potentials. . Carbon 186::501–8
     [Crossref] [Google Scholar]
  116. 116.
    Islam MM, Strachan A. 2019.. Reactive molecular dynamics simulations to investigate the shock response of liquid nitromethane. . J. Phys. Chem. C 123:(4):2613–26
     [Crossref] [Google Scholar]
  117. 117.
    Yoo P, Sakano M, Desai S, Islam MM, Liao P, Strachan A. 2021.. Neural network reactive force field for C, H, N, and O systems. . NPJ Comput. Mater. 7:(1):9
     [Crossref] [Google Scholar]
  118. 118.
    Hamilton BW, Yoo P, Sakano MN, Islam MM, Strachan A. 2023.. High-pressure and temperature neural network reactive force field for energetic materials. . J. Chem. Phys. 158:(14):144117
     [Crossref] [Google Scholar]
  119. 119.
    Chu Q, Chang X, Ma K, Fu X, Chen D. 2022.. Revealing the thermal decomposition mechanism of RDX crystals by a neural network potential. . Phys. Chem. Chem. Phys. 24:(42):25885–94
     [Crossref] [Google Scholar]
  120. 120.
    Lindsey RK, Pham HC, Goldman N, Bastea S, Fried LE. 2022.. Machine-learning a solution for reactive atomistic simulations of energetic materials. . Propellants Explos. Pyrotech. 47:(8):e202200001
     [Crossref] [Google Scholar]
  121. 121.
    Xu R, Meisner J, Chang AM, Thompson KC, Martínez TJ. 2023.. First principles reaction discovery: from the Schrodinger equation to experimental prediction for methane pyrolysis. . Chem. Sci. 14:(27):7447–64
     [Crossref] [Google Scholar]
  122. 122.
    Zeng J, Cao L, Xu M, Zhu T, Zhang JZH. 2020.. Complex reaction processes in combustion unraveled by neural network-based molecular dynamics simulation. . Nat. Commun. 11:(1):5713
     [Crossref] [Google Scholar]
  123. 123.
    Zhang S, Makoś M, Jadrich R, Kraka E, Barros K, et al. 2023.. Exploring the frontiers of chemistry with a general reactive machine learning potential. . ChemRxiv. https://doi.org/10.26434/chemrxiv-2022-15ct6-v3
  124. 124.
    Wang LP, Titov A, McGibbon R, Liu F, Pande VS, Martínez TJ. 2014.. Discovering chemistry with an ab initio nanoreactor. . Nat. Chem. 6:(12):1044–48
     [Crossref] [Google Scholar]
  125. 125.
    Wang LP. 2019.. Force field development and nanoreactor chemistry. . In Computational Approaches for Chemistry Under Extreme Conditions, ed. N Goldman , pp. 127–59. Cham, Switz.:: Springer
     [Google Scholar]
  126. 126.
    Dewyer AL, Argüelles AJ, Zimmerman PM. 2018.. Methods for exploring reaction space in molecular systems. . WIREs Comput. Mol. Sci. 8:(2):e1354
     [Crossref] [Google Scholar]
  127. 127.
    Zhu X, Thompson KC, Martínez TJ. 2019.. Geodesic interpolation for reaction pathways. . J. Chem. Phys. 150:(16):164103
     [Crossref] [Google Scholar]
  128. 128.
    Pinheiro M Jr., Zhang S, Dral PO, Barbatti M. 2023.. WS22 database, Wigner sampling and geometry interpolation for configurationally diverse molecular datasets. . Sci. Data 10:(1):95
     [Crossref] [Google Scholar]
  129. 129.
    Hillery M, O'Connell RF, Scully MO, Wigner EP. 1984.. Distribution functions in physics: fundamentals. . Phys. Rep. 106:(3):121–67
     [Crossref] [Google Scholar]
  130. 130.
    Smith JS, Nebgen B, Lubbers N, Isayev O, Roitberg AE. 2018.. Less is more: sampling chemical space with active learning. . J. Chem. Phys. 148:(24):241733
     [Crossref] [Google Scholar]
  131. 131.
    Kulichenko M, Barros K, Lubbers N, Li YW, Messerly R, et al. 2023.. Uncertainty-driven dynamics for active learning of interatomic potentials. . Nat. Comput. Sci. 3:(3):230–39
     [Crossref] [Google Scholar]
  132. 132.
    Zhao Q, Vaddadi SM, Woulfe M, Ogunfowora LA, Garimella SS, et al. 2023.. Comprehensive exploration of graphically defined reaction spaces. . Sci. Data 10:(1):145
     [Crossref] [Google Scholar]
  133. 133.
    St. John PC, Guan Y, Kim Y, Etz BD, Kim S, Paton RS. 2020.. Quantum chemical calculations for over 200,000 organic radical species and 40,000 associated closed-shell molecules. . Sci. Data 7:(1):244
     [Crossref] [Google Scholar]
  134. 134.
    Spiekermann K, Pattanaik L, Green WH. 2022.. High accuracy barrier heights, enthalpies, and rate coefficients for chemical reactions. . Sci. Data 9:(1):417
     [Crossref] [Google Scholar]
  135. 135.
    Grambow CA, Pattanaik L, Green WH. 2020.. Reactants, products, and transition states of elementary chemical reactions based on quantum chemistry. . Sci. Data 7:(1):137
     [Crossref] [Google Scholar]
  136. 136.
    Stuyver T, Coley CW. 2023.. Machine learning-guided computational screening of new candidate reactions with high bioorthogonal click potential. . Chem. Eur. J. 29:(28):e202300387
     [Crossref] [Google Scholar]
  137. 137.
    von Rudorff GF, Heinen SN, Bragato M, von Lilienfeld OA. 2020.. Thousands of reactants and transition states for competing E2 and SN2 reactions. . Mach. Learn. Sci. Technol. 1:(4):045026
     [Crossref] [Google Scholar]
  138. 138.
    Goerigk L, Hansen A, Bauer C, Ehrlich S, Najibi A, Grimme S. 2017.. A look at the density functional theory zoo with the advanced GMTKN55 database for general main group thermochemistry, kinetics and noncovalent interactions. . Phys. Chem. Chem. Phys. 19:(48):32184–215
     [Crossref] [Google Scholar]
  139. 139.
    Guan X, Das A, Stein CJ, Heidar-Zadeh F, Bertels L, et al. 2022.. A benchmark dataset for hydrogen combustion. . Sci. Data 9:(1):215
     [Crossref] [Google Scholar]
  140. 140.
    Prasad VK, Pei Z, Edelmann S, Otero-de-la-Roza A, DiLabio GA. 2021.. BH9, a new comprehensive benchmark data set for barrier heights and reaction energies: assessment of density functional approximations and basis set incompleteness potentials. . J. Chem. Theory Comput. 18:(1):151–66
     [Crossref] [Google Scholar]
  141. 141.
    Ko TW, Finkler JA, Goedecker S, Behler J. 2021.. A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer. . Nat. Commun. 12:(1):398
     [Crossref] [Google Scholar]
/content/journals/10.1146/annurev-physchem-062123-024417
Loading
Machine Learning of Reactive Potentials
Annual Review of Physical Chemistry 75, 371 (2024); https://doi.org/10.1146/annurev-physchem-062123-024417
/content/journals/10.1146/annurev-physchem-062123-024417
/content/journals/10.1146/annurev-physchem-062123-024417
Loading

Data & Media loading...

  • Article Type: Review Article

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error