Artificial Neural Networks as Propagators in Quantum Dynamics
Source abstract
Abstract
The utilization of artificial neural networks (ANNs) provides strategies for accelerating molecular simulations. Herein, ANNs are implemented as propagators of the time-dependent Schrödinger equation to simulate the quantum dynamics of systems with time-dependent potentials. These ANN propagators are trained to map nonstationary wavepackets from a given time to a future time within the discrete variable representation. Each propagator is trained for a specified time step, and iterative application of the propagator enables the propagation of wavepackets over long time scales. Such ANN propagators are developed and applied to one- and two-dimensional proton transfer systems, which exhibit nuclear quantum effects such as hydrogen tunneling. These ANN propagators are trained for either a specific time-independent potential or general potentials that can be time-dependent. Hierarchical, multiple time step algorithms enable parallelization, and the extension to higher dimensions is straightforward. This strategy is applicable to quantum dynamical simulations of diverse chemical and biological processes.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Spectroscopy and Quantum Chemical Studies · Quantum, superfluid, helium dynamics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Chemistry, Yale University, 225 Prospect Street, New Haven, Connecticut 06520, United States
Funding
U.S. Department of Energy
References (51)
Show source-provided references
1. 10.1038/ncomms1389010.1038/ncomms13890 ↗
2. 10.1063/1.501977910.1063/1.5019779 ↗
3. 10.1103/PhysRevLett.119.15060110.1103/PhysRevLett.119.150601 ↗
4. 10.1021/acs.jpclett.0c0216810.1021/acs.jpclett.0c02168 ↗
5. 10.1021/acs.jpca.0c0612510.1021/acs.jpca.0c06125 ↗
6. 10.1039/C9SC02696G10.1039/C9SC02696G ↗
7. 10.1007/BF0255127410.1007/BF02551274 ↗
8. 10.1016/0893-6080(89)90020-810.1016/0893-6080(89)90020-8 ↗
9. 10.1016/j.jmaa.2014.03.09210.1016/j.jmaa.2014.03.092 ↗
10. 10.1063/1.508839310.1063/1.5088393 ↗
11. 10.1021/acs.jctc.8b0063610.1021/acs.jctc.8b00636 ↗
12. 10.1088/2632-2153/ab7d3010.1088/2632-2153/ab7d30 ↗
13. 10.1063/1.470454610.1063/1.4704546 ↗
14. 10.1038/s41467-020-19093-110.1038/s41467-020-19093-1 ↗
15. 10.1103/PhysRevB.94.24512910.1103/PhysRevB.94.245129 ↗
16. 10.1016/S0098-1354(98)00191-410.1016/S0098-1354(98)00191-4 ↗
17. 10.1063/1.506169310.1063/1.5061693 ↗
18. Raissi M. · arXiv · 2018 · 1801.01236
19. 10.1016/j.jcp.2019.06.05610.1016/j.jcp.2019.06.056 ↗
20. 10.1103/PhysRevLett.122.25050210.1103/PhysRevLett.122.250502 ↗
21. 10.1103/PhysRevX.10.01100610.1103/PhysRevX.10.011006 ↗
22. 10.1021/acs.jpclett.1c0007910.1021/acs.jpclett.1c00079 ↗
23. 10.1080/0892702950802234310.1080/08927029508022343 ↗
24. 10.1143/JPSJ.17.110010.1143/JPSJ.17.1100 ↗
25. 10.1063/1.170028310.1063/1.1700283 ↗
26. 10.1063/1.46673910.1063/1.466739 ↗
27. 10.1063/1.46770010.1063/1.467700 ↗
28. 10.1103/PhysRevB.24.368410.1103/PhysRevB.24.3684 ↗
29. 10.1016/j.physrep.2008.11.00110.1016/j.physrep.2008.11.001 ↗
30. 10.1063/1.172655010.1063/1.1726550 ↗
31. 10.1063/1.44850810.1063/1.448508 ↗
32. Feynman R. P. · 2010
33. 10.1016/0749-6036(87)90217-510.1016/0749-6036(87)90217-5 ↗
34. 10.1021/j100112a05010.1021/j100112a050 ↗
35. 10.1063/1.143630610.1063/1.1436306 ↗
36. 10.1016/0009-2614(94)87055-110.1016/0009-2614(94)87055-1 ↗
37. 10.1103/PhysRev.172.131510.1103/PhysRev.172.1315 ↗
38. Levine I. N. · 2009 · 6
39. 10.1126/science.264671610.1126/science.2646716 ↗
40. 10.1016/0301-0104(93)85117-Q10.1016/0301-0104(93)85117-Q ↗
41. 10.1126/science.275.5301.81710.1126/science.275.5301.817 ↗
42. 10.1021/ja035199510.1021/ja0351995 ↗
43. 10.1021/cr400400p10.1021/cr400400p ↗
44. 10.1021/jacs.0c1047410.1021/jacs.0c10474 ↗
45. 10.1039/D1SC03782J10.1039/D1SC03782J ↗
46. 10.1021/acs.jpclett.1c0022910.1021/acs.jpclett.1c00229 ↗
47. 10.1016/0301-0104(80)85267-010.1016/0301-0104(80)85267-0 ↗
48. Abadi M. · arXiv · 2016 · 1603.04467
49. 10.1103/PhysRevA.30.161010.1103/PhysRevA.30.1610 ↗
50. 10.1103/PhysRevE.73.04620410.1103/PhysRevE.73.046204 ↗
51. Liu Y. · arXiv · 2020 · 2008.09768