Machine-learning Kohn–Sham potential from dynamics in time-dependent Kohn–Sham systems
The construction of a better exchange-correlation potential in time-dependent density functional theory (TDDFT) can improve the accuracy of TDDFT calculations and provide more accurate predictions of the properties of many-electron systems. Here, we propose a machine learning method to develop the e...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ace8f0 |
| _version_ | 1797740085029896192 |
|---|---|
| author | Jun Yang James Whitfield |
| author_facet | Jun Yang James Whitfield |
| author_sort | Jun Yang |
| collection | DOAJ |
| description | The construction of a better exchange-correlation potential in time-dependent density functional theory (TDDFT) can improve the accuracy of TDDFT calculations and provide more accurate predictions of the properties of many-electron systems. Here, we propose a machine learning method to develop the energy functional and the Kohn–Sham potential of a time-dependent Kohn–Sham (TDKS) system is proposed. The method is based on the dynamics of the Kohn–Sham system and does not require any data on the exact Kohn–Sham potential for training the model. We demonstrate the results of our method with a 1D harmonic oscillator example and a 1D two-electron example. We show that the machine-learned Kohn–Sham potential matches the exact Kohn–Sham potential in the absence of memory effect. Our method can still capture the dynamics of the Kohn–Sham system in the presence of memory effects. The machine learning method developed in this article provides insight into making better approximations of the energy functional and the Kohn–Sham potential in the TDKS system. |
| first_indexed | 2024-03-12T14:07:27Z |
| format | Article |
| id | doaj.art-2858a28890014c69990f0c305a1e7787 |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-03-12T14:07:27Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-2858a28890014c69990f0c305a1e77872023-08-21T12:20:44ZengIOP PublishingMachine Learning: Science and Technology2632-21532023-01-014303502210.1088/2632-2153/ace8f0Machine-learning Kohn–Sham potential from dynamics in time-dependent Kohn–Sham systemsJun Yang0https://orcid.org/0000-0001-5621-4962James Whitfield1Department of Physics and Astronomy, Dartmouth College , Hanover, NH 03755, United States of AmericaDepartment of Physics and Astronomy, Dartmouth College , Hanover, NH 03755, United States of AmericaThe construction of a better exchange-correlation potential in time-dependent density functional theory (TDDFT) can improve the accuracy of TDDFT calculations and provide more accurate predictions of the properties of many-electron systems. Here, we propose a machine learning method to develop the energy functional and the Kohn–Sham potential of a time-dependent Kohn–Sham (TDKS) system is proposed. The method is based on the dynamics of the Kohn–Sham system and does not require any data on the exact Kohn–Sham potential for training the model. We demonstrate the results of our method with a 1D harmonic oscillator example and a 1D two-electron example. We show that the machine-learned Kohn–Sham potential matches the exact Kohn–Sham potential in the absence of memory effect. Our method can still capture the dynamics of the Kohn–Sham system in the presence of memory effects. The machine learning method developed in this article provides insight into making better approximations of the energy functional and the Kohn–Sham potential in the TDKS system.https://doi.org/10.1088/2632-2153/ace8f0Hamiltonian neural networksTDDFTtime-dependent Kohn–Sham systempotential inversionmachine learning |
| spellingShingle | Jun Yang James Whitfield Machine-learning Kohn–Sham potential from dynamics in time-dependent Kohn–Sham systems Machine Learning: Science and Technology Hamiltonian neural networks TDDFT time-dependent Kohn–Sham system potential inversion machine learning |
| title | Machine-learning Kohn–Sham potential from dynamics in time-dependent Kohn–Sham systems |
| title_full | Machine-learning Kohn–Sham potential from dynamics in time-dependent Kohn–Sham systems |
| title_fullStr | Machine-learning Kohn–Sham potential from dynamics in time-dependent Kohn–Sham systems |
| title_full_unstemmed | Machine-learning Kohn–Sham potential from dynamics in time-dependent Kohn–Sham systems |
| title_short | Machine-learning Kohn–Sham potential from dynamics in time-dependent Kohn–Sham systems |
| title_sort | machine learning kohn sham potential from dynamics in time dependent kohn sham systems |
| topic | Hamiltonian neural networks TDDFT time-dependent Kohn–Sham system potential inversion machine learning |
| url | https://doi.org/10.1088/2632-2153/ace8f0 |
| work_keys_str_mv | AT junyang machinelearningkohnshampotentialfromdynamicsintimedependentkohnshamsystems AT jameswhitfield machinelearningkohnshampotentialfromdynamicsintimedependentkohnshamsystems |