Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites
Supervised machine learning (ML) and unsupervised ML have been performed on descriptors generated from nonadiabatic (NA) molecular dynamics (MD) trajectories representing non-radiative charge recombination in CsPbI3, a promising solar cell and optoelectronic material. Descriptors generated from ever...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/161252 |
| _version_ | 1811692046100987904 |
|---|---|
| author | How, Wei Bin Wang, Bipeng Chu, Weibin Kovalenko, Sergiy M. Tkatchenko, Alexandre Prezhdo, Oleg V. |
| author2 | School of Physical and Mathematical Sciences |
| author_facet | School of Physical and Mathematical Sciences How, Wei Bin Wang, Bipeng Chu, Weibin Kovalenko, Sergiy M. Tkatchenko, Alexandre Prezhdo, Oleg V. |
| author_sort | How, Wei Bin |
| collection | NTU |
| description | Supervised machine learning (ML) and unsupervised ML have been performed on descriptors generated from nonadiabatic (NA) molecular dynamics (MD) trajectories representing non-radiative charge recombination in CsPbI3, a promising solar cell and optoelectronic material. Descriptors generated from every third atom of the iodine sublattice alone are sufficient for a satisfactory prediction of the bandgap and NA coupling for the use in the NA-MD simulation of nonradiative charge recombination, which has a strong influence on material performance. Surprisingly, descriptors based on the cesium sublattice perform better than those of the lead sublattice, even though Cs does not contribute to the relevant wavefunctions, while Pb forms the conduction band and contributes to the valence band. Simplification of the ML models of the NA-MD Hamiltonian achieved by the present analysis helps to overcome the high computational cost of NA-MD through ML and increase the applicability of NA-MD simulations. |
| first_indexed | 2024-10-01T06:29:33Z |
| format | Journal Article |
| id | ntu-10356/161252 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:29:33Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1612522023-02-28T20:11:17Z Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites How, Wei Bin Wang, Bipeng Chu, Weibin Kovalenko, Sergiy M. Tkatchenko, Alexandre Prezhdo, Oleg V. School of Physical and Mathematical Sciences Science::Chemistry Lead Compounds Optoelectronic Eevices Supervised machine learning (ML) and unsupervised ML have been performed on descriptors generated from nonadiabatic (NA) molecular dynamics (MD) trajectories representing non-radiative charge recombination in CsPbI3, a promising solar cell and optoelectronic material. Descriptors generated from every third atom of the iodine sublattice alone are sufficient for a satisfactory prediction of the bandgap and NA coupling for the use in the NA-MD simulation of nonradiative charge recombination, which has a strong influence on material performance. Surprisingly, descriptors based on the cesium sublattice perform better than those of the lead sublattice, even though Cs does not contribute to the relevant wavefunctions, while Pb forms the conduction band and contributes to the valence band. Simplification of the ML models of the NA-MD Hamiltonian achieved by the present analysis helps to overcome the high computational cost of NA-MD through ML and increase the applicability of NA-MD simulations. Published version This work was supported by the U.S. National Science Foundation under Grant No. CHE-1900510. 2022-08-22T07:23:46Z 2022-08-22T07:23:46Z 2022 Journal Article How, W. B., Wang, B., Chu, W., Kovalenko, S. M., Tkatchenko, A. & Prezhdo, O. V. (2022). Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites. Journal of Chemical Physics, 156(5), 054110-. https://dx.doi.org/10.1063/5.0078473 0021-9606 https://hdl.handle.net/10356/161252 10.1063/5.0078473 35135269 2-s2.0-85124260384 5 156 054110 en Journal of Chemical Physics © 2022 Author(s). All rights reserved. This paper was published by AIP Publishing in Journal of Chemical Physics and is made available with permission of Author(s). application/pdf |
| spellingShingle | Science::Chemistry Lead Compounds Optoelectronic Eevices How, Wei Bin Wang, Bipeng Chu, Weibin Kovalenko, Sergiy M. Tkatchenko, Alexandre Prezhdo, Oleg V. Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites |
| title | Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites |
| title_full | Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites |
| title_fullStr | Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites |
| title_full_unstemmed | Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites |
| title_short | Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites |
| title_sort | dimensionality reduction in machine learning for nonadiabatic molecular dynamics effectiveness of elemental sublattices in lead halide perovskites |
| topic | Science::Chemistry Lead Compounds Optoelectronic Eevices |
| url | https://hdl.handle.net/10356/161252 |
| work_keys_str_mv | AT howweibin dimensionalityreductioninmachinelearningfornonadiabaticmoleculardynamicseffectivenessofelementalsublatticesinleadhalideperovskites AT wangbipeng dimensionalityreductioninmachinelearningfornonadiabaticmoleculardynamicseffectivenessofelementalsublatticesinleadhalideperovskites AT chuweibin dimensionalityreductioninmachinelearningfornonadiabaticmoleculardynamicseffectivenessofelementalsublatticesinleadhalideperovskites AT kovalenkosergiym dimensionalityreductioninmachinelearningfornonadiabaticmoleculardynamicseffectivenessofelementalsublatticesinleadhalideperovskites AT tkatchenkoalexandre dimensionalityreductioninmachinelearningfornonadiabaticmoleculardynamicseffectivenessofelementalsublatticesinleadhalideperovskites AT prezhdoolegv dimensionalityreductioninmachinelearningfornonadiabaticmoleculardynamicseffectivenessofelementalsublatticesinleadhalideperovskites |