Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites

Wei Bin How; Bipeng Wang; Weibin Chu; Sergiy M Kovalenko; Alexandre Tkatchenko; Oleg V Prezhdo

doi:10.1063/5.0078473

Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites

J Chem Phys. 2022 Feb 7;156(5):054110. doi: 10.1063/5.0078473.

Authors

Wei Bin How¹, Bipeng Wang², Weibin Chu³, Sergiy M Kovalenko⁴, Alexandre Tkatchenko⁵, Oleg V Prezhdo²

Affiliations

¹ Division of Chemistry and Biological Chemistry, School of Physical and Mathematical Sciences, Nanyang Technological University, 637371, Singapore.
² Department of Chemical Engineering, University of Southern California, Los Angeles, California 90089, USA.
³ Department of Chemistry, University of Southern California, Los Angeles, California 90089, USA.
⁴ Department of Organic Chemistry, V. N. Karazin Kharkiv National University, Kharkiv 61022, Ukraine.
⁵ Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg.

PMID: 35135269
DOI: 10.1063/5.0078473

Abstract

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.