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

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.

Fluctuations at Metal Halide Perovskite Grain Boundaries Create Transient Trap States: Machine Learning Assisted Ab Initio Analysis

“…The majority of the features encountered in Table S1 are formed by Pb and Br atoms, which form the CB and VB electronic states. At the same time, many features contain Cs atoms as well, as seen in the prior analyses. , Although Cs + cation do not contribute to the electronic states, they influence charge carriers electrostatically and through interactions with the surrounding Br – anions.…”

“…At the same time, many features contain Cs atoms as well, as seen in the prior analyses. 67,68 Although Cs + cation do not contribute to the electronic states, they influence charge carriers electrostatically and through interactions with the surrounding Br − anions.…”

Highly Efficient and Stable Wide‐Bandgap Perovskite Solar Cells via Strain Management

“…Introduction of DMSO reduced the contents of the laterally arranged (CsI) 0.08 (PbI 1.4 Br 0.6 ) and (CsI 0.125 Br 0.875 ) 0.08 (PbI 1.2 Br 0.8 ) intermediates, and the Raman peaks of both films shifted to a smaller wavenumber, indicating a tensile strain as proved by the XRD results. [ 46,47 ]…”

Ag–Bi Charge Redistribution Creates Deep Traps in Defective Cs2AgBiBr6: Machine Learning Analysis of Density Functional Theory

“…Experimental works have identified these detrimental defects in Cs 2 AgBiBr 6 and developed strategies to passivate them. − However, the lack of explicit knowledge of correlations between defect configurations and relevant trap states limits the investigation efficiency . Recently, machine learning (ML) analysis of nonadiabatic molecular dynamics (NA-MD) simulations has emerged as a powerful approach to uncover the interdependence between the structural and electronic properties and excited-state dynamics. − The energy gap and nonadiabatic coupling (NAC) fluctuations have been found dominated by structural deformations , and chemical environment of individual elements, , rather than particular atomic motions, allowing one to uncover defect features that are key in producing trap-assisted recombination centers. Such analyses provide direct guidelines on eliminating the detrimental traps.…”