Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

AI-Enhanced High-Resolution Functional Imaging Reveals Trap States and Charge Carrier Recombination Pathways in Perovskite

Shi, Qi LU and Pullerits, Tönu LU (2025) In Energy and Environmental Materials 8(6).
Abstract

Understanding and managing charge carrier recombination dynamics is crucial for optimizing the performance of metal halide perovskite optoelectronic devices. In this work, we introduce a machine learning-assisted intensity-modulated two-photon photoluminescence microscopy approach for quantitatively mapping recombination processes in MAPbBr3 perovskite microcrystalline films at micrometer-scale resolution. To enhance model accuracy, a balanced classification sampling strategy was applied during the machine learning optimization stage. The trained regression chain model accurately predicts key physical parameters—exciton generation rate ((Formula presented.)), initial trap concentration ((Formula presented.)), and trap energy... (More)

Understanding and managing charge carrier recombination dynamics is crucial for optimizing the performance of metal halide perovskite optoelectronic devices. In this work, we introduce a machine learning-assisted intensity-modulated two-photon photoluminescence microscopy approach for quantitatively mapping recombination processes in MAPbBr3 perovskite microcrystalline films at micrometer-scale resolution. To enhance model accuracy, a balanced classification sampling strategy was applied during the machine learning optimization stage. The trained regression chain model accurately predicts key physical parameters—exciton generation rate ((Formula presented.)), initial trap concentration ((Formula presented.)), and trap energy barrier ((Formula presented.))—across a 576-pixel spatial mapping. These parameters were then used to solve a system of coupled ordinary differential equations, yielding spatially resolved simulations of carrier populations and recombination behaviors at steady-state photoexcitation. The resulting maps reveal pronounced local variations in exciton, electron, hole, and trap populations, as well as photoluminescence and nonradiative losses. Correlation analysis identifies three distinct recombination regimes: 1) a trap-filling regime predominated by nonradiative recombination, 2) a crossover regime, and 3) a band-filling regime with significantly enhanced radiative efficiency. A critical trap density threshold (~1017 (Formula presented.)) marks the transition between these regimes. This work demonstrates machine learning-assisted intensity-modulated two-photon photoluminescence microscopy as a powerful framework for diagnosing carrier dynamics and guiding defect passivation strategies in perovskite materials.

(Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
charge carrier dynamics, intensity modulation two-photon excited photoluminescence (IM2PM), machine learning, nonradiative recombination, trap states
in
Energy and Environmental Materials
volume
8
issue
6
article number
e70062
publisher
John Wiley & Sons Inc.
external identifiers
  • scopus:105009287253
ISSN
2575-0348
DOI
10.1002/eem2.70062
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2025 The Author(s). Energy & Environmental Materials published by John Wiley & Sons Australia, Ltd on behalf of Zhengzhou University.
id
fe325cdd-f0a5-4aa4-9be0-cfe5ba227441
date added to LUP
2025-12-18 10:17:59
date last changed
2025-12-18 10:18:29
@article{fe325cdd-f0a5-4aa4-9be0-cfe5ba227441,
  abstract     = {{<p>Understanding and managing charge carrier recombination dynamics is crucial for optimizing the performance of metal halide perovskite optoelectronic devices. In this work, we introduce a machine learning-assisted intensity-modulated two-photon photoluminescence microscopy approach for quantitatively mapping recombination processes in MAPbBr<sub>3</sub> perovskite microcrystalline films at micrometer-scale resolution. To enhance model accuracy, a balanced classification sampling strategy was applied during the machine learning optimization stage. The trained regression chain model accurately predicts key physical parameters—exciton generation rate ((Formula presented.)), initial trap concentration ((Formula presented.)), and trap energy barrier ((Formula presented.))—across a 576-pixel spatial mapping. These parameters were then used to solve a system of coupled ordinary differential equations, yielding spatially resolved simulations of carrier populations and recombination behaviors at steady-state photoexcitation. The resulting maps reveal pronounced local variations in exciton, electron, hole, and trap populations, as well as photoluminescence and nonradiative losses. Correlation analysis identifies three distinct recombination regimes: 1) a trap-filling regime predominated by nonradiative recombination, 2) a crossover regime, and 3) a band-filling regime with significantly enhanced radiative efficiency. A critical trap density threshold (~10<sup>17</sup> (Formula presented.)) marks the transition between these regimes. This work demonstrates machine learning-assisted intensity-modulated two-photon photoluminescence microscopy as a powerful framework for diagnosing carrier dynamics and guiding defect passivation strategies in perovskite materials.</p>}},
  author       = {{Shi, Qi and Pullerits, Tönu}},
  issn         = {{2575-0348}},
  keywords     = {{charge carrier dynamics; intensity modulation two-photon excited photoluminescence (IM2PM); machine learning; nonradiative recombination; trap states}},
  language     = {{eng}},
  number       = {{6}},
  publisher    = {{John Wiley & Sons Inc.}},
  series       = {{Energy and Environmental Materials}},
  title        = {{AI-Enhanced High-Resolution Functional Imaging Reveals Trap States and Charge Carrier Recombination Pathways in Perovskite}},
  url          = {{http://dx.doi.org/10.1002/eem2.70062}},
  doi          = {{10.1002/eem2.70062}},
  volume       = {{8}},
  year         = {{2025}},
}