Machine Learning Regression Analyses of Intensity Modulation Two-Photon Microscopy (ml-IM2PM) in Perovskite Microcrystals
(2024) In ACS Photonics 11(3). p.1093-1102- Abstract
Perovskite thin films hold great promise for optoelectronic applications, such as solar cells and light-emitting diodes. One challenge is the inevitable formation of defects in the material. A thorough understanding of the defect formation and its dynamics has proven difficult based on traditional spectroscopy. Here, we have integrated functional intensity modulation two-photon spectroscopy with artificial intelligence-enhanced data analysis to gain a deep understanding of defect-related trap states in perovskite microcrystals. We present a novel model of carrier recombination dynamics that comprehensively includes exciton and electron-hole pair photoluminescence (PL) emissions as well as trapping and detrapping equilibrium dynamics. By... (More)
Perovskite thin films hold great promise for optoelectronic applications, such as solar cells and light-emitting diodes. One challenge is the inevitable formation of defects in the material. A thorough understanding of the defect formation and its dynamics has proven difficult based on traditional spectroscopy. Here, we have integrated functional intensity modulation two-photon spectroscopy with artificial intelligence-enhanced data analysis to gain a deep understanding of defect-related trap states in perovskite microcrystals. We present a novel model of carrier recombination dynamics that comprehensively includes exciton and electron-hole pair photoluminescence (PL) emissions as well as trapping and detrapping equilibrium dynamics. By variation of the parameters in the dynamics model, a large pool of temperature-dependent intensity modulation PL spectra can be simulated by solving the ordinary differential equations in the carrier dynamics model. Then, the tree-based supervised machine learning methods and ensemble technique, regression chain, were used to optimize the machine learning regression analyses of intensity modulation two-photon microscopy (ml-IM2PM), which helps to determine the parameters of the charge carrier dynamics model based on the temperature-dependent intensity-modulated PL spectra in perovskite. And the reliability of the ml-IM2PM-predicted trap property parameters is confirmed by directly comparing the ml-IM2PM obtained intensity modulation spectra with experimental data. Furthermore, our approach not only reveals valuable insights into PL emissions, including those of excitons and free electron-hole pairs, but also provides details of trapping, detrapping, and nonradiative depopulation processes, providing a comprehensive understanding of the photophysics of perovskite materials. This study suggests that ml-IM2PM applications are promising for the study of various photoactive devices.
(Less)
- author
- Shi, Qi LU and Pullerits, Tönu LU
- organization
- publishing date
- 2024-03
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- extra tree, intensity modulation technique, intensity modulation two-photon microscopy, machine learning, MAPbBr perovskite, regression chain
- in
- ACS Photonics
- volume
- 11
- issue
- 3
- pages
- 10 pages
- publisher
- The American Chemical Society (ACS)
- external identifiers
-
- scopus:85187573580
- ISSN
- 2330-4022
- DOI
- 10.1021/acsphotonics.3c01523
- language
- English
- LU publication?
- yes
- id
- ec019f77-68c1-4567-9a35-85a104d6d7b5
- date added to LUP
- 2024-04-02 12:08:14
- date last changed
- 2024-04-03 11:47:20
@article{ec019f77-68c1-4567-9a35-85a104d6d7b5,
abstract = {{<p>Perovskite thin films hold great promise for optoelectronic applications, such as solar cells and light-emitting diodes. One challenge is the inevitable formation of defects in the material. A thorough understanding of the defect formation and its dynamics has proven difficult based on traditional spectroscopy. Here, we have integrated functional intensity modulation two-photon spectroscopy with artificial intelligence-enhanced data analysis to gain a deep understanding of defect-related trap states in perovskite microcrystals. We present a novel model of carrier recombination dynamics that comprehensively includes exciton and electron-hole pair photoluminescence (PL) emissions as well as trapping and detrapping equilibrium dynamics. By variation of the parameters in the dynamics model, a large pool of temperature-dependent intensity modulation PL spectra can be simulated by solving the ordinary differential equations in the carrier dynamics model. Then, the tree-based supervised machine learning methods and ensemble technique, regression chain, were used to optimize the machine learning regression analyses of intensity modulation two-photon microscopy (ml-IM2PM), which helps to determine the parameters of the charge carrier dynamics model based on the temperature-dependent intensity-modulated PL spectra in perovskite. And the reliability of the ml-IM2PM-predicted trap property parameters is confirmed by directly comparing the ml-IM2PM obtained intensity modulation spectra with experimental data. Furthermore, our approach not only reveals valuable insights into PL emissions, including those of excitons and free electron-hole pairs, but also provides details of trapping, detrapping, and nonradiative depopulation processes, providing a comprehensive understanding of the photophysics of perovskite materials. This study suggests that ml-IM2PM applications are promising for the study of various photoactive devices.</p>}},
author = {{Shi, Qi and Pullerits, Tönu}},
issn = {{2330-4022}},
keywords = {{extra tree; intensity modulation technique; intensity modulation two-photon microscopy; machine learning; MAPbBr perovskite; regression chain}},
language = {{eng}},
number = {{3}},
pages = {{1093--1102}},
publisher = {{The American Chemical Society (ACS)}},
series = {{ACS Photonics}},
title = {{Machine Learning Regression Analyses of Intensity Modulation Two-Photon Microscopy (ml-IM2PM) in Perovskite Microcrystals}},
url = {{http://dx.doi.org/10.1021/acsphotonics.3c01523}},
doi = {{10.1021/acsphotonics.3c01523}},
volume = {{11}},
year = {{2024}},
}