Machine Learning Regression Analyses of Intensity Modulation Two-Photon Microscopy (ml-IM2PM) in Perovskite Microcrystals

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.