Probing the Low-Frequency Response of Impedance Spectroscopy of Halide Perovskite Single Crystals Using Machine Learning
Küçük Resim Yok
Tarih
2023
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Amer Chemical Soc
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Electrochemical impedance spectroscopy (EIS) has emergedas a versatiletechnique for characterization and analysis of metal halide perovskitesolar cells (PSCs). The crucial information about ion migration andcarrier accumulation in PSCs can be extracted from the low-frequencyregime of the EIS spectrum. However, lengthy measurement time at lowfrequencies along with material degradation due to prolonged exposureto light and bias motivates the use of machine learning (ML) in predictingthe low-frequency response. Here, we have developed an ML model topredict the low-frequency response of the halide perovskite singlecrystals. We first synthesized high-quality MAPbBr(3) singlecrystals and subsequently recorded the EIS spectra at different appliedbias and illumination intensities to prepare the dataset comprising8741 datapoints. The developed supervised ML model can predict thereal and imaginary parts of the low-frequency EIS response with an R (2) score of 0.981 and a root mean squared error(RMSE) of 0.0196 for the testing set. From the ground truth experimentaldata, it can be observed that negative capacitance prevails at a higherapplied bias. Our developed model can closely predict the real andimaginary parts at a low frequency (50 Hz-300 mHz). Thus, ourmethod makes recording of EIS more accessible and opens a new wayin using the ML techniques for EIS.
Açıklama
Anahtar Kelimeler
Machine Learning, Halide Perovskites, Singlecrystals, Impedance Spectroscopy, Negative Capacitance, Low-Frequency Resistance
Kaynak
Acs Applied Materials & Interfaces
WoS Q Değeri
Scopus Q Değeri
Q1
Cilt
15
Sayı
23