Machine Learning assisted Prediction of Impedance response of Perovskites

A thorough understanding of the charge carrier dynamics in Halide Perovskites (HyPes) is crucial for comprehending and handling the degradation and operational processes in optoelectronic devices. In addition to the semiconducting properties, HyPes show notable ionic conductivity arising from the diffusion of ions and resulting in the non-uniform distribution of charged particles throughout the material. This particular charge transport mechanism has been identified as the underlying cause of several distinctive properties observed in HyPes, which have been the subject of extensive debate with numerous proposed explanations.

Impedance Spectroscopy (IS) has emerged as an appealing technique for understanding ion diffusion by the presence of low-frequency contribution. Rigorous efforts have been put forth in analyzing the EIS spectra of HyPes and related devices under different external stimuli of applied bias, temperature, and light intensity and obtaining in-depth insights about different physical processes. Along with this fact, the measurement time needed to collect the EIS spectrum at lower frequencies increases with a set of experimental parameters.

In our recent work, we have developed a Machine Learning model to forecast the low-frequency impedance response of Methylammonium lead tri bromide single crystals under different measurement conditions of applied DC bias and illumination.

Click here to read the full article which is published in ACS AMI on June 02, 2023, American Chemical Society

#perovskite #solar #machinelearning #artificialintelligence #renewableenergy #research #phdstudent #solarcells #photodetectors #MLInnovation #EfficientDevices #futuretech #chemistry #materials #semiconductor #MLforScience #techbreakthroughs