Machine-Learning-Assisted Screening of Interface Passivation Materials for Perovskite Solar Cells
Dr. Nishi Parikh
Data Scientist, Machine learning, Batteries, Semi-conductors, Swiss Government Excellence Fellow
Recent advances in AI/ML hold the promise of revolutionizing the way materials for energy are discovered and optimized, and their processing engineered.?Hybrid Perovskite Solar Cells are promising contenders for next-generation low-cost photovoltaics.
Controlling the interface dynamics is one of the most explored strategies to mitigate the issues related to the stability of these devices.
Despite the efforts of the perovskite PV community in device engineering, it remains challenging to establish a clear selection criterion for numerous ammonium salts to achieve good surface passivation and device PCE.
The research group led by Prof. Li and Prof. Liu presented an ML ensemble regression algorithm to screen potential ammonium salts for passivation. The authors stated that hydrogen bond donor, hydrogen atom, and lipid–water partition coefficient should be primarily considered when selecting new ammonium salts to achieve a good interface passivation effect.
The work is published in ACS Energy Letters on 15 February 2023.
Find the original copy of work here.