Machine Learning for Predicting Perovskite Solar Cell Opto-Electronic Properties

Authors:
Publisher website
Google Scholar
Abstract
Photovoltaic technology has gain much attention in recent years for its potential to provide renewable energy in leu of traditional fossil fuels. Perovskite Solar cells have shown much promise in a relatively short time. Power conversion efficiencies have increased from 3.8% to 24.2 % in a span of ten years. Perovskite solar cells have attracted much attention in research because of the relatively low cost in manufacturing and production. Current silicon photovoltaic devices are more expensive than conventional fossil fuel. The use of Machine Learning (ML) to research and predict the opto-electronic properties of perovskite can greatly accelerate the development of this technology. ML techniques such as Linear Regression (LR), Support Vector Regression (SVR), and Artificial Neural Networks (ANNs) can greatly improve the chemical processing and manufacturing techniques. Such tools used to improve this technology have major impacts for the further proliferation of solar energy on a national scale. In this paper, we explore the current research of the development of perovskite solar cells using ML techniques. Furthermore, we cite the limitations and potential areas of further research.

This publication has 11 references indexed in Scilit: