Optoelectronic Devices Analytics: MachineLearning-Driven Models for Predicting the Performance of a Dye-Sensitized Solar Cell

Optoelectronic devices, which combine optics and electronics, are vital for converting light energy into electrical energy. Various solar cell technologies, such as dye-sensitized solar cells (DSSCs), silicon solar cells, and perovskite solar cells, among others, belong to this category. DSSCs have gained significant attention due to their affordability, flexibility, and ability to function under low light conditions. The current research incorporates machine learning (ML) models to predict the performance of a modified Eu3+-doped Y2WO6/TiO2 photo-electrode DSSC. Experimental data were collected from the “Dryad Repository Database” to feed into the models, and a detailed data visualization analysis was performed to study the trends in the datasets. The support vector regression (SVR) and Random Forest regression (RFR) models were applied to predict the short-circuit current density (Jsc) and maximum power (Pmax) output of the device. Both models achieved reasonably accurate predictions, and the RFR model attained a better prediction response, with the percentage difference between the experimental data and model prediction being 0.73% and 1.01% for the Jsc and Pmax respectively, while the SVR attained a percentage difference of 1.22% and 3.54% for the Jsc and Pmax respectively.