Main Article Content
In the last decade, the development of perovskite-based solar cells has emerged as a technological alternative for the photovoltaic generation with a higher efficiency/cost ratio. Many contributions have been made in recent years, as evidenced by many academic publications with worldwide experimental results in this area. Machine learning as a tool can support the development of this technology by predicting new materials, novel solar cell configurations, and evaluating the most relevant experimental parameters, among others. For this, the automatic learning models used in predicting or classifying the information available in the literature or generated experimentally must be improved. One way to improve these models is by including new descriptors that allow improving the prediction. In this work, we evaluated the use of the absorber layer thickness as a descriptor in a linear regression model using a database of 221 literature records containing information on the bandgap, the ?HOMO (perovskite-HTL), and ?LUMO (perovskite-ETL) of different perovskite cells, together with the thickness of the absorber layer. By building two multiple linear regression models, including or not the thickness of the absorber layer, a reduction in the root mean square error RMSE of 4.4% and 2.8% was found in the prediction of the Jsc and PCE, respectively. By applying a linear regression model, an improvement in the prediction of Jsc can be seen due to the inclusion of thickness as a descriptor, which is in line with the relatively high value of the mutual information measure between thickness and Jsc.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.