Bandgap prediction of metal halide perovskites using regression machine learning models

Organometal halide perovskites represent a type of nanomaterials, which are extensively used in solar cells, light-emitting diodes, detectors and memristors due to their outstanding optical, electrical mechanical properties. Here, we use dataset composed 240 train two machine learning models, ElasticNet Isotonic Regression, able predict the bandgaps. The performance our ML models is evaluated using Correlation coefficient, Mean Absolute Error (MAE), Root Square (RMSE). lowest MAE 0.09 eV calculated for Cs-based from Ten-fold cross-validation results. While highest 0.34 was obtained MA-based with Regression. Furthermore, high correlation value 0.98 between DFT predicted results observed. From detailed comparative analysis, emerges as prominent model predicting bandgap metal more accurately. This can also be further employed various properties materials selection different applications well expand investigation other structures organic molecules.