Machine Learning Assisted Bithiophene Based Donor Acceptor Selection to Design New Fluoresent Dyes for Photovoltaic Applications.

This study investigates the electronic properties and photovoltaic (PV) performance of newly designed bithiophene-based dyes, focusing on their light harvesting efficiency (LHE), open-circuit voltage (V), fill factor (FF), and short-circuit current density (J).These new dyes are designed with the help of machine learning (ML) to design best donor acceptor designs. For this, we collect 2567 differenr electron donor groups and calculated their bandgap with the help of Random Forest (RF) Regression method. Their maximum absorption (λ) values are redshifted with their 367-501 nm range having TA1 with higher value. Their LHE values range from 52 to 89%, with TA3 demonstrating the highest efficiency. Their V values varies significantly, with TA2 achieving the highest at 1.584 V, while TA5 and TA6 exhibit lowest values. Their FF)from 25.9 for TA4 to 59.3 for TA3, highlighting the superior charge extraction capabilities. Their J values further reflect their performance potential, with TA1 leading at 39.43 mA/cm², while TA4 and TA6 show significantly lower values of 3.28 and 4.40 mA/cm², respectively. Overall, the findings suggest that the bithiophene-based dyes, particularly TA2 and TA3, possess promising characteristics for enhancing the efficiency of solar cells.