A machine learning and DFT assisted analysis of benzodithiophene based organic dyes for possible photovoltaic applications

Abstract

We present a synergistic approach to combine Machine Learning (ML), Density Functional Theory (DFT), and molecular descriptor analysis for designing high-performance benzodithiophene (BDT) based chromophores. A dataset of 366 BDT incorporated moieties is compiled from literature while their molecular descriptors are designed by using Python programming language. Linear and Random Forest Regression models produces best results to predict their exciton binding energy (Eb) with their R-Squared (R2) value 0.87 and 0.94 respectively. Their DFT calculations provides additional features, including molecular charges. Their ML models also reveals that their E_b values are a crucial predictor for their photovoltaic (PV) performance as its lower value could facilitate efficient charge carrier separation. For this, their hydrogen bond acceptors (HBA) and topological polar surface area (TPSA) emerges as key descriptors during their regression analysis. Their DFT validation shows negligible differences in their molecular charges to suggest their electron donor/acceptor moieties can significantly impact their chromophore nature. The current research work is helpful for efficiently screening the suitability of organic chromophores for their PV applications through advanced computational tools.