Decision Trees Based Performance Analysis for Influence of Sensitizers Characteristics in Dye-Sensitized Solar Cells

The focus of the scientific community has shifted towards renewable and sustainable natural photosensitizers for Dye-Sensitized Solar Cells (DSSCs). Here, we statistically investigate the possibility to achieve relatively high PCEs in naturally-sensitized-photoanode-based DSSCs using decision trees (machine learning). We studied the chemical structure and bandgap of 27 sensitizers, which were then correlated to the literature reported PCEs. Tree training was carried out via 4 (dye) predictors including the number of p-bonds (PI), the number of anchoring groups (X), HOMO(H)-LUMO(L), and Bandgap Energy (BG), with 2 responses regarding the statistical possibility to achieve high PCEs (Yes/No). Trained datasets revealed the controlling parameters responsible for increasing PCEs. Testing (future) datasets were chosen to check for built models' accuracy in performance prediction for enhanced charge injection (current density). This work shows the potential of natural sensitizers used in DSSCs for renewable, cost-effective, and sustainable energy production.