New Strategies for constructing and analyzing semiconductor photosynthetic biohybrid systems based on ensemble Machine learning Models: Visualizing complex mechanisms and yield prediction

Abstract

Photosynthetic biohybrid systems (PBSs) composed of semiconductor-microbial hybrids provide a novel approach for converting light into chemical energy. However, comprehending the intricate interactions between materials and microbes that lead to PBSs with high apparent quantum yields (AQY) is challenging. Machine learning holds promise in predicting these interactions. To address this issue, this study employs ensemble learning (ESL) based on Random Forest, Gradient Boosting Decision Tree, and eXtreme Gradient Boosting to predict AQY of PBSs utilizing a dataset comprising 15 influential factors. The ESL model demonstrates exceptional accuracy and interpretability (R2 value of 0.927), offering insights into the impact of these factors on AQY while facilitating the selection of efficient semiconductors. Furthermore, this research propose that efficient charge carrier separation and transfer at the bio-abiotic interface are crucial for achieving high AQY levels. This research provides guidance for selecting semiconductors suitable for productive PBSs while elucidating mechanisms underlying their enhanced efficiency.