Machine Learning-Assisted Fabrication of PCBM-Perovskite Solar Cells with Nanopatterned TiO₂ Layer

To unlock the full potential of PSCs, machine learning (ML) was implemented in this research to predict the optimal combination of mesoporous-titanium dioxide (mp-TiO₂) and weight percentage (wt%) of phenyl-C₆₁-butyric acid methyl ester (PCBM), along with the current density (J_sc), open-circuit voltage (V_oc), fill factor (ff), and energy conversion efficiency (ECE). Then, the combination that yielded the highest predicted ECE was selected as a reference to fabricate PCBM-PSCs with nanopatterned TiO₂ layer. Subsequently, the PCBM-PSCs with nanopatterned TiO₂ layers were fabricated and characterized to further understand the effects of nanopatterning depth and wt% of PCBM on PSCs. Experimentally, the highest ECE of 17.338% is achieved at 127 nm nanopatterning depth and 0.10 wt% of PCBM, where the J_sc, V_oc, and ff are 22.877 mA cm⁻², 0.963 V, and 0.787, respectively. The measured J_sc, V_oc, ff, and ECE values show consistencies with the ML prediction. Hence, these findings not only revealed the potential of ML to be used as a preliminary investigation to navigate the research of PSCs but also highlighted that nanopatterning depth has a significant impact on J_sc, and the incorporation of PCBM on perovskite layer influenced the V_oc and ff, which further boosted the performance of PSCs.