Predictive Modelling and Optimization of CdTeBased Solar Cells Using SCAPS-1D and ML Models
Journal of Ovonic Research · 2026-03 · 22 (1) · 30-50
DOI: 10.15251/jor.2026.221.30 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Ovonic Research, 2026-03. Verfasst von Raj Kumar Mishra und 1 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben.
Abstract (Originalsprache)
The outstanding photovoltaic efficiency of CdTe solar cells keeps drawing interest. In this work, SCAPS-1D (Solar Cell Capacitance Simulator in one dimension) is used to design and analyze a Cu2O/CdTe/SnO₂/ITO thin-film solar cell. By methodically examining the effects of doping concentration (1×10¹⁵–1×10¹⁹ cm⁻³) and layer thickness (0.04–0.15 µm for Cu₂O and SnO₂; 1–4 µm for CdTe), 4097 datasets are produced. The RMSE (Root Mean Square Error) and R2(Coefficient of Determination) are used for training and assessing six ML (Machine Learning) models: LR (Linear Regression), DT (Decision Tree), GBR (Gradient Boost Regression), SVR (Support Vector Regression), ANN (Artificial Neural Network), and RF (Random Forest). The two ML that show the best predictive accuracy among them are DT and RF. By increasing efficiency from 0.59% to 29.54%, the optimized structure shows that merging machine learning and SCAPS-1D simulation provides a viable approach to creating high-performance CdTe solar cells.
Zitieren
APA
Mishra, R. K., & Anwar, N. (2026). Predictive Modelling and Optimization of CdTeBased Solar Cells Using SCAPS-1D and ML Models. Journal of Ovonic Research, 22(1), 30-50. https://doi.org/10.15251/jor.2026.221.30
Vancouver
Mishra RK, Anwar N. Predictive Modelling and Optimization of CdTeBased Solar Cells Using SCAPS-1D and ML Models. Journal of Ovonic Research. 2026;22(1):30-50. doi:10.15251/jor.2026.221.30
BibTeX
@article{Mishra2026,
author = {Mishra, Raj Kumar and Anwar, Nishat},
title = {Predictive Modelling and Optimization of CdTeBased Solar Cells Using SCAPS-1D and ML Models},
journal = {Journal of Ovonic Research},
year = {2026},
volume = {22},
number = {1},
pages = {30--50},
doi = {10.15251/jor.2026.221.30}
}
EUVIMED