Prediction of High-Performance Donor–Acceptor Pairs for Organic Photovoltaics with Machine Learning
Abstract
Organic solar cells are widely recognized for their flexibility, light weight and semitransparency, all relevant for niche applications. A significant challenge in their development lies in the accurate prediction of their power conversion efficiency depending on the combination of the donor and acceptor selected in the bulk heterojunction. To address this issue, we developed a robust machine learning (ML) framework designed to establish correlations between molecular structure and device performance. A feature selection strategy, incorporating SHapley Additive exPlanations and Boruta algorithms, was employed to extract the most informative descriptors. Among the regression models that were systematically evaluated on a curated dataset comprising 1575 experimentally characterized donor-acceptor pairs, histogram-based gradient boosting demonstrated superior predictive performance, giving an R 2 score of 0.79, with a low root mean square error of 2.16. Subsequently, the optimized model was used to predict new donor-acceptor pairs with PCEs above 20% and identify prospective candidates for further experimental validation.
Related
- Reliable Structure-Processing-Performance Learning in Organic Photovoltaics: Chemical Generalization, Processing-Aware Prediction and Uncertainty under Domain Shift
- Charge-Transfer-State Descriptors from Donor–Acceptor Interfaces Enable Improved Prediction of Indoor Organic Photovoltaic Efficiency
- Reducing Synthetic Complexity: A Fluorine-Free Benzodithiophene-Thienopyrrolodione Donor Polymer by Direct Arylation Polycondensation for Organic Photovoltaics
- Ground-State Charge Generation-Enabled Nondestructive Defect Passivation in Organic Photovoltaics.
- Molecular Diffusion-Driven Graded Polymer Hole-Transport Layers Enabling Efficient and Durable Organic Photovoltaics
BibTeX
@article{mbina2026prediction,
title = {{Prediction of High-Performance Donor–Acceptor Pairs for Organic Photovoltaics with Machine Learning}},
author = {Esther Mbina and Bruno Grandidier and Kekeli N’konou},
journal = {Solar},
year = {2026},
month = aug,
doi = {10.3390/solar6040051},
url = {https://hal.science/hal-05737593v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Prediction of High-Performance Donor–Acceptor Pairs for Organic Photovoltaics with Machine Learning
AU - Esther Mbina
AU - Bruno Grandidier
AU - Kekeli N’konou
PY - 2026
DA - 2026/08/17
JO - Solar
DO - 10.3390/solar6040051
UR - https://hal.science/hal-05737593v1
AB - Organic solar cells are widely recognized for their flexibility, light weight and semitransparency, all relevant for niche applications. A significant challenge in their development lies in the accurate prediction of their power conversion efficiency depending on the combination of the donor and acceptor selected in the bulk heterojunction. To address this issue, we developed a robust machine learning (ML) framework designed to establish correlations between molecular structure and device performance. A feature selection strategy, incorporating SHapley Additive exPlanations and Boruta algorithms, was employed to extract the most informative descriptors. Among the regression models that were systematically evaluated on a curated dataset comprising 1575 experimentally characterized donor-acceptor pairs, histogram-based gradient boosting demonstrated superior predictive performance, giving an R 2 score of 0.79, with a low root mean square error of 2.16. Subsequently, the optimized model was used to predict new donor-acceptor pairs with PCEs above 20% and identify prospective candidates for further experimental validation.
SN - 2673-9941
ER -