Implementing High‐Throughput Screening of Organic Solar Cells using Transfer Learning Based on Fine‐Tuning Neural Network Strategy DOI
Zijing Lu, Cunbin An, Xuefeng Liu

et al.

Advanced Optical Materials, Journal Year: 2025, Volume and Issue: unknown

Published: May 19, 2025

Abstract In organic solar cells (OSCs), traditional ensemble learning models have advanced the development of photovoltaic materials, reducing reliance on labor‐intensive trial‐and‐error methods. However, these suffer from insufficient generalization and poor transferability, leading to low accuracy in predicting power conversion efficiency (PCE) for new materials. this work, a transferable neural network‐based framework is established predict PCEs binary OSCs. Specifically, 1431 sets donor (excluding PM6):acceptor data are collected train validate four network model. These achieved Pearson correlation coefficients ( r ) ranging 0.75 0.84. Subsequently, dataset containing 113 PM6:acceptor pairs used test their abilities. The exhibited significantly decreased 0.55–0.60, whereas model maintained above 0.80. Additionally, two electron acceptors differing only alkyl chain branching points synthesized. predicted similar both acceptors. Conversely, different PCEs, consistent with experimental results. This work demonstrates that developed predictive offers substantial advantages accurately

Language: Английский

Implementing High‐Throughput Screening of Organic Solar Cells using Transfer Learning Based on Fine‐Tuning Neural Network Strategy DOI
Zijing Lu, Cunbin An, Xuefeng Liu

et al.

Advanced Optical Materials, Journal Year: 2025, Volume and Issue: unknown

Published: May 19, 2025

Abstract In organic solar cells (OSCs), traditional ensemble learning models have advanced the development of photovoltaic materials, reducing reliance on labor‐intensive trial‐and‐error methods. However, these suffer from insufficient generalization and poor transferability, leading to low accuracy in predicting power conversion efficiency (PCE) for new materials. this work, a transferable neural network‐based framework is established predict PCEs binary OSCs. Specifically, 1431 sets donor (excluding PM6):acceptor data are collected train validate four network model. These achieved Pearson correlation coefficients ( r ) ranging 0.75 0.84. Subsequently, dataset containing 113 PM6:acceptor pairs used test their abilities. The exhibited significantly decreased 0.55–0.60, whereas model maintained above 0.80. Additionally, two electron acceptors differing only alkyl chain branching points synthesized. predicted similar both acceptors. Conversely, different PCEs, consistent with experimental results. This work demonstrates that developed predictive offers substantial advantages accurately

Language: Английский

Citations

0