A cascaded QSAR model for efficient prediction of overall power conversion efficiency of all‐organic dye‐sensitized solar cells. Issue 14 (14th March 2015)

• Record Type: Journal Article
• Authors: Li, Hongzhi; Zhong, Ziyan; Li, Lin; Gao, Rui; Cui, Jingxia; Gao, Ting; Hu, Li Hong; Lu, Yinghua; Su, Zhong‐Min; Li, Hui
• Is Part Of: Journal of computational chemistry. Volume 36:Issue 14(2015)
• Page Start: 1036
• Page End: 1046
• Publication Date: 2015-03-14
• Subjects: quantum chemical calculations -- machine learning methods -- organic dye sensitizers -- dye‐sensitizer solar cells -- quantitative structure activity relationship -- power conversion efficiency; Chemistry -- Data processing -- Periodicals; 542.85
• DOI: 10.1002/jcc.23886
• Languages: English
• ISSNs: 0192-8651

Abstract

Abstract : A cascaded model is proposed to establish the quantitative structure–activity relationship (QSAR) between the overall power conversion efficiency (PCE) and quantum chemical molecular descriptors of all‐organic dye sensitizers. The cascaded model is a two‐level network in which the outputs of the first level ( J SC, V OC, and FF) are the inputs of the second level, and the ultimate end‐point is the overall PCE of dye‐sensitized solar cells (DSSCs). The model combines quantum chemical methods and machine learning methods, further including quantum chemical calculations, data division, feature selection, regression, and validation steps. To improve the efficiency of the model and reduce the redundancy and noise of the molecular descriptors, six feature selection methods (multiple linear regression, genetic algorithms, mean impact value, forward selection, backward elimination, and + n‐m algorithm) are used with the support vector machine. The best established cascaded model predicts the PCE values of DSSCs with a MAE of 0.57 (%), which is about 10% of the mean value PCE (5.62%). The validation parameters according to the OECD principles are R 2 (0.75), Q 2 (0.77), and Q cv 2 (0.76), which demonstrate the great goodness‐of‐fit, predictivity, and robustness of the model. Additionally, the applicability domain of the cascaded QSAR model is defined for further application. This study demonstrates that the established cascaded model is able to effectively predict the PCE for organic dye sensitizers with very low cost and relatively high accuracy, providing a useful tool for the design of dye sensitizers with high PCE. © 2015 Wiley Periodicals, Inc. Abstract : A cascaded support vector machine CasSVM model is built to establish the relationship between structures of all‐organic dye molecules and the overall power conversion efficiency (PCE) of dye sensitized solar cells (DSSCs). The prediction mean absolute error (MAE) is about 10% of the mean value of experimental PCE. The validation parameters show the unique model could efficiently predict the PCE values of DSSCs with little cost, which may be practically useful for developing novel organic dyes.