Accelerated Discovery of Potential Organic Dyes for Dye‐Sensitized Solar Cells by Interpretable Machine Learning Models and Virtual Screening

Abstract

The development of highly efficient dye-sensitized solar cells (DSSCs) is greatly hindered by the lack of a reliable and understandable quantitative structureproperty relationship (QSPR) model. Herein, an accurate, robust, and interpretable QSPR model is established by combining the machine learning technique and computational quantum chemistry, and with this model, virtual screening as well as the assessment of synthetic accessibility is performed to identify new efficient and synthetically accessible organic dyes for DSSCs. Finally, eight promising organic dyes with high power conversion efficiency and synthetic accessibility are screened out from %10 000 candidates. Meanwhile, the interpretability of the model is used for deducing reasonable chemical rules for high-performance organic dyes, which are expected to contribute to further innovations for the practical applications of DSSCs.

Dye-sensitized solar cells strike back

“…On the other hand, several tools are already available for automated screening and analysis of large datasets, 205 compiled from experiments and/or advanced QM calculations, aimed at finding new, unexpected combinations of DSC components that maximize photo-conversion efficiencies, even at different light conditions. [206][207][208] The future of these tools looks bright, together with their further integration within the new promising quantum information technologies. 209…”

High-throughput virtual screening for organic electronics: a comparative study of alternative strategies

“…In these cases it is possible to separate the role of the anchoring group from that of the rest of the dye 301 and screen separately for the best anchoring group 302 and the best dye. 40,74 e. Crystal structure prediction For a range of organic electronics applications, the function is determined by molecular arrangement in highly ordered or crystalline domains, i.e. the properties are a combination of molecular properties and intermolecular interactions.…”

“…[357][358][359] Y. Wen et al considered synthetic accessibility in their DFT and ML combined approach to screen approximately 10 000 novel dyes for DSSC applications. 40 For 500 promising hit candidates, they provide the synthetic accessibility score by Ertl and Schuffenhauer. 360 They pointed out that some of the candidates with high predicted PCE are also predicted to have low synthetic feasibility.…”

Molecular design and performance improvement in organic solar cells guided by high‐throughput screening and machine learning

“…Wen et al. [ 77 ] implemented a new approach combining ML and virtual screening to discover potential organic dyes, which is illustrated in Figure 3A. Firstly, the molecular properties of DSSCs were calculated by quantum chemistry.…”

“…Reproduced with permission. [ 77 ] Copyright (2020), Wiley‐VCH. B, Theoretically predicted versus experimental PCE for the testing set (a) and all data points using the leave‐one‐out cross‐validation technique for the GB model (b).…”