Luminescent solar concentrators (LSCs) are devices designed to efficiently collect both direct and diffuse solar radiation and concentrate it on photovoltaic cells to foster their use in building-integrated photovoltaics (BIPV). The optimization of LSC performances involves the adjustment of both the fluorophore and the guest polymer matrix. On this account, we investigated a series of high quantum yield, donor–acceptor–donor (D–A–D) photostable fluorophores (DQ1–5), presenting a central quinoxalinic acceptor core, not previously employed in LSCs, and triarylamines or phenothiazine as donor groups. The molecules were also decorated with alkyl chains on the central core and/or the donor groups, to explore their compatibility with the poly(methyl methacrylate) (PMMA) and poly(cyclohexyl methacrylate) (PCMA) matrices utilized in this study. The PMMA and PCMA films (25 μm thick), containing 0.2–2.2 wt% of DQ1–5, absorbed in the 370–550 nm range and presented emission maxima at 550–600 nm, with fluorescence quantum yields higher than 40% even at the highest doping contents. Notably, the DQ1/PMMA thin-films showed enhanced phase compatibility and excellent quantum yields, i.e., >95%. Accordingly, they were designed to obtain 25 cm² area LSCs with remarkable internal (η_int) and external (η_ext) photon efficiencies of 42.9% and 6.2%, respectively, higher than those observed from state-of-the-art devices based on the Lumogen Red 305 (LR305) as the reference fluorophore. Overall, these were the best results ever achieved in our laboratory for thin-film LSCs built with organic fluorescent emitters.

The excellent ability of dye-sensitized solar cells (DSSCs) to capture ambient light and convert it into electric current makes them attractive power sources for indoor applications, including powering Internet of Things (IoT) devices. In this context, substantial research efforts have been devoted to the discovery of novel organic dyes able to harvest energy from a wide range of indoor light sources at different intensities. However, such activities are often based on trial-and-error procedures which are frequently expensive and time-consuming. Here, Machine Learning (ML) techniques and Density Functional Theory (DFT) methods have been combined in a two-stage approach, with the aim to accelerate the design of new, synthetically accessible organic dyes for indoor DSSC applications. By predicting the power conversion efficiency (PCE) under different indoor light sources and intensities, potentially high-performance organic dyes have been identified.