Predicting the efficiency of luminescent solar concentrators for solar energy harvesting using machine learning

• Published in: Scientific reports Vol. 14; no. 1; p. 4160
• Main Authors: Ferreira, Rute A. S., Correia, Sandra F. H., Fu, Lianshe, Georgieva, Petia, Antunes, Mario, André, Paulo S.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 20.02.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/301; 639/624; Algorithms; Clustering; Efficiency; Humanities and Social Sciences; Informatics; Learning algorithms; Luminescent solar concentrators; Machine learning; Materials science; Metal forming; multidisciplinary; Optical properties; Optics; Photovoltaic cells; Photovoltaics; Radiation; Regression; Regression analysis; Science; Science (multidisciplinary); Solar energy; Regression; Luminescent solar concentrators; Clustering; Machine learning
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-54657-x

Building-integrated photovoltaics (BIPV) is an emerging technology in the solar energy field. It involves using luminescent solar concentrators to convert traditional windows into energy generators by utilizing light harvesting and conversion materials. This study investigates the application of machine learning (ML) to advance the fundamental understanding of optical material design. By leveraging accessible photoluminescent measurements, ML models estimate optical properties, streamlining the process of developing novel materials, offering a cost-effective and efficient alternative to traditional methods, and facilitating the selection of competitive materials. Regression and clustering methods were used to estimate the optical conversion efficiency and power conversion efficiency. The regression models achieved a Mean Absolute Error (MAE) of 10%, which demonstrates accuracy within a 10% range of possible values. Both regression and clustering models showed high agreement, with a minimal MAE of 7%, highlighting the efficacy of ML in predicting optical properties of luminescent materials for BIPV.