Hybrid perovskites show promise as low-cost photovoltaics. However, achieving high efficiency necessitates careful optimization of their composition. Traditionally, exploring the vast compositional space is inefficient and time-consuming. This study demonstrates machine learning (ML) techniques to effectively and rapidly map the relationships between perovskite composition and critical band gap energy (Eg), leading to the path of find-ing highly efficient perovskites for solar cell applications. Among these, Random Forest and Gradient Boosting Regression algorithms demonstrated exceptional predictive performance. Compositions with E, values between 1.2 and 2.0 eV were screened for further study. To validate data-driven approach, F APb(Br0_375I0_625)3 was se-lected from the screened data and further studied through Oensity Functional Theory (OFT) and experimental methods. To the best of our knowledge, no previous studies have analyzed organic-inorganic halide perovskites in such depth, focusing on their crystal structure, stability (offering a new perspective on organic components), and Eg. These aspects were thoroughly investigated andvalidated using ML, OFT, and experimental synthesis with characterization.
Grigoryan, S.; Petrosyan, N.; Kootyan, G.; Kozmanyan, A.; Avetisyan, V.; Zakaryan, H.; Schöning, M.J.; Asatryan, A.; Khachatryan, H., Accelerated composition optimization of hybrid perovskites via data-driven materials design, DFT calculations and synthesis, Materials & Design 260 (2025) 114902. doi.org/10.1016/j.matdes.2025.114902.
