In this study, we present a novel approach to the development of thermally activated delayed fluorescence (TADF) molecules with potentials for organic light-emitting diode (OLED) applications, leveraging machine learning (ML) algorithms to guide the materials design process. Recognizing the imperative for high-efficiency, low-cost emissive materials, we integrated ML driven models with experimental characterization to expedite the discovery of TADF compounds. Initially, a database of ML-designed TADF molecules was employed, with samples being approved to possess optimized photophysical properties. The proposed molecules were synthesized using palladium-catalyzed coupling reactions. Subsequent characterization of these molecules utilized a suite of analytical methods, including nuclear magnetic resonance (NMR) spectroscopy, photoluminescence (PL) spectroscopy, and transient PL decay etc., to confirm their structural integrity and evaluate their performance metrics. The photophysical analysis revealed notable emission efficiencies and significant delayed fluorescence characteristics in solution phases, underscoring the potential of ML-designed TADF molecules. Theoretical validations, through quantum chemical calculations, corroborated the experimental findings, demonstrating the predictive power of our ML models. This interdisciplinary approach not only accelerates the pace of TADF molecule development but also provides a scalable framework for future material innovation especially in the OLED research field.
Read full abstract