Accelerating the Discovery of Efficient Phosphorescent Iridium(III) Complex Emitters with Targeted Color Gamuts Through Interpretable Machine Learning Models and Virtual Screening

To meet the growing demands across various application fields, there is an urgent need to develop phosphorescent iridium(III) complex luminescent materials that combine high luminous efficiency with precise color gamut control. In this study, we integrate machine learning with quantum chemical calculations to establish high-precision, robust, and interpretable quantitative structure–property relationship (QSPR) models for predicting emission wavelength, photoluminescence quantum yield (PLQY), and radiative transition rate constant (Kr). Based on model analysis, we propose a novel molecular design strategy for efficient phosphorescent iridium(III) complex emitters. Using this strategy, we designed 203 candidate structures and identified over 100 high-potential blue iridium(III) complexes with excellent PLQY. This work not only provides a comprehensive understanding of the photoluminescent mechanism but also opens new avenues for optimizing phosphorescent iridium(III) complexes.