Accelerating Organic Luminescent Material Discovery: From Quantum Chemical Calculations to Machine Learning

Abstract

Organic luminescent materials have gathered significant attentions for their pivotal roles in optoelectronic devices, chemical sensing, and biomedical diagnostics. However, the rational design of organic luminescent materials with specific functions remains a challenging task. Because the photophysical properties of these materials are intricately governed by complex electronic transitions of excited states and subtle structural variations. This complexity is further intensified by the inherent contradictions between key physical parameters, such as the trade-off between quantum efficiency and lifetime, or between singlet-triplet energy gaps and oscillator strength, as well as the vastness of the chemical space. In this review, we systematically review recent advances in rational design of organic luminescent materials, including functional fluorescent dyes, room-temperature phosphorescent systems, and thermally activated delayed fluorescence systems by quantum mechanics calculations and machine learning (ML). Importantly, key molecular descriptors are established via theoretical calculation to bridge microscopic electronic structures with macroscopic photophysical properties, effectively decoupling conflicting performance factors. And ML establishes a robust high-throughput screening framework for the discovery of high-performance candidates, which facilitates the precise "on-demand customization" of advanced organic luminescent materials in the future.