Deep Learning Prediction of Triplet–Triplet Annihilation Parameters in Blue Fluorescent Organic Light‐Emitting Diodes

• Published in: Advanced materials (Weinheim) 2024-07, Vol.36 (28), p.e2312774-n/a
• Main Authors: Lim, Junseop, Kim, Jae‐Min, Lee, Jun Yeob
• Format: Article
• Language: English
• Subjects: Deep learning; exciton dynamics; Excitons; Fluorescence; Kinetic coefficients; Light emitting diodes; multilayer perceptron; organic light‐emitting diodes; Parameters; Polarons; Predictions; triplet–triplet annihilation (TTA) ratio
• ISSN: 0935-9648; 1521-4095; 1521-4095
• DOI: 10.1002/adma.202312774

The triplet–triplet annihilation (TTA) ratio and the rate coefficient (kTT) of TTA are key factors in estimating the contribution of triplet excitons to radiative singlet excitons in fluorescent TTA organic light‐emitting diodes. In this study, deep learning models are implemented to predict key factors from transient electroluminescence (trEL) data using new numerical equations. A new TTA model is developed that considers both polaron and exciton dynamics, enabling the distinction between prompt and delayed singlet decays with a fundamental understanding of the mechanism. In addition, deep learning models for predicting the kinetic coefficients and TTA ratio are established. After comprehensive optimization inspired by photophysics, determination coefficient values of 0.992 and 0.999 are achieved in the prediction of kTT and TTA ratio, respectively, indicating a nearly perfect prediction. The contribution of each kinetic parameter of polaron and exciton dynamics to the trEL curve is discussed using various deep‐learning models. An advanced triplet‐triplet annihilation (TTA) decay model is implemented and deep learning (DL) model for the prediction of kinetic coefficients is developed using the new TTA model, which DL model presented superior predictability by obtaining determination coefficient value of 0.992 and 0.999 of the TTA rate coefficient and TTA ratio.