Thursday, May 2025

05:00 PM - 08:00 PM

Room: 220A

Session: OLED Posters

Accelerating OLED Development with AI-Driven High-Throughput Screening

Description:

OLEDs have emerged as a leading display technology, finding applications in smartphones, TVs, and more. However their development is hindered by the vast combinatorial space of materials and the computational expense of traditional physical simulations. To address this, we propose a high-throughput machine learning pipeline that leverages TCAD simulation data to rapidly predict OLED device characteristics. Our model, based on catboost, achieves an R² of 96.2%, indicating highly accurate predictions. With a prediction speed of 0.463 microseconds, it enables screening of billions of material combinations in an hour, significantly accelerating the OLED development process. By dramatically reducing development time, our approach facilitates the discovery of novel, high-performance OLED materials. Future work will focus on extending our model to predict the characteristics of tandem OLEDs, which offer higher efficiency and lower manufacturing costs.