Developing organic light-emitting diodes (OLEDs) with
a desired
emission color and efficiency involves complex efforts in material
selection and optimizing the device structure due to their multilayered
architectures. Notably, the cavity structure in the OLEDs allows for
a wide range of emission colors and efficiencies based on the thicknesses
and optical constants of the layers, even within a specific material
set. Conventional approaches to achieving optimized OLED designs can
prove to be financial-, labor-, and time-intensive for researchers,
considering the multitude of combinations necessary for the complex,
multilayered structure. To address these challenges, this study introduces
a novel machine learning (ML) algorithm capable of intelligently predicting
the ideal device structure for OLEDs, considering organic layer thicknesses
and refractive indexes. The rule-based ML algorithm exhibits impressive
accuracy, with an error margin of less than 0.5% for red-, green-,
and blue-emitting OLEDs. These findings emphasize the potential of
the ML algorithm as an invaluable solution to streamline the process
of obtaining optimized OLED designs, offering substantial time and
resource savings with high precision.