A QMC-deep learning method for diffusivity estimation in random domains
This addresses the need for precise control of heterojunctions in opto-electronic devices, offering a new strategy to analyze interfacial ordering effects, though it appears incremental as it combines existing techniques in a novel way.
The researchers tackled the problem of accurately estimating exciton diffusion in random domains for organic semiconducting devices, which is challenging due to high-dimensional parameterization, and developed a method combining quasi-Monte Carlo sampling with deep learning to achieve high accuracy and efficiency.
Exciton diffusion plays a vital role in the function of many organic semiconducting opto-electronic devices, where an accurate description requires precise control of heterojunctions. This poses a challenging problem because the parameterization of heterojunctions in high-dimensional random space is far beyond the capability of classical simulation tools. Here, we develop a novel method based on quasi-Monte Carlo sampling to generate the training data set and deep neural network to extract a function for exciton diffusion length on surface roughness with high accuracy and unprecedented efficiency, yielding an abundance of information over the entire parameter space. Our method provides a new strategy to analyze the impact of interfacial ordering on exciton diffusion and is expected to assist experimental design with tailored opto-electronic functionalities.