arrow
Volume 13, Issue 4
A QMC-Deep Learning Method for Diffusivity Estimation in Random Domains

Liyao Lyu, Zhiwen Zhang & Jingrun Chen

Numer. Math. Theor. Meth. Appl., 13 (2020), pp. 908-927.

Published online: 2020-06

Export citation
  • Abstract

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.

  • AMS Subject Headings

35K57, 65C05, 65M06, 65M32

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{NMTMA-13-908, author = {Lyu , LiyaoZhang , Zhiwen and Chen , Jingrun}, title = {A QMC-Deep Learning Method for Diffusivity Estimation in Random Domains}, journal = {Numerical Mathematics: Theory, Methods and Applications}, year = {2020}, volume = {13}, number = {4}, pages = {908--927}, abstract = {

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.

}, issn = {2079-7338}, doi = {https://doi.org/10.4208/nmtma.OA-2020-0032}, url = {http://global-sci.org/intro/article_detail/nmtma/16959.html} }
TY - JOUR T1 - A QMC-Deep Learning Method for Diffusivity Estimation in Random Domains AU - Lyu , Liyao AU - Zhang , Zhiwen AU - Chen , Jingrun JO - Numerical Mathematics: Theory, Methods and Applications VL - 4 SP - 908 EP - 927 PY - 2020 DA - 2020/06 SN - 13 DO - http://doi.org/10.4208/nmtma.OA-2020-0032 UR - https://global-sci.org/intro/article_detail/nmtma/16959.html KW - Exciton diffusion length, deep learning, Quasi-Monte Carlo sampling, diffusion equation. AB -

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.

Liyao Lyu, Zhiwen Zhang & Jingrun Chen. (2020). A QMC-Deep Learning Method for Diffusivity Estimation in Random Domains. Numerical Mathematics: Theory, Methods and Applications. 13 (4). 908-927. doi:10.4208/nmtma.OA-2020-0032
Copy to clipboard
The citation has been copied to your clipboard