BROWSE

Related Researcher

Author's Photo

Kim, Jaeup U.
Nanostructured Polymer Materials Theory Lab
Research Interests
  • block copolymers, soft matter, nanostructures & patterning, machine learning

ITEM VIEW & DOWNLOAD

Accelerating Langevin Field-Theoretic Simulation of Polymers with Deep Learning

Cited 0 times inthomson ciCited 0 times inthomson ci
Title
Accelerating Langevin Field-Theoretic Simulation of Polymers with Deep Learning
Author
Yong, DaeseongKim, Jaeup U.
Issue Date
2022-08
Publisher
American Chemical Society
Citation
MACROMOLECULES, v.55, no.15, pp.6505 - 6515
Abstract
Langevin field-theoretic simulation (L-FTS) is a promising tool in polymer field theory that can account for the compositional fluctuation effect, which is neglected in the self-consistent field theory (SCFT). However, L-FTS is a computationally expensive tool, and it may take more than a week to accurately calculate ensemble averages of thermodynamic quantities. In our previous study, we introduced a deep neural network (DNN) that estimates the saddle point of the pressure field to reduce the subsequent Anderson mixing (AM) iterations. Herein, we propose a novel DNN that can be successively applied to determine the saddle point without using conventional field-update algorithms. Major deep learning (DL) models for semantic segmentation in computer vision are adopted to construct the optimal DNN architecture. Our model utilizing atrous convolutions in parallel is accurate and computationally efficient, and it is robust to the simulation parameter changes and can consequently be reused after single training. We demonstrate that our DNN can achieve speedup of factor 6 or more compared to the AM method without affecting accuracy. Open-source code for our deep Langevin FTS (DL-FTS) enables an easy and rapid Python scripting of SCFT and L-FTS incorporated with CPU or GPU parallelization and DL.
URI
https://scholarworks.unist.ac.kr/handle/201301/60046
DOI
10.1021/acs.macromol.2c00705
ISSN
0024-9297
Appears in Collections:
PHY_Journal Papers
Files in This Item:
There are no files associated with this item.

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU