| jh240063 |
Physics Informed Machine Learning for Soft Matter |
| 課題代表者 |
John Molina(Kyoto University / Dept. Chemical Engineering)
John Molina
(Kyoto University / Department of Chemical Engineering)
|
| 概要 |
The purpose of this project is to develop physics informed Machine Learning (ML) methods to accelerate and/or complement state-of-the-art simulation methods for Soft-Matter flows. Following our work of the previous two years, we are considering three basic problems: (A) ML for polymer rheoogy, (B) ML Stokes Flows, and (C) ML for "smart" swimmers. For topic (A), we have extended our method to learn the constitutive relation of entangled polymer melts for generic multi-deformation mode flows in 2D. For topic (B), we have extended our learning method to 3D, and have performed detailed comparisons against Physics Informed Neural Networks, to show the robustness and efficiency of our approach. Finally, for topic (C), we have extended our Reinforcement Learning method to consider load-carrying swimmers in complex flows.
|
| 関連Webページ |
|
| 報告書等 |
研究紹介ポスター
／
最終報告書
|
| 業績一覧 |
(1) 学術論文 （査読あり） |
|
[]
Mayank Dixit, Takashi Taniguchi, 2025, Investigation of Homogeneous and Heterogeneous Cluster Formation in Mixtures of Ester and Hydroxy-Terminated <i>cis</i>-1,4-Polyisoprene Chains in Oligomers of Natural Rubber, ACS Applied Engineering Materials, 3 (2), 337-356
|
|
[]
Mayank Dixit, Takashi Taniguchi, 2024, Exploring the Role of Hydroxy- and Phosphate-Terminated <i>cis</i>-1,4-Polyisoprene Chains in the Formation of Physical Junction Points in Natural Rubber: Insights from Molecular Dynamics Simulations, ACS Polymers Au, 4 (4), 273-288
|
|
[]
Krongtum Sankaewtong, John J. Molina, Ryoichi Yamamoto, Efficient navigation of cargo-towing microswimmer in non-uniform flow fields, Physical Review Research, 6 (3)
|
| (2) 国際会議プロシーディングス （査読あり） |
| 該当なし |
| (3) 国際会議発表（査読なし） |
|
[]
John J. Molina, "Physics-Informed Machine Learning for the Physical and Social Sciences", Computational and Physical Understanding of Biological Information Processing - OIST TSVP, Okinawa, Japan, March 3 - 14, 2025. -INVITED-
|
|
[]
John J. Molina, "Differentiable Physics for Inverse Problems", International Active Matter Workshop 2025, Tokyo, Japan, January 24 - 25, 2025.
|
|
[]
Krongtum Sankaewtong, John J. Molina (*), Ryoichi Yamamoto, "Teaching Swimmers How to Navigate Flows", International Workshop on Active Soft Matter - sensing and responding to its environment, Fukuoka, Japan, February 28, 2025.
|
|
[]
John J. Molina, "Inferring Stokes Flows using Probabilistic Machine Learning", Computational and Physical Understanding of Biological Information Processing (Symposium) - OIST TSVP, Okinawa, Japan, March 3 - 14, 2025. -INVITED-
|
|
[]
John J. Molina, "Bayesian Machine Learning for Inverse Problems in Soft Matter", The Physics of Self-Organizing Matter (Higgs Centre Workshop), Edinburgh, U.K., July 8 - 10, 2024. -INVITED-
|
|
[]
Mark P. Lynch, "Inferring the Utility from Optimal Behaviour in an Epidemic using Neural Networks", The British Applied Mathematics Colloquium, Newcastle, U.K., April 9-11, 2024.
|
| (4) 国内会議発表（査読なし） |
|
[]
Souta Miyamoto, Yoshiki Ueno, John J. Molina (*), Takashi Taniguchi, "Applications of Bayesian Machine Learning to Complex Flows", 化学工学会 第55回秋季大会, Hokkaido, Japan, September 11 - 13, 2024.
|
|
[]
Kenta Ogawa, John J. Molina (*), Takashi Taniguchi, "Stokesian Processes: a Physics-Informed Probabilistic Stokes Solver", 第72回レオロジー討論会, Yamagata, Japan, October 17-18, 2024.
|
|
[]
宮本奏汰 (*), John J Molina, 谷口貴志, "Multi-scale simulations of well-entangled polymer melts using machine-learned surrogate model", 第72回レオロジー討論会, Yamagata, Japan, October 17 - 18, 2024.
|
|
[]
Mayank Dixit, Takashi Taniguchi, "Exploring \omega-Terminals in cis-1,4-Polyisoprene: Molecular Dynamics Insights into Polar Aggregate Formation in Natural Rubber", 第72回レオロジー討論会, Yamagata, Japan, October 17 - 18, 2024.
|
| (5) 公開したライブラリなど |
| 該当なし |
| (6) その他（特許，プレスリリース，著書等） |
| 該当なし |
