• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Physics Informed Machine Learning for Complex Flows

Publicly Offered Research

Project AreaFoundation of "Machine Learning Physics" --- Revolutionary Transformation of Fundamental Physics by A New Field Integrating Machine Learning and Physics
Project/Area Number 23H04508
Research Category

Grant-in-Aid for Transformative Research Areas (A)

Allocation TypeSingle-year Grants
Review Section Transformative Research Areas, Section (II)
Research InstitutionKyoto University

Principal Investigator

MOLINA JOHN  京都大学, 工学研究科, 助教 (20727581)

Project Period (FY) 2023-04-01 – 2025-03-31
Project Status Granted (Fiscal Year 2024)
Budget Amount *help
¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2024: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2023: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
KeywordsMachine Learning / Stokes Flow / Multi-Scale Simulation / Soft Matter / Multi-Scale Simulations / Polymer Melts / Flow Inference / Gaussian Processes
Outline of Research at the Start

We will improve and optimize the learning methods we have developed for (A) multi-scale simulations of polymer flows and (B) the inference of Stokes flows with missing and/or noisy data. For the former, we will learn the constitutive relation for the canonical polymer entanglement model (i.e., Doi-Takimoto), and use it to simulate the dynamics of entangled polymer melt flows in 2D/3D. For the latter, we will incorporate hydrodynamics stresses and moving boundaries into the inference framework, to consider experimentally relevant flow problems (e.g., biofluids and colloidal dispersions).

Outline of Annual Research Achievements

For theme A, we have succeeded in extending our Gaussian Process (GP) based learning method, originally developed for non-interacting polymers, to entangled polymer melts relevant for industry. In particular, we have learned the (non-linear) constitutive relation of the dual slip-link model, a coarse-grained entanglement model that can explain many of the rheological properties of polymer melts. Our learned model is able to accurately reproduce the flow behavior of entangled polymers (compared to multi-scale simulations) at a small fraction of the cost. This work was published in Physics of Fluids and selected as "Editor's Pick".

For theme B, we have succeeded in developing a probabilistic framework for solving Stokes flow problems, based on a Physics-Informed Gaussian Process regression. We have validated our method on a non-trivial 2D problem: pressure driven flow through a sinusoidal channel. We are able to accurately solve both forward and inverse problems with a high-degree of accuracy. Our method is capable of inferring velocity/pressure fields from partial and/or noisy data, as well as stresses/forces on boundaries. Furthermore, we have shown that our approach is faster and more robust than alternative Machine-Learning solutions, e.g., Physics-Informed Neural Networks.

Current Status of Research Progress
Current Status of Research Progress

2: Research has progressed on the whole more than it was originally planned.

Reason

Our project is progressing smoothly.
We have made progress on both themes, in line with our original plan.

For theme (A), we have extended our method to entangled polymers. Flow predictions using the learned relations are in good agreement with full-scale multi-scale simulations (at a fraction of the cost), even for complex geometries/flows. For theme (B) we have developed a generalized 2D/3D Stokes flow solver. Our method is able to infer physically meaningful flow solutions given sparse/incomplete data, showing that it is a viable candidate for analyzing experiments.

In addition, we have also explored other areas where Physics-Informed Machine Learning approaches can be used to solve Soft Matter flow problems (e.g., autonomous navigation, inferring molecular weights of polymers).

Strategy for Future Research Activity

We will continue to develop themes (A) and (B) to be able to study complex 3D flows.

For theme (A), this requires parallelizing our code for high-performance GPU systems (or hybrid GPU/CPU systems). In particular, we aim to develop efficient parallel data structures to handle the creation/destruction of polymer entanglements within the slip-link model. Furthermore, we will also continue to investigate how to implement data-driven / active learning protocols, to improve the accuracy of our predictions.

For theme (B), we will investigate why the Black-Box Matrix-Matrix method, which is the state-of-the-art for Gaussian Process regression, does not yield the expected performance on our custom physics-informed GP problems. If necessary, we will consider alternative methods, e.g., using different pre-conditioners or dense matrix algorithms. Finally, we will apply our method to experimental 3D data.

Report

(1 results)
  • 2023 Annual Research Report
  • Research Products

    (20 results)

All 2024 2023

All Journal Article (4 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 4 results,  Open Access: 2 results) Presentation (16 results) (of which Int'l Joint Research: 12 results)

  • [Journal Article] Autonomous navigation of smart microswimmers in non-uniform flow fields2024

    • Author(s)
      Sankaewtong Krongtum、Molina John J.、Yamamoto Ryoichi
    • Journal Title

      Physics of Fluids

      Volume: 36 Issue: 4

    • DOI

      10.1063/5.0193113

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Stokesian processes : inferring Stokes flows using physics-informed Gaussian processes2023

    • Author(s)
      Molina John J、Ogawa Kenta、Taniguchi Takashi
    • Journal Title

      Machine Learning: Science and Technology

      Volume: 4 Issue: 4 Pages: 045013-045013

    • DOI

      10.1088/2632-2153/ad0286

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Machine-learned constitutive relations for multi-scale simulations of well-entangled polymer melts2023

    • Author(s)
      Miyamoto Souta、Molina John J、Taniguchi Takashi
    • Journal Title

      Physics of Fluids

      Volume: 35 Issue: 6

    • DOI

      10.1063/5.0156272

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Rational social distancing policy during epidemics with limited healthcare capacity2023

    • Author(s)
      Schnyder Simon K.、Molina John J.、Yamamoto Ryoichi、Turner Matthew S.
    • Journal Title

      PLOS Computational Biology

      Volume: 19 Issue: 10 Pages: e1011533-e1011533

    • DOI

      10.1371/journal.pcbi.1011533

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Presentation] Physics Informed Machine Learning for Soft Matter Flows2024

    • Author(s)
      John J. Molina (*), Kenta Ogawa, Takashi Taniguchi
    • Organizer
      アクティブマター研究会 2024
    • Related Report
      2023 Annual Research Report
  • [Presentation] Bayesian Machine Learning for Multi-Scale Simulations of Polymer Flows2023

    • Author(s)
      Souta Miyamoto, Yoshiki Ueno, Takashi Taniguchi, John J. Molina (*)
    • Organizer
      International Congress on Rheology (ICR2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Machine Learning for Accelerated Multi-Scale Polymer Flow Simulations2023

    • Author(s)
      John J. Molina (*), Souta Miyamoto, Yoshiki Ueno, Takashi Taniguchi
    • Organizer
      10th International Congress on Industrial and Applied Mathematics (ICIAM2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Stokesian Processes: Physics Informed Machine Learning for Soft Matter Flows2023

    • Author(s)
      John J. Molina (*), Kenta Ogawa, Takashi Taniguchi
    • Organizer
      The 7th International Soft Matter Conference (ISMC2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 構成関係の機械学習回帰モデルを用いた高分子溶融体の流動予測シミュレーション2023

    • Author(s)
      Souta Miyamoto (*), John J. Molina, Takashi Taniguchi
    • Organizer
      日本流体力学会年会2023
    • Related Report
      2023 Annual Research Report
  • [Presentation] Flow simulations of well-entangled polymer melts using machine-learned constitutive relations2023

    • Author(s)
      Souta Miyamoto (*), John J. Molina, Takashi Taniguchi
    • Organizer
      第71回レオロジー討論会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Inferring Stokes Flows using Physics-Informed Gaussian Processes2023

    • Author(s)
      Kenta Ogawa (*), John J. Molina, Takashi Taniguchi
    • Organizer
      第71回レオロジー討論会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Machine-learned constitutive relations of entangled polymer melts for multi-scale flow simulations (POSTER)2023

    • Author(s)
      Souta Miyamoto (*), John J. Molina, Takashi Taniguchi
    • Organizer
      34th IUPAP Conference on Computational Physics (CCP2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Stokes Flow Inference using Physics-Informed Gaussian Processes (POSTER)2023

    • Author(s)
      Kenta Ogawa (*), John J. Molina, Takashi Taniguchi
    • Organizer
      28th International Conference on Statistical Physics (Statphys28)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Physics-Informed Gaussian Processes for Stokes Flow Inference (POSTER)2023

    • Author(s)
      Kenta Ogawa (*), John J. Molina, Takashi Taniguchi
    • Organizer
      The 7th International Soft Matter Conference (ISMC2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Smart microswimmer navigation using hydrodynamical signals (POSTER)2023

    • Author(s)
      Krongtum Sankawtong (*), John J. Molina, Ryoichi Yamamoto
    • Organizer
      The 7th International Soft Matter Conference (ISMC2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Flow simulations of well-entangled polymer melts using machine-learned constitutive relations (POSTER)2023

    • Author(s)
      Souta Miyamoto (*), John J. Molina, Takashi Taniguchi
    • Organizer
      Advanced core-to-core network for the physics of self-organizing active matter
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Physics-Informed Gaussian Processes for Stokes Flow Inference (POSTER)2023

    • Author(s)
      Kenta Ogawa (*), John J. Molina, Takashi Taniguchi
    • Organizer
      Advanced core-to-core network for the physics of self-organizing active matter
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Role of order parameters in learning of fish schooling (POSTER)2023

    • Author(s)
      Krongtum Sankawtong (*), John J. Molina, Ryoichi Yamamoto
    • Organizer
      Advanced core-to-core network for the physics of self-organizing active matter
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Physics Informed Optimal Control: Inferring Hidden Utilitites form Optimal Behavior (POSTER)2023

    • Author(s)
      John J. Molina (*), Mark P. Lynch, Simon K. Schnyder, Matthew S. Turner, Ryoichi Yamamoto
    • Organizer
      Advanced core-to-core network for the physics of self-organizing active matter
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Physics Informed Machine Learning for Flow Inference (POSTER)2023

    • Author(s)
      John J. Molina (*)
    • Organizer
      International Conference on Machine Learning Physics
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2023-04-13   Modified: 2024-12-25  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi