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

Study of profile formation processes of fusion plasmas by first-principle turbulence calculations and machine learning modeling

Research Project

Project/Area Number 20K14450
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 14020:Nuclear fusion-related
Research InstitutionNational Institutes for Quantum Science and Technology

Principal Investigator

Narita Emi  国立研究開発法人量子科学技術研究開発機構, 那珂研究所 先進プラズマ研究部, 主任研究員 (50757804)

Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Fiscal Year 2022: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2021: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Keywords核融合 / 乱流輸送 / 準線形乱流輸送モデル / 帯状流 / ジャイロ運動論コード / 機械学習 / ニューラルネットワークモデル / 統合シミュレーション / ニューラルネットワーク / 分布硬直性 / 統合輸送シミュレーション / プラズマ乱流 / ジャイロ運動論 / 機械学習モデリング / 統合型輸送コード / プラズマ・核融合
Outline of Research at the Start

核融合出力を決定づけるプラズマの密度と温度の予測は重要な研究課題である。密度と温度を支配する乱流輸送は第一原理計算で定量的に評価できるが、計算コストの高さから密度と温度の予測を行う統合型輸送コードには適さず、その計算に第一原理計算から示される輸送物理は反映され難い。
本研究では、複数の物理過程に起因する輸送量を第一原理計算で評価し、その結果を機械学習によって高速に再現する輸送モデルを構築する。統合型輸送コードとの結合で、第一原理計算を反映した密度と温度の分布計算を可能にし、実験から示唆されている「密度・温度の分布形状の硬直性」と「プラズマの粒子種毎の密度分布形状の相違」の原因を解明する。

Outline of Final Research Achievements

The turbulent transport model DeKANIS has been modified to improve its ability. The current DeKANIS predicts multi-species multi-channel transport fluxes, uses an improved turbulent saturation model, and includes a hydrogen isotope effect. Since DeKANIS utilizes a machine learning model, which has been trained on first principle calculation results, it can compute turbulent fluxes quickly, distinguishing several transport processes. Improvement in DeKANIS enables us to predict dominant transport processes in ITER and to reproduce tendencies for profile formation related to experimentally observed hydrogen isotope effects. In addition to improvement in DeKANIS, another machine learning model has been developed, which analyzes images showing the time evolution of the distribution function given by first principle calculations and can improve the efficiency of turbulent transport research.

Academic Significance and Societal Importance of the Research Achievements

核融合プラズマの性能予測に用いられる統合シミュレーションでは、プラズマの密度や温度を左右する乱流輸送の予測精度が鍵となると同時に、実用性の観点から計算の高速化も求められている。DeKANISは機械学習を利用することで高速な密度・温度予測を可能にし、かつ、第一原理計算に基づき支配的な輸送過程を示すことができる。本研究課題におけるDeKANISの改良により、将来装置における輸送過程の予測や実験観測の再現が可能になった。また、画像解析によって乱流輸送研究を高効率化する全く新しい手法を提案した。

Report

(4 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (20 results)

All 2023 2022 2021 2020

All Journal Article (5 results) (of which Peer Reviewed: 5 results,  Open Access: 1 results) Presentation (15 results) (of which Int'l Joint Research: 6 results,  Invited: 4 results)

  • [Journal Article] Modification of a machine learning-based semi-empirical turbulent transport model for its versatility2023

    • Author(s)
      E. Narita, M. Honda, M. Nakata, N. Hayashi, T. Nakayama, M. Yoshida
    • Journal Title

      Contributions to Plasma Physics

      Volume: 2023 Issue: 5-6 Pages: 1-11

    • DOI

      10.1002/ctpp.202200152

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Multimodal convolutional neural networks for predicting evolution of gyrokinetic simulations2023

    • Author(s)
      Honda Mitsuru、Narita Emi、Maeyama Shinya、Watanabe Tomo‐Hiko
    • Journal Title

      Contributions to Plasma Physics

      Volume: - Issue: 5-6

    • DOI

      10.1002/ctpp.202200137

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Toward efficient runs of nonlinear gyrokinetic simulations assisted by a convolutional neural network model recognizing wavenumber-space images2022

    • Author(s)
      E. Narita, M. Honda, S. Maeyama, T.-H. Watanabe
    • Journal Title

      Nuclear Fusion

      Volume: 62 Issue: 8 Pages: 086037-086037

    • DOI

      10.1088/1741-4326/ac70e8

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Quasilinear turbulent particle and heat transport modelling with a neural-network- based approach founded on gyrokinetic calculations and experimental data2021

    • Author(s)
      E. Narita, M. Honda, M. Nakata, M. Yoshida and N. Hayashi
    • Journal Title

      Nuclear Fusion

      Volume: 61 Issue: 11 Pages: 116041-116041

    • DOI

      10.1088/1741-4326/ac25be

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Review of hydrogen isotope effects on H-mode confinement in JT-60U2021

    • Author(s)
      Urano H、Narita E
    • Journal Title

      Plasma Physics and Controlled Fusion

      Volume: 63 Issue: 8 Pages: 084003-084003

    • DOI

      10.1088/1361-6587/ac048c

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Presentation] 乱流熱流束の時間発展を予測するマルチモーダルニューラルネットワークモデルの開発2023

    • Author(s)
      成田絵美、本多充、前山伸也、渡邉智彦
    • Organizer
      第2回成果創出加速プログラム研究交流会「富岳百景」
    • Related Report
      2022 Annual Research Report
  • [Presentation] 磁場閉じ込め核融合プラズマのデータ駆動型研究の進展2023

    • Author(s)
      成田絵美
    • Organizer
      第70回応用物理学会春季学術講演会
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] 水素同位体効果を考慮した準線形乱流輸送モデリングと温度・密度分布予測2023

    • Author(s)
      成田絵美、本多充、仲田資季、中山智成、林伸彦
    • Organizer
      日本物理学会2023年春季大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Machine-learning assistance with nonlinear gyrokinetic simulations by recognizing wavenumber-space images2022

    • Author(s)
      E. Narita, M. Honda, S. Maeyama and T.-H. Watanabe
    • Organizer
      27th International Conference on Numerical Simulation of Plasmas
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research / Invited
  • [Presentation] 機械学習を利用した半経験乱流輸送モデルの拡張と汎用性の検証2022

    • Author(s)
      成田絵美、本多充、仲田資季、吉田麻衣子、林伸彦、中山智成
    • Organizer
      第39回プラズマ・核融合学会年会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 機械学習を利用した半経験的乱流輸送モデルの汎用性改善に向けた拡張2022

    • Author(s)
      成田 絵美、本多 充,仲田 資季、林 伸彦
    • Organizer
      第77回日本物理学会年次大会
    • Related Report
      2021 Research-status Report
  • [Presentation] Modification of a turbulence saturation model applied in DeKANIS2022

    • Author(s)
      Narita Emi, Honda Mitsuru, Nakata Motoki, Yoshida Maiko, Hayashi Nobuhiko, Nakayama Tomonari
    • Organizer
      28th ITPA Transport and Confinement Topical Group Meeting
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Machine-learning-based modeling for acquiring insights into turbulent transport in fusion plasmas2021

    • Author(s)
      Narita Emi, Honda Mitsuru
    • Organizer
      3rd International Conference on Data Driven Plasma Science
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Quasilinear Turbulent Particle and Heat Transport Modeling with Development of Unique Saturation Rules for Insights into Profile Formation Mechanisms2021

    • Author(s)
      Narita Emi, Honda Mitsuru, Nakata Motoki, Yoshida Maiko, Hayashi Nobuhiko
    • Organizer
      28th IAEA Fusion Energy Conference (FEC 2020)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Neural-network-based turbulent transport modeling with development of saturation rules based on gyrokinetic analysis of JT-60U plasmas2021

    • Author(s)
      Narita Emi, Honda Mitsuru, Nakata Motoki, Yoshida Maiko, Hayashi Nobuhiko
    • Organizer
      Asia-Pacific Transport Working Group Meeting
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] 機械学習による核融合プラズマの輸送モデリング2021

    • Author(s)
      成田 絵美、本多 充
    • Organizer
      プラズマ・核融合学会 第38回年会
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] Improvements in efficiency of gyrokinetic simulation runs with convolutional neural network models analyzing nonlinear saturation processes2021

    • Author(s)
      Narita Emi, Honda Mitsuru, Maeyama Shinya, Watanabe Tomo-Hiko
    • Organizer
      Fourth IAEA Technical Meeting on Fusion Data Processing, Validation and Analysis
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] 粒子・熱流束の実験値を考慮した準線形乱流輸送モデリング2021

    • Author(s)
      成田 絵美、本多 充、仲田 資季、吉田 麻衣子、林 伸彦
    • Organizer
      第76回 日本物理学会年次大会
    • Related Report
      2020 Research-status Report
  • [Presentation] 乱流飽和則の開発によるニューラルネットワーク輸送モデリング2020

    • Author(s)
      成田 絵美、本多 充、仲田 資季、吉田 麻衣子、林 伸彦
    • Organizer
      日本物理学会 2020年秋季大会
    • Related Report
      2020 Research-status Report
  • [Presentation] 乱流揺動の非線形飽和過程の可視化と特徴抽出2020

    • Author(s)
      成田 絵美、本多 充、前山 伸也、渡邉 智彦
    • Organizer
      第37回 プラズマ・核融合学会 年会
    • Related Report
      2020 Research-status Report

URL: 

Published: 2020-04-28   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi