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

Application of Neural Network Driven Molecular Dynamics with First-Principles Accuracy to Origin of Life

Research Project

Project/Area Number 19K14676
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 13040:Biophysics, chemical physics and soft matter physics-related
Research InstitutionKumamoto University

Principal Investigator

Shimamura Kohei  熊本大学, 大学院先端科学研究部(理), 助教 (60772647)

Project Period (FY) 2019-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2019: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Keywords機械学習力場(原子間ポテンシャル) / 人工ニューラルネットワーク / 分子動力学法 / 第一原理分子動力学法 / 生命の起源 / 機械学習原子間ポテンシャル / 原子間ポテンシャル / 高速化 / 機械学習 / 力場(経験的原子間ポテンシャル)
Outline of Research at the Start

人工ニューラルネットワーク(ANN)力場は「ユーザ自身が利用の都度調整し直せる」というこれまでの力場の概念を覆しこのデータサイエンス時代に登場した新しい可能性である。正しく適用範囲を認識できていれば誰にでも使える強力な手法となる。ただ、多元系、特に複雑系である生命系への適用は手法が確立されていないためにまだ無い。そこで、我々は本課題で生命起源の重要問題への挑戦を掲げるとともに、多元系への適用手法の確立を目指して先陣を切る。このためにはANN力場の開発コードだけでなく教師データを作るための第一原理分子動力学計算コードにも精通している必要があるが、両方に対して十分な経験を持つ我々に一日の長がある。

Outline of Final Research Achievements

In this study, we refined a machine learning-based force field construction method to investigate chemical reactions in highly nonequilibrium systems such as deep-sea hydrothermal vent environments from a microscopic viewpoint. Although there is still room for improvement in describing chemical reactions in highly nonequilibrium systems, we have gained fruitful knowledge of useful construction methods. The atomic forces and pressure in addition to potential energy were trained to improve the accuracy of molecular dynamics simulations. The trained force fields accomplished not only describing solid-liquid phase transitions but also calculating thermal conductivity. It was also found that a more robust force field can be constructed by adjusting the coefficient of the cost function. We have suggested the worsening accuracy of the force field due to the arbitrariness of the atomic energy, and have proposed a possible solution to the issue with a data-driven approach.

Academic Significance and Societal Importance of the Research Achievements

機械学習に基づく力場は低計算コストながら第一原理計算の精度を有するため、空間・時間スケールの観点でこれまで手が届かなかった領域へ我々を導く潜在力があり、物性分野においてフロンティアを開拓しつつある。それゆえ、潜在力をより物理的かつ実用的なレベルに押し上げるために、深海熱水噴出孔環境などの難易度の高い計算対象に取り組むことで、本研究では様々な重要な構築方法の要素を世に示せたと考えている。非平衡性の高い系に対するアプローチを完全に確立できたわけではないが、原子エネルギーという新たな視点から精度向上が期待できる手法を考案するなど、今後この分野に貢献する可能性のある成果も得られている。

Report

(4 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (19 results)

All 2022 2021 2020 2019 Other

All Int'l Joint Research (2 results) Journal Article (10 results) (of which Int'l Joint Research: 4 results,  Peer Reviewed: 9 results,  Open Access: 1 results) Presentation (7 results) (of which Invited: 1 results)

  • [Int'l Joint Research] 南カリフォルニア大学(米国)

    • Related Report
      2021 Annual Research Report
  • [Int'l Joint Research] 南カリフォルニア大学(米国)

    • Related Report
      2019 Research-status Report
  • [Journal Article] Exploring far-from-equilibrium ultrafast polarization control in ferroelectric oxides with excited-state neural network quantum molecular dynamics2022

    • Author(s)
      Linker Thomas、Nomura Ken-ichi、Aditya Anikeya、Fukushima Shogo、Kalia Rajiv K.、Krishnamoorthy Aravind、Nakano Aiichiro、Rajak Pankaj、Shimamura Kohei、Shimojo Fuyuki、Vashishta Priya
    • Journal Title

      Science Advances

      Volume: 8 Issue: 12

    • DOI

      10.1126/sciadv.abk2625

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Importance of Adjusting Coefficients in Cost Function for Construction of High-Accuracy Machine-Learning Interatomic Potential2022

    • Author(s)
      Irie Ayu、Shimamura Kohei、Koura Akihide、Shimojo Fuyuki
    • Journal Title

      Journal of the Physical Society of Japan

      Volume: 91 Issue: 4 Pages: 045002-045002

    • DOI

      10.7566/jpsj.91.045002

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Thermal conductivity calculation based on Green-Kubo formula using ANN potential for β-Ag2Se2022

    • Author(s)
      Takeshita Yusuke、Shimamura Kohei、Fukushima Shogo、Koura Akihide、Shimojo Fuyuki
    • Journal Title

      Journal of Physics and Chemistry of Solids

      Volume: 163 Pages: 110580-110580

    • DOI

      10.1016/j.jpcs.2022.110580

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Reproduction of Melting and Crystallization of Sodium by Machine-Learning Interatomic Potential Based on Artificial Neural Networks2021

    • Author(s)
      Irie Ayu、Fukushima Shogo、Koura Akihide、Shimamura Kohei、Shimojo Fuyuki
    • Journal Title

      Journal of the Physical Society of Japan

      Volume: 90 Issue: 9 Pages: 094603-094603

    • DOI

      10.7566/jpsj.90.094603

    • NAID

      210000159250

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Neural Network Quantum Molecular Dynamics, Intermediate Range Order in GeSe2, and Neutron Scattering Experiments2021

    • Author(s)
      Rajak Pankaj、Baradwaj Nitish、Nomura Ken-ichi、Krishnamoorthy Aravind、Rino Jose P.、Shimamura Kohei、Fukushima Shogo、Shimojo Fuyuki、Kalia Rajiv、Nakano Aiichiro、Vashishta Priya
    • Journal Title

      The Journal of Physical Chemistry Letters

      Volume: 12 Issue: 25 Pages: 6020-6028

    • DOI

      10.1021/acs.jpclett.1c01272

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Estimating thermal conductivity of α-Ag2Se using ANN potential with Chebyshev descriptor2021

    • Author(s)
      Shimamura Kohei、Takeshita Yusuke、Fukushima Shogo、Koura Akihide、Shimojo Fuyuki
    • Journal Title

      Chemical Physics Letters

      Volume: 778 Pages: 138748-138748

    • DOI

      10.1016/j.cplett.2021.138748

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Dielectric Constant of Liquid Water Determined with Neural Network Quantum Molecular Dynamics2021

    • Author(s)
      Krishnamoorthy Aravind、Nomura Ken-ichi、Baradwaj Nitish、Shimamura Kohei、Rajak Pankaj、Mishra Ankit、Fukushima Shogo、Shimojo Fuyuki、Kalia Rajiv、Nakano Aiichiro、Vashishta Priya
    • Journal Title

      Physical Review Letters

      Volume: 126 Issue: 21 Pages: 216403-216403

    • DOI

      10.1103/physrevlett.126.216403

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Computational and training requirements for interatomic potential based on artificial neural network for estimating low thermal conductivity of silver chalcogenides2020

    • Author(s)
      Kohei Shimamura
    • Journal Title

      Journal of Chemical Physics

      Volume: 153 Issue: 23 Pages: 234301-234301

    • DOI

      10.1063/5.0027058

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Recent Progress and Current Issues in Development of Artificial Neural Network Interatomic Potential for Molecular Dynamics Simulation2019

    • Author(s)
      島村孝平,下條冬樹,田中成典
    • Journal Title

      The Brain & Neural Networks

      Volume: 26 Issue: 4 Pages: 145-155

    • DOI

      10.3902/jnns.26.145

    • NAID

      130007795111

    • ISSN
      1340-766X, 1883-0455
    • Year and Date
      2019-12-05
    • Related Report
      2019 Research-status Report
  • [Journal Article] Guidelines for Creating Artificial Neural Network Empirical Interatomic Potential from First-Principles Molecular Dynamics Data under Specific Conditions and Its Application to α-Ag2Se2019

    • Author(s)
      K. Shimamura, S. Fukushima, A. Koura, F. Shimojo, M. Misawa, R.K. Kalia, A. Nakano, P. Vashishta, T. Matsubara, and S. Tanaka
    • Journal Title

      J. Chem. Phys.

      Volume: 151 Issue: 12 Pages: 124303-124303

    • DOI

      10.1063/1.5116420

    • NAID

      120006734929

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] 熱伝導度計算に有効な人工ニューラルネットワークに基づく 原子間ポテンシャル構築方法の検討IV2022

    • Author(s)
      島村孝平, 竹下雄輔, 福島省吾, 高良明英, 下條冬樹
    • Organizer
      日本物理学会 第77回年次大会(2022年)
    • Related Report
      2021 Annual Research Report
  • [Presentation] 熱伝導度計算に有効な人工ニューラルネットワークに基づく 原子間ポテンシャル構築方法の検討III2021

    • Author(s)
      島村孝平, 竹下雄輔, 福島省吾, 高良明英, 下條冬樹
    • Organizer
      日本物理学会 2021年秋季大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 熱伝導度計算に有効な人工ニューラルネットワークに基づく 原子間ポテンシャル構築方法の検討II2021

    • Author(s)
      島村孝平, 竹下雄輔, 福島省吾, 高良明英, 下條冬樹
    • Organizer
      日本物理学会 第76回年次大会(2021年)
    • Related Report
      2020 Research-status Report
  • [Presentation] 熱伝導度計算に有効な人工ニューラルネットワークに基づく 原子間ポテンシャル構築方法の検討2020

    • Author(s)
      島村孝平, 竹下雄輔, 福島省吾, 高良明英, 下條冬樹
    • Organizer
      日本物理学会 2020年秋季大会
    • Related Report
      2020 Research-status Report
  • [Presentation] 計算機シミュレーションを用いた生命起源研究2020

    • Author(s)
      島村孝平
    • Organizer
      CBI学会2020オンライン大会 FS-02生命の起源:化学反応と情報
    • Related Report
      2020 Research-status Report
    • Invited
  • [Presentation] 生命の起源問題に対する計算科学からの試み2019

    • Author(s)
      島村孝平
    • Organizer
      研究会「計算生命科学~多体問題から生命システムへ」
    • Related Report
      2019 Research-status Report
  • [Presentation] 夾雑系理解のための分子動力学手法の開発とその応用2019

    • Author(s)
      島村孝平
    • Organizer
      新学術領域「分子夾雑の生命化学」第2回関西地区シンポジウム
    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi