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

Development of Real-time Tsunami Risk Evaluation Method Using Machine Learning and Bayesian Updating

Research Project

Project/Area Number 21K20441
Research Category

Grant-in-Aid for Research Activity Start-up

Allocation TypeMulti-year Fund
Review Section 0303:Civil engineering, social systems engineering, safety engineering, disaster prevention engineering, and related fields
Research InstitutionTohoku University

Principal Investigator

Nomura Reika  東北大学, 災害科学国際研究所, 助教 (50900320)

Project Period (FY) 2021-08-30 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2022: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2021: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Keywordsリアルタイム津波リスク評価 / 固有直交分解 / ベイズ更新 / 津波シミュレーション / 最尤シナリオ同定 / 最尤シナリオ推定 / 固有値直交分解
Outline of Research at the Start

発生と同時に伝播・遡上よりもはるかに早く沿岸部リスクを予測するリアルタイム津波リスク評価技術は,信頼性と即時性を両立する必要がある.この二つの性能は近い将来その到来が憂慮されている南海トラフ沖地震津波で,さらに高い水準で両立することを求められている.こうした要求に応えるために,既存手法に替わる,新しいリアルタイム津波リスク評価技術の開発が望まれる.本研究では, 津波シミュレーション技術と,教師なし学習(固有値直交分解),ベイズ理論に基づく最尤シナリオ推定という3つの要素技術によって,信頼性と即時性の両方を兼ね備えた,新しいリアルタイム津波予測技術を開発することを目的とする.

Outline of Final Research Achievements

Real-time tsunami risk prediction should satisfy both reliability and rapidness for longer evacuation leading times. In this project, we developed a real-time tsunami risk evaluation framework by using three key components: tsunami simulation, proper orthogonal decomposition (POD), and scenario detection based on Bayesian update. By inputting the in situ wave observation data, the proposed method can identify the most probable scenario from a database of numerous tsunami simulation results. According to the detected scenario, tsunami risks, such as maximum wave height and inundation area, can be evaluated within several or tens of minutes after quake occurrences.

Academic Significance and Societal Importance of the Research Achievements

地震の発生をスタートとし,津波の発生・伝播・遡上を,その経時的進行よりもはるかに速く解析するフォワードシミュレーションの発達により,津波到達時刻や沿岸部浸水リスクを実時間の数十倍以上の速さで予想することが可能となっている.一方,フォワードシミュレーションとは別に,そのリスクを観測データから確率論的に議論したり,機械学習技術やデータ同化技術を基に評価したりする研究も進展してきた.本研究は,このような二つの津波リスク評価技術,すなわち,堅牢な力学的洞察を有する数値シミュレーション技術とデータサイエンス技術の利点を活かした先駆的な試みに続くものと位置づけられる.

Report

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

    (7 results)

All 2022 2021 Other

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

  • [Int'l Joint Research] University of Washington(米国)

    • Related Report
      2022 Annual Research Report
  • [Journal Article] Real-time tsunami risk evaluation method by synthetic dynamics and Bayesian update2022

    • Author(s)
      野村 怜佳, 藤田 真粹, 大竹 雄, 森口 周二, 越村 俊一, 寺田 賢二郎, 橋詰 正広
    • Journal Title

      Transactions of the Japan Society for Computational Engineering and Science

      Volume: 2022 Issue: 0 Pages: 20220003-20220003

    • DOI

      10.11421/jsces.2022.20220003

    • ISSN
      1344-9443, 1347-8826
    • Year and Date
      2022-05-19
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Sequential Bayesian update to detect the most likely tsunami scenario using observational wave sequences2022

    • Author(s)
      Reika Nomura, Saneiki Fujita, Joseph M. Galbreath, Yu Otake, Shuji Moriguchi, Shunichi Koshimura, Randall J. LeVeque, Kenjiro Terada
    • Journal Title

      Journal of Geophysical Research: Oceans

      Volume: 127(10) Issue: 10

    • DOI

      10.1029/2021jc018324

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Presentation] 地盤変動データの利用による逐次更新型津波シナリオ推定の精度向上に関する検討2022

    • Author(s)
      野村怜佳
    • Organizer
      第25回応用力学シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Improvement of a tsunami scenario detection framework by using synthetic geodetic data2022

    • Author(s)
      Reika Nomura, Saneiki Fujita, Louise A. Hirao Vermare, Yu Otake, Shuji Moriguchi, Diego Melgar, Randall J. LeVeque, Kenjiro Terada
    • Organizer
      15th World Congress on Computational Mechanics (WCCM-XV) 8th Asian Pacific Congress on Computational Mechanics (APCOM-VIII)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 数値シミュレーションとデータサイエンスの融合による津波リスク評価技術の開発2022

    • Author(s)
      野村怜佳
    • Organizer
      土木学会応用力学委員会 計算力学小委員会×α 関東地区フォーラム
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] Real-time tsunami forecast/update system by combined use of TUNAMI-N2 simulations and POD: A case study in Nankai subduction zone in Japan2021

    • Author(s)
      Reika Nomura, Joseph M. Galbreath,Yu Otake,Shunichi Koshimura,Shuji Moriguchi,Kenjiro Terada
    • Organizer
      Mechanistic Machine Learning and Digital Twins for Computational Science, Engineering & Technology (MMLD-CSET 2021)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2021-10-22   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi