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

Development of Dam Operation Support Technology for Minimizing Flood Damage Using Machine Learning Methods

Research Project

Project/Area Number 20K04698
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 22040:Hydroengineering-related
Research InstitutionMuroran Institute of Technology

Principal Investigator

Nakatsugawa Makoto  室蘭工業大学, 大学院工学研究科, 教授 (10344425)

Co-Investigator(Kenkyū-buntansha) 小林 洋介  室蘭工業大学, 大学院工学研究科, 助教 (10735103)
一言 正之  日本工営株式会社中央研究所, 先端研究開発センター, 研究員 (40463559)
Project Period (FY) 2020-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2022: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2021: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2020: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywordsダム流入量予測 / 機械学習 / スパースモデリング / Elastic Net / 未経験事例 / 予測手法の一般化 / 気候変動 / 事前放流 / クラスター分析 / 異常洪水時防災操作 / ダム群の連携 / ダム貯水位予測 / 機械学習法 / ダム操作判断支援 / 異常洪水時 / ダム操作 / 貯水位予測
Outline of Research at the Start

近年,気候変動の影響とみられる大雨によってダムの貯水池が満杯となり,洪水調節ができなくなる事態が起きている。これを回避するために,ダムへの流入量を予測し,事前に放流して貯水量を増やす操作が考えられる。
操作に関わる流入量や貯水位の予測において,最近は,過去の事例を学習させて流出量や水位を予測する機械学習法が注目されている。これには過去に経験していない(未経験)事例の予測は難しいという課題がある。
それに対し,我々はスパースモデリングの手法が,未経験事例の予測にも有用であるとの見解を示した。本研究は,未経験事例にも適用可能な機械学習法によるダム貯水位の予測手法とダム操作の判断支援手法を提案する。

Outline of Final Research Achievements

This research aims to improve the flood control function of dams by utilizing the large amount of accumulated and disclosed meteorological and hydrological information and based on the remarkable progress of machine learning methods. Specifically, the primary mission is to improve the accuracy of inflow prediction to develop technology that can be implemented in flood control measures that can respond to floods that are becoming more severe due to climate change.
Therefore, the prediction accuracy for "non-experienced cases" can be improved by applying "the Elastic Net", a representative method of sparse modeling, and considering the soil moisture state. In addition, by grouping the catchment area and using a representative model, it is possible to generalize the inflow prediction method that can be applied to an unspecified number of dams.

Academic Significance and Societal Importance of the Research Achievements

気候変動によって頻発・激甚化する水害に対し,あらゆる関係者が防災・減災に取り組む「流域治水」の推進を念頭に,ダムの能力の最大限の活用が求められている。本研究は,蓄積公開が進む大量の気象水文情報および進歩の目覚ましい機械学習法を活用し,流入量予測の精度向上手法に取り組んだ。
この結果,未経験の洪水への対処でき,手法の一般化を図ることで,今後の気候変動で予想される大規模水害に,不特定多数のダムに適用できる予測手法を提案できたことが学術的意義となる。また,その技術が治水能力の向上を促進し,今後推進が図られる流域治水に貢献できることが社会的意義となる。

Report

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

    (24 results)

All 2023 2022 2021 2020 Other

All Journal Article (10 results) (of which Peer Reviewed: 10 results) Presentation (13 results) (of which Int'l Joint Research: 4 results) Remarks (1 results)

  • [Journal Article] RESEARCH ON FLOOD RISK REDUCTION IN SNOWY COLD REGION THROUGH DAM LINKAGE2022

    • Author(s)
      NISHIJIIMA Seren、NAKATSUGAWA Makoto
    • Journal Title

      Journal of Japan Society of Civil Engineers, Ser. B1 (Hydraulic Engineering)

      Volume: 78 Issue: 2 Pages: I_1273-I_1278

    • DOI

      10.2208/jscejhe.78.2_I_1273

    • ISSN
      2185-467X
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] EVALUATION OF APPLICABILITY OF DATA AUGMENTATION METHOD FOR DAM INFLOW PREDICTION USING DEEP LEARNING2022

    • Author(s)
      HITOKOTO Masayuki、ARAKI Takeru、HAKOISHI Kenta、ENDO Yuto
    • Journal Title

      Journal of Japan Society of Civil Engineers, Ser. B1 (Hydraulic Engineering)

      Volume: 78 Issue: 2 Pages: I_175-I_180

    • DOI

      10.2208/jscejhe.78.2_I_175

    • ISSN
      2185-467X
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] A STUDY ON THE GENERALIZATION OF DAM INFLOW PREDICTION METHOD USING THE ELASTIC NET2022

    • Author(s)
      小嶋 侑、中津川 誠、小林 洋介、山洞 智弘
    • Journal Title

      Intelligence, Informatics and Infrastructure

      Volume: 3 Issue: J2 Pages: 498-507

    • DOI

      10.11532/jsceiii.3.J2_498

    • ISSN
      2435-9262
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] PERFORMANCE COMPARISON OF RIVER WATER LEVEL PREDICTION USING SPARSE MODELING ASSUMING HEAVY RAIN DISASTER2022

    • Author(s)
      高宮 立、小林 洋介、中津川 誠、山洞 智弘
    • Journal Title

      Intelligence, Informatics and Infrastructure

      Volume: 3 Issue: J2 Pages: 446-455

    • DOI

      10.11532/jsceiii.3.J2_446

    • ISSN
      2435-9262
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] PROPOSAL FOR DATA AUGMENTATION METHOD FOR DAM INFLOW PREDICTION USING DEEP LEARNING - IMPROVEMENT OF APPLICABILITY FOR UNPRECEDENTED SCALE RUNOFF -2022

    • Author(s)
      一言 正之、荒木 健、箱石 健太、遠藤 優斗
    • Journal Title

      Advances in River Engineering

      Volume: 28 Issue: 0 Pages: 67-72

    • DOI

      10.11532/river.28.0_67

    • ISSN
      2436-6714
    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] STUDY ON THE FREQUENCY OF EMERGENCY SPILLWAY GATE OPERATION IN MULTIPLE-PURPOSE DAMS IN SNOWY AREAS DUE TO CLIMATE CHANGE2021

    • Author(s)
      NISHIJIMA Seren、NAKATSUGAWA Makoto、SANDOU Tomohiro
    • Journal Title

      Journal of Japan Society of Civil Engineers, Ser. B1 (Hydraulic Engineering)

      Volume: 77 Issue: 2 Pages: I_43-I_48

    • DOI

      10.2208/jscejhe.77.2_I_43

    • NAID

      130008160139

    • ISSN
      2185-467X
    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] PREDICTION OF DAM STORAGE LEVELS AND THE VOLUME OF DISCHARGE ASSOCIATED WITH DISASTER PREVENTION MANAGEMENT DURING EXTREME FLOODING USING ELASTIC NET2021

    • Author(s)
      WAKASAYA Shoma、NAKATSUGAWA Makoto、KOBAYASHI Yosuke、SANDO Tomohiro
    • Journal Title

      Journal of Japan Society of Civil Engineers, Ser. B1 (Hydraulic Engineering)

      Volume: 77 Issue: 2 Pages: I_67-I_72

    • DOI

      10.2208/jscejhe.77.2_I_67

    • NAID

      130008160195

    • ISSN
      2185-467X
    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] EXTRAPOLATION OF PREDICTIONS OF DAM INFLOW BASED ON THE SPARSE MODELING METHOD2021

    • Author(s)
      山洞 智弘、中津川 誠、小林 洋介
    • Journal Title

      Intelligence, Informatics and Infrastructure

      Volume: 2 Issue: J2 Pages: 393-399

    • DOI

      10.11532/jsceiii.2.J2_393

    • NAID

      130008118369

    • ISSN
      2435-9262
    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] APPLICATION OF DAM OPERATION MODEL USING DEEP REINFORCEMENT LEARNING IN RECENT FLOOD CASES2021

    • Author(s)
      箱石 健太、一言 正之
    • Journal Title

      Intelligence, Informatics and Infrastructure

      Volume: 2 Issue: J2 Pages: 165-171

    • DOI

      10.11532/jsceiii.2.J2_165

    • NAID

      130008118245

    • ISSN
      2435-9262
    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] 未経験洪水事例に適用できるElastic Netによる24時間先までのダム流入量予測手法の提案2020

    • Author(s)
      山洞智弘, 中津川誠, 小林洋介, 坂本莉子
    • Journal Title

      土木学会論文集B1(水工学)

      Volume: 76

    • NAID

      130008122737

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Presentation] 機械学習手法に基づくダム流入量予測の一般化に関する研究2023

    • Author(s)
      佐藤匠, 小嶋侑, 中津川誠, 小林洋介
    • Organizer
      令和4年度土木学会北海道支部
    • Related Report
      2022 Annual Research Report
  • [Presentation] 予測雨量の不確実性を考慮したダム流入量予測の研究2023

    • Author(s)
      渡辺修, 若狭谷昇真, 中津川誠, 小林洋介
    • Organizer
      令和4年度土木学会北海道支部
    • Related Report
      2022 Annual Research Report
  • [Presentation] Prediction of Dam Reservoir Level and Downstream River Level as Influenced by Discharge Based on a Machine Learning Method2022

    • Author(s)
      Shoma Wakasaya, Makoto Nakatsugawa, Yosuke Kobayashi, Tomohiro Sando
    • Organizer
      the 39th IAHR World Congress
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Frequency of the Emergency Discharge Operation of Dams in Snowy Regions Considering the Uncertainty of Heavy Rain and Snowmelt Due to Climate Change2022

    • Author(s)
      Seren Nishijima, Makoto Nakatsugawa, Tomohiro Sando
    • Organizer
      the 39th IAHR World Congress
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Research on Practical Predictions of Dam Inflow Based on the Sparse Modeling Method2022

    • Author(s)
      Makoto Nakatsugawa, Tomohiro Sando;Yosuke Kobayashi
    • Organizer
      the 39th IAHR World Congress
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Elastic Netを用いた利水専用ダムの流入量と貯水位の予測に関する研究2022

    • Author(s)
      小嶋 侑, 中津川 誠, 山洞 智弘, 小林 洋介
    • Organizer
      第77回土木学会年次学術講演会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 機械学習手法による幌別ダムの流入量と貯水位の予測に関する研究2022

    • Author(s)
      小嶋 侑, 山洞 智弘, 中津川 誠, 小林 洋介
    • Organizer
      令和3年度土木学会北海道支部
    • Related Report
      2021 Research-status Report
  • [Presentation] 気候変動に伴う定山渓ダムの異常洪水時防災操作実施頻度の推定2022

    • Author(s)
      近藤 一平,西島 星蓮,中津川 誠
    • Organizer
      令和3年度土木学会北海道支部
    • Related Report
      2021 Research-status Report
  • [Presentation] メソ数値予報を入力値としたElastic Netによるダム貯水位予測の研究2022

    • Author(s)
      西尾 優輝,若狭谷 昇真,中津川 誠,小林 洋介
    • Organizer
      令和3年度土木学会北海道支部
    • Related Report
      2021 Research-status Report
  • [Presentation] Elastic Netを用いた未経験洪水事例を対象とした河川水位予測2021

    • Author(s)
      若狭谷 昇真,山洞 智弘,中津川 誠,小林 洋介
    • Organizer
      令和3年度土木学会全国大会第76回年次学術講演会
    • Related Report
      2021 Research-status Report
  • [Presentation] Elastic Netを用いた大河川下流部の水位予測の研究2021

    • Author(s)
      若狭谷昇真, 山洞智弘, 中津川誠, 小林洋介
    • Organizer
      土木学会北海道支部
    • Related Report
      2020 Research-status Report
  • [Presentation] 北海道のダムを対象とした回帰手法に基づくダム流入量予測の一般化の研究2021

    • Author(s)
      神坂敬伍, 山洞智弘, 中津川誠, 小林洋介
    • Organizer
      土木学会北海道支部
    • Related Report
      2020 Research-status Report
  • [Presentation] RESEARCH ON DAM INFLOW PREDICTION DURING SEVERE FLOOD USING MACHINE LEARNING METHODS2020

    • Author(s)
      MAKOTO NAKATSUGAWA, RIKO SAKAMOTO, YOSUKE KOBAYASHI
    • Organizer
      IAHR-APD Congress 2020
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Remarks] 水環境システム研究室[中津川研]研究内容

    • URL

      https://u.muroran-it.ac.jp/riverlab/research.html

    • Related Report
      2022 Annual Research 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