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

Elucidation of impacts of climate changes on spatio-temporal distributions of marine animals using machine learning approaches

Research Project

Project/Area Number 19K06216
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 40030:Aquatic bioproduction science-related
Research InstitutionFisheries Research and Education Agency

Principal Investigator

Okamura Hiroshi  国立研究開発法人水産研究・教育機構, 水産資源研究所(横浜), 主幹研究員 (40371942)

Co-Investigator(Kenkyū-buntansha) 黒田 寛  国立研究開発法人水産研究・教育機構, 水産資源研究所(札幌), 主任研究員 (30531107)
森田 晶子  国立研究開発法人水産研究・教育機構, 水産資源研究所(札幌), 主任研究員 (40443387)
Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2020: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Keywords水産資源評価 / 漁業管理 / 機械学習 / 頑健推定 / 海面水温 / 予測 / 加入予測 / 勾配ブースティング / 資源管理 / 時空間モデル / 統計的機械学習 / 資源量指標値 / 再生産関係 / 親潮 / 西部亜寒帯循環 / 時空間分布解析 / 海洋環境と密度変化 / 時空間分布予測 / 環境影響
Outline of Research at the Start

統計的機械学習手法を活用して,環境変動と海洋生物の資源量指標値の時空間変動の関係を正確に予測するモデルの開発を行い,多魚種を対象とした漁獲データに適用する.さらに,その統計モデルから得られるアウトプットに漁業・生物情報を加え,因果関係推定が可能となるメカニスティックなモデルを適用することにより,時空間的な個体群動態の変化を記述する個体群動態モデルを構築し,それに基づく将来予測から多魚種を対象とする漁業における最適な漁獲戦略を導く方法を探索し,実際の多魚種漁業資源の漁獲データへの適用を図る.

Outline of Final Research Achievements

Spatiotemporal model analysis of fish, prediction of stock-recruitment relationship, and prediction of fish recruitment were conducted. In particular, we used statistical machine learning methods to predict recruitment for arabesque greenling. The linear regression model (LRM), random forest model (RFM), and gradient boosting model (GBM) were compared, and GBM had the best prediction performance; the most influential factor on recruitment in GBM was spawning stock biomass, followed by catch rates of older fish. SST had a small effect, but the overall effect was weak, and the variability seemed to be more effective than the warming trend. On the other hand, in LRM, SST was the most influential factor. The differences between the models suggest the importance of nonlinearities and variable interactions.

Academic Significance and Societal Importance of the Research Achievements

複数の海面水温データを取得し,北海道周辺の海面水温データセットを整備した.整備した海面水温データセットは,様々な解析に利用可能である.また,再生産関係を頑健に推定する統計手法の開発を行った.従来の頑健推定手法に比較して,外れ値の影響を軽減しつつ,自己相関を正確に推定することが可能な手法となっている.さらに,機械学習手法を活用して,加入尾数を精度良く予測する手法の開発を行った.これらは,水産資源の持続的利用に大きく貢献するものと考えられ,社会的な意義が大きい.また,手法をさらに発展・一般化させることにより,他分野のデータにも利用可能なものと考えられ,学術的な意義も大きい.

Report

(5 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (8 results)

All 2023 2021 2020 2019

All Journal Article (5 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 5 results,  Open Access: 4 results) Presentation (3 results)

  • [Journal Article] Co-occurrence of marine extremes induced by tropical storms and an ocean eddy in summer 2016: Anomalous hydrographic conditions in the Pacific shelf waters off southeast Hokkaido, Japan.2021

    • Author(s)
      Kuroda, H., Y. Taniuchi, H. Kasai, T. Nakanowatari and T. Setou
    • Journal Title

      Atmosphere

      Volume: 12 Issue: 7 Pages: 888-888

    • DOI

      10.3390/atmos12070888

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Extensive marine heatwaves at the sea surface in the northwestern Pacific Ocean in summer 2021.2021

    • Author(s)
      Kuroda, H. and T. Setou
    • Journal Title

      Remote Sensing

      Volume: 13 Issue: 19 Pages: 3989-3989

    • DOI

      10.3390/rs13193989

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Novel robust time series analysis for long-term and short-term prediction2021

    • Author(s)
      H Okamura, Y Osada, S Nishijima, S Eguchi
    • Journal Title

      Scientific reports

      Volume: 11 Issue: 1

    • DOI

      10.1038/s41598-021-91327-8

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] High-Resolution Sea Surface Temperatures Derived from Landsat 8: A Study of Submesoscale Frontal Structures on the Pacific Shelf off the Hokkaido Coast, Japan2020

    • Author(s)
      Hiroshi Kuroda, Yuko Toya
    • Journal Title

      Resmote Sensing

      Volume: 12 Issue: 20 Pages: 3326-3326

    • DOI

      10.3390/rs12203326

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] ESTIMATION OF PELAGIC FISH DISTRIBUTION IN INNER BAY WITH MACHINE LEARNING2019

    • Author(s)
      濱田 孝治, 吉田 司, 岡村 寛, 原 武史, 鈴木 輝明
    • Journal Title

      Journal of Japan Society of Civil Engineers, Ser. B2 (Coastal Engineering)

      Volume: 75 Issue: 2 Pages: I_1129-I_1134

    • DOI

      10.2208/kaigan.75.I_1129

    • NAID

      130007730114

    • ISSN
      1883-8944, 1884-2399
    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Presentation] LIS:複雑なCPUE標準化の解釈2023

    • Author(s)
      岡村 寛・森田晶子
    • Organizer
      日本水産学会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 頑健な再生産関係の推定2020

    • Author(s)
      岡村 寛,長田 穣,西嶋 翔太
    • Organizer
      水産海洋学会
    • Related Report
      2020 Research-status Report
  • [Presentation] 北海道日本海およびオホーツク海におけるホッケ0歳魚と成魚の分布密度の時空間変化2020

    • Author(s)
      森田晶子・千村昌之・濱津友紀・石野光弘・山下夕帆・西嶋翔太・岡村寛
    • Organizer
      令和2年度日本水産学会春季大会
    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi