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

Deep Learning of Artificial Neural Network for Short-term Rainfall Forecasting

Research Project

Project/Area Number 17K18903
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Research Field Civil engineering and related fields
Research InstitutionKyoto University

Principal Investigator

Kim Sunmin  京都大学, 工学研究科, 准教授 (10546013)

Project Period (FY) 2017-06-30 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥6,240,000 (Direct Cost: ¥4,800,000、Indirect Cost: ¥1,440,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Keywords降雨予測 / 深層学習 / CNN / 機械学習 / 気象データ / 衛星データ / 豪雨予測 / 気象観測データ / 畳み込みニューラルネットワーク / 人工知能 / 短期降雨予測
Outline of Final Research Achievements

This study investigated the applicability of convolutional neural network (CNN) and convolutional encoder-decoder network (ConvED) to develop a new concept of rainfall forecasting model. CNN and ConvED are well known machine learning algorithm that is specialized in image recognition.
In this study, three-dimensional spatiotemporal data was created with the time series of multiple atmospheric variables from Amedas point gauged data and Himawari satellite observation data. This three-dimensional data array (time-space-variable) is treated as an image with multiple color channels, and it is utilized into CNN and ConvED algorithms to predict rainfall occurrence and rainfall amount in 30 min lead-time.

Academic Significance and Societal Importance of the Research Achievements

本研究は「ANNの深層学習のアルゴリズムは、物理モデルの代わりとして定量的な答えを精度よく出せるのか」の疑問に答えを探すために、そして「ANNの深層学習を物理モデルの代わりとして活用するためにはどのような構造や学習アルゴリズムが必要なのか」を一歩早く調べてその知識を活用するために企画された。
特に、理学・工学の中で最も難しいテーマの一つである短時間降雨予測を対象にCNNとConvEDアルゴリズムを活用して実験を行い、深層学習のアルゴリズムは複雑な自然現象を表現することが十分可能であることを確認した。深層学習のアルゴリズムを活用して、新たな概念の予測モデルを作成することができた。

Report

(4 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (12 results)

All 2019 2018 2017

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

  • [Journal Article] Sensitivity analysis on data array and model structure of convolutional neural network for rainfall occurrence prediction2019

    • Author(s)
      Moonsun PARK, Sunmin KIM, Tsuguaki SUZUKI, Yasuto TACHIKAWA
    • Journal Title

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

      Volume: 75

    • NAID

      130007940012

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Real time river-stage prediction by ANN with observed rainfall and river-stage information2019

    • Author(s)
      Sumaiya TAZIN, Sunmin KIM, Yasuto TACHIKAWA
    • Journal Title

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

      Volume: 75

    • NAID

      130007940152

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Sensitivity Analysis on Data Array and Model Structure of Convolutional Neural Network for Rainfall Occurrence Prediction2019

    • Author(s)
      PARK MOONSUN、KIM SUNMIN、鈴木 紹晟、立川 康人
    • Journal Title

      Proceeding of Annual Conference

      Volume: 32 Issue: 0 Pages: 130

    • DOI

      10.11520/jshwr.32.0_130

    • NAID

      130007759902

    • Related Report
      2019 Annual Research Report
  • [Journal Article] 豪雨の発生予測に対する畳み込みニューラルネットワークの応用2018

    • Author(s)
      鈴木紹晟・キムスンミン・立川康人・市川温・萬和明
    • Journal Title

      土木学会論文集B1(水工学)

      Volume: 74 Pages: 00-00

    • NAID

      130007757781

    • Related Report
      2018 Research-status Report
    • Peer Reviewed
  • [Journal Article] Real-Time River-Stage Prediction With Artificial Neural Network Based On Only Upstream Observation Data2018

    • Author(s)
      Sunmin Kim and Yasuto Tachikawa
    • Journal Title

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

      Volume: 73 Pages: 00-00

    • NAID

      130007628172

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] ニューラルネットワークを用いた積雪地域の河川流量予測における重要入力因子の抽出2018

    • Author(s)
      滝口修司・キムスンミン・立川康人・市川 温・萬 和明
    • Journal Title

      土木学会論文集B1(水工学)

      Volume: 73 Pages: 00-00

    • NAID

      130007628262

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Presentation] Sensitivity analysis on data array and model structure of convolutional neural network for rainfall occurrence prediction2019

    • Author(s)
      Moonsun PARK, Sunmin KIM, Tsuguaki SUZUKI, Yasuto TACHIKAWA
    • Organizer
      Annual Conference of Hydraulic Engineering, JSCE
    • Related Report
      2019 Annual Research Report
  • [Presentation] Real time river-stage prediction by ANN with observed rainfall and river-stage information2019

    • Author(s)
      Sumaiya TAZIN, Sunmin KIM, Yasuto TACHIKAWA
    • Organizer
      Annual Conference of Hydraulic Engineering, JSCE
    • Related Report
      2019 Annual Research Report
  • [Presentation] Real-Time River-Stage Prediction with ANN Based on Upstream River-Stage Data2018

    • Author(s)
      Sunmin Kim and Yasuto Tachikawa
    • Organizer
      KWRA 2018 Annual Conference
    • Related Report
      2018 Research-status Report
  • [Presentation] River-stage Prediction with Artificial Neural Network based on Only Upstream Observation Data2018

    • Author(s)
      Sunmin Kim and Yasuto Tachikawa
    • Organizer
      The 12th International Symposium on Climate Change and UAV Application on Floods and Droughts in Asia Region
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] ANNを用いた河川流量予測における入力データ選択に関する考察2017

    • Author(s)
      滝口 修司, キム スンミン, 立川 康人, 市川 温, 萬 和明
    • Organizer
      水文・水資源学会研究発表会
    • Related Report
      2017 Research-status Report
  • [Presentation] Hydrologic Forecasting In Snow Dominent Region With Ann Algorithm2017

    • Author(s)
      Sunmin Kim and Yasuto Tachikawa
    • Organizer
      KWRA 2017 Annual Conference
    • Related Report
      2017 Research-status Report

URL: 

Published: 2017-07-21   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi