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

New Development of Strong Motion Evaluation and Realtime Prediction by Deep Learning

Research Project

Project/Area Number 19K22002
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Review Section Medium-sized Section 23:Architecture, building engineering, and related fields
Research InstitutionTohoku University

Principal Investigator

OHNO SUSUMU  東北大学, 災害科学国際研究所, 准教授 (40361141)

Project Period (FY) 2019-06-28 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥6,110,000 (Direct Cost: ¥4,700,000、Indirect Cost: ¥1,410,000)
Fiscal Year 2021: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2020: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2019: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Keywords深層学習 / 強震動評価 / 建物応答 / 即時予測
Outline of Research at the Start

建築構造物の地震安全性を向上させるためには,建物側に比べて精度が低い地震動の評価精度の向上が不可欠である。ニューラルネットは,豊富なデータがあれば非常に複雑な現象であっても精度よくモデル化できること,その適用が即時かつ容易であることが特徴であり,強震動の高精度予測や地震時の即時評価が可能となれば,防災上の波及効果は大きい。本研究では,深層学習を用いた強震動予測や地震動の即時評価・面的評価に挑戦する。

Outline of Final Research Achievements

In order to mainly improve the evaluation accuracy of seismic motion, which is less accurate than that of the building side, this study challenged the prediction of strong ground motion, real-time and spatial evaluation of seismic motion, and building response prediction using deep learning. We used a large number of strong-motion records including large-amplitude records of the Tohoku region, Japan.
Although it should be noted that deep learning is highly dependent on the number and distribution of data, we showed that deep learning can model complex phenomena and contribute to evaluation accuracy improvement. Although it takes time to learn, neural network can be applied immediately and is effective for earthquake early warning and immediate response for earthquake disasters.

Academic Significance and Societal Importance of the Research Achievements

深層学習による物理シミュレーションの代理モデル作成は,複雑な現象をモデル化できること,学習に時間はかかるが即時に適用可能な点が大きな特徴である。本研究では,単に震度予測にとどまらず,建物では高次モードまで含めた多成分の応答波形予測が可能であること,地震動では事前予測としてスペクトルの高精度評価,早期地震警報としてスペクトルの即時予測,地震直後ではスペクトルの面的評価がそれぞれ可能であることを示した。早期地震警報や発災時対応に有効と思われる。

Report

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

    (10 results)

All 2022 2021 2020

All Journal Article (2 results) (of which Peer Reviewed: 2 results) Presentation (8 results)

  • [Journal Article] Deep learning techniques for predicting nonlinear multi-component seismic responses of structural buildings2021

    • Author(s)
      Torky Ahmed A.、Ohno Susumu
    • Journal Title

      Computers & Structures

      Volume: 252 Pages: 106570-106570

    • DOI

      10.1016/j.compstruc.2021.106570

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] DEEP LEARNING TECHNIQUES FOR STRUCTURAL RESPONSE PREDICTION DURING STRONG GROUND MOTIONS2020

    • Author(s)
      A. A. Torky, S. Ohno, T. Kashima
    • Journal Title

      Proc. 17WCEE

      Volume: 9c Pages: 0018-0018

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Presentation] Deep Learning Technique for Temporal Site-to-Site Seismic Predictions using short-interval Fourier Amplitude Spectra2022

    • Author(s)
      Ahmed Alaaeldean Torky, Susumu Ohno
    • Organizer
      Japan Geoscience Union Meeting 2022
    • Related Report
      2021 Annual Research Report
  • [Presentation] 深層学習を用いた地震動応答スペクトルの準即時面的予測2021

    • Author(s)
      森川拓海・Torky Ahmed・大野晋
    • Organizer
      日本建築学会大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 深層学習を用いた地震動スペクトル評価の検討2020

    • Author(s)
      松岡恭平・大野晋
    • Organizer
      日本建築学会東北支部研究報告会
    • Related Report
      2020 Research-status Report
  • [Presentation] A Deep Learning Approach to Dynamic Response Predictions for Structures2020

    • Author(s)
      A. A. Torky, S. Ohno, T. Kashima
    • Organizer
      日本建築学会大会
    • Related Report
      2020 Research-status Report
  • [Presentation] 深層学習を用いた地震動スペクトル評価の検討2020

    • Author(s)
      松岡恭平・大野晋
    • Organizer
      日本建築学会大会
    • Related Report
      2020 Research-status Report
  • [Presentation] 深層学習による強震動スペクトル評価2020

    • Author(s)
      大野晋,松岡恭平
    • Organizer
      第48回地盤震動シンポジウム
    • Related Report
      2020 Research-status Report
  • [Presentation] 機械学習を用いた地震動スペクトル評価に関する検討2020

    • Author(s)
      松岡恭平・大野晋
    • Organizer
      日本地震工学会第15回年次大会
    • Related Report
      2020 Research-status Report
  • [Presentation] Deep Learning Predictions of Seismic Capacity Curves of Buildings2020

    • Author(s)
      A. A. Torky, S. Ohno
    • Organizer
      日本地震工学会第15回年次大会
    • Related Report
      2020 Research-status Report

URL: 

Published: 2019-07-04   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi