딥러닝 기반 침수 수위 예측: 미국 텍사스 트리니티강 사례연구

This paper presents an attempt to apply Deep Learning technology to solve the problem of forecasting floods in urban areas. We employ Recurrent Neural Networks (RNNs), which are suitable for analyzing time series data, to learn observed data of river water and to predict the water level. To test the...

Full description

Saved in:
Bibliographic Details
Published inChŏngbo Kwahakhoe nonmunji Vol. 44; no. 6; pp. 607 - 612
Main Authors 트란 광 카이, 송사광, Tran, Quang-Khai, Song, Sa-kwang
Format Journal Article
LanguageKorean
Published 한국정보과학회 01.06.2017
Subjects
Online AccessGet full text
ISSN2383-630X
2383-6296

Cover

Abstract This paper presents an attempt to apply Deep Learning technology to solve the problem of forecasting floods in urban areas. We employ Recurrent Neural Networks (RNNs), which are suitable for analyzing time series data, to learn observed data of river water and to predict the water level. To test the model, we use water observation data of a station in the Trinity river, Texas, the U.S., with data from 2013 to 2015 for training and data in 2016 for testing. Input of the neural networks is a 16-record-length sequence of 15-minute-interval time-series data, and output is the predicted value of the water level at the next 30 minutes and 60 minutes. In the experiment, we compare three Deep Learning models including standard RNN, RNN trained with Back Propagation Through Time (RNN-BPTT), and Long Short-Term Memory (LSTM). The prediction quality of LSTM can obtain Nash Efficiency exceeding 0.98, while the standard RNN and RNN-BPTT also provide very high accuracy. 도시에서 홍수 피해를 방지하기 위한 침수를 예측하기 위해 본 논문에서는 딥러닝(Deep Learning) 기법을 적용한다. 딥러닝 기법 중 시계열 데이터 분석에 적합한 Recurrent Neural Networks (RNNs)을 활용하여 강의 수위 관측 데이터를 학습하고 침수 가능성을 예측하였다. 예측 정확도 검증을 위해 사용한 데이터는 미국의 트리니티강의 데이터로, 학습을 위해 2013 년부터 2015 년까지 데이터를 사용하였고 평가 데이터로는 2016 년 데이터를 사용하였다. 입력은 16개의 레코드로 구성된 15분단위의 시계열 데이터를 사용하였고, 출력으로는 30분과 60분 후의 강의 수위 예측 정보이다. 실험에 사용한 딥러닝 모델들은 표준 RNN, RNN-BPTT(Back Propagation Through Time), LSTM(Long Short-Term Memory)을 사용했는데, 그 중 LSTM의 NE(Nash Efficiency)가 0.98을 넘는 정확도로 기존 연구에 비해 매우 높은 성능 향상을 보였고, 표준 RNN과 RNN-BPTT에 비해서도 좋은 성능을 보였다.
AbstractList 도시에서 홍수 피해를 방지하기 위한 침수를 예측하기 위해 본 논문에서는 딥러닝(Deep Learning) 기법을 적용한다. 딥러닝 기법 중 시계열 데이터 분석에 적합한 Recurrent Neural Networks (RNNs)을 활용하여 강의 수위 관측 데이터를 학습하고 침수 가능성을 예측하였다. 예측 정확도 검증을 위해 사용한 데이터는 미국의 트리니티강의 데이터로, 학습을 위해 2013 년부터 2015 년까지 데이터를 사용하였고 평가 데이터로는 2016 년 데이터를 사용하였다. 입력은 16개의 레코드로 구성된 15분단위의 시계열 데이터를 사용하였고, 출력으로는 30분과 60분 후의 강의 수위 예측 정보이다. 실험에 사용한 딥러닝 모델들은 표준 RNN, RNN-BPTT(Back Propagation Through Time), LSTM(Long Short-Term Memory)을 사용했는데, 그 중 LSTM의 NE(Nash Efficiency)가 0.98을 넘는 정확도로 기존 연구에 비해 매우 높은 성능 향상을 보였고, 표준 RNN과 RNN-BPTT에 비해서도 좋은 성능을 보였다. This paper presents an attempt to apply Deep Learning technology to solve the problem of forecasting floods in urban areas. We employ Recurrent Neural Networks (RNNs), which are suitable for analyzing time series data, to learn observed data of river water and to predict the water level. To test the model, we use water observation data of a station in the Trinity river, Texas, the U.S., with data from 2013 to 2015 for training and data in 2016 for testing. Input of the neural networks is a 16-record-length sequence of 15-minute-interval time-series data, and output is the predicted value of the water level at the next 30 minutes and 60 minutes. In the experiment, we compare three Deep Learning models including standard RNN, RNN trained with Back Propagation Through Time (RNN-BPTT), and Long Short-Term Memory (LSTM). The prediction quality of LSTM can obtain Nash Efficiency exceeding 0.98, while the standard RNN and RNN-BPTT also provide very high accuracy. KCI Citation Count: 9
This paper presents an attempt to apply Deep Learning technology to solve the problem of forecasting floods in urban areas. We employ Recurrent Neural Networks (RNNs), which are suitable for analyzing time series data, to learn observed data of river water and to predict the water level. To test the model, we use water observation data of a station in the Trinity river, Texas, the U.S., with data from 2013 to 2015 for training and data in 2016 for testing. Input of the neural networks is a 16-record-length sequence of 15-minute-interval time-series data, and output is the predicted value of the water level at the next 30 minutes and 60 minutes. In the experiment, we compare three Deep Learning models including standard RNN, RNN trained with Back Propagation Through Time (RNN-BPTT), and Long Short-Term Memory (LSTM). The prediction quality of LSTM can obtain Nash Efficiency exceeding 0.98, while the standard RNN and RNN-BPTT also provide very high accuracy. 도시에서 홍수 피해를 방지하기 위한 침수를 예측하기 위해 본 논문에서는 딥러닝(Deep Learning) 기법을 적용한다. 딥러닝 기법 중 시계열 데이터 분석에 적합한 Recurrent Neural Networks (RNNs)을 활용하여 강의 수위 관측 데이터를 학습하고 침수 가능성을 예측하였다. 예측 정확도 검증을 위해 사용한 데이터는 미국의 트리니티강의 데이터로, 학습을 위해 2013 년부터 2015 년까지 데이터를 사용하였고 평가 데이터로는 2016 년 데이터를 사용하였다. 입력은 16개의 레코드로 구성된 15분단위의 시계열 데이터를 사용하였고, 출력으로는 30분과 60분 후의 강의 수위 예측 정보이다. 실험에 사용한 딥러닝 모델들은 표준 RNN, RNN-BPTT(Back Propagation Through Time), LSTM(Long Short-Term Memory)을 사용했는데, 그 중 LSTM의 NE(Nash Efficiency)가 0.98을 넘는 정확도로 기존 연구에 비해 매우 높은 성능 향상을 보였고, 표준 RNN과 RNN-BPTT에 비해서도 좋은 성능을 보였다.
Author Tran, Quang-Khai
송사광
Song, Sa-kwang
트란 광 카이
Author_xml – sequence: 1
  fullname: 트란 광 카이
– sequence: 2
  fullname: 송사광
– sequence: 3
  fullname: Tran, Quang-Khai
– sequence: 4
  fullname: Song, Sa-kwang
BackLink https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002230288$$DAccess content in National Research Foundation of Korea (NRF)
BookMark eNo1j81Kw0AAhINUsNa-Qy4ePAT2PxtvpfhTLRQkB29LtkkkpKTQ-AAiCqHFm2IOihRUPFTMpRBfKbt9B4PV0zcMMwOzbTSScRJsGE2EObYYcljjX2NwvmW00zSSAEGOCHdQ03DV_Zt6WajZs1mVhSpyU39_6KxGluunG1PnmS7n-6b6Kqvlp7m6vdPXCz19NVfTUr3XvWw1K6riwaxtNb_Sj0W1XOwYm6E3SoP2H1uGe3jgdo-t_uCo1-30rZgRbkEfSxkM_cAObTAkADjEDhzEKIY2DQOf2BRRT1KAfV9SIiUEzKMcsxAhDEOCW8beejaZhCIeRmLsRb-8GIt4Ijpnbk_A-jpzeJ3dXWfjKL2MROKnI3HSOR0gAG2EIMMEY8Ih_gEKvHRL
ContentType Journal Article
DBID JDI
ACYCR
DEWEY 005
DatabaseName KoreaScience
Korean Citation Index
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Library & Information Science
Computer Science
DocumentTitleAlternate Water Level Forecasting based on Deep Learning: A Use Case of Trinity River-Texas-The United States
EISSN 2383-6296
EndPage 612
ExternalDocumentID oai_kci_go_kr_ARTI_1383698
JAKO201722163433481
GroupedDBID ALMA_UNASSIGNED_HOLDINGS
JDI
ACYCR
ID FETCH-LOGICAL-k648-1d3bbecde7f70c400947e92653175fed47525ab503ddb54bb106a5836f2231f43
ISSN 2383-630X
IngestDate Tue Nov 21 21:29:15 EST 2023
Fri Dec 22 12:03:31 EST 2023
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Issue 6
Language Korean
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-k648-1d3bbecde7f70c400947e92653175fed47525ab503ddb54bb106a5836f2231f43
Notes KISTI1.1003/JNL.JAKO201722163433481
OpenAccessLink http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO201722163433481&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
PageCount 6
ParticipantIDs nrf_kci_oai_kci_go_kr_ARTI_1383698
kisti_ndsl_JAKO201722163433481
PublicationCentury 2000
PublicationDate 2017-06
PublicationDateYYYYMMDD 2017-06-01
PublicationDate_xml – month: 06
  year: 2017
  text: 2017-06
PublicationDecade 2010
PublicationTitle Chŏngbo Kwahakhoe nonmunji
PublicationTitleAlternate Journal of KIISE
PublicationYear 2017
Publisher 한국정보과학회
Publisher_xml – name: 한국정보과학회
SSID ssib021824892
ssib053377434
ssib044742769
ssj0000579380
ssib022331829
Score 1.6368505
Snippet This paper presents an attempt to apply Deep Learning technology to solve the problem of forecasting floods in urban areas. We employ Recurrent Neural Networks...
도시에서 홍수 피해를 방지하기 위한 침수를 예측하기 위해 본 논문에서는 딥러닝(Deep Learning) 기법을 적용한다. 딥러닝 기법 중 시계열 데이터 분석에 적합한...
SourceID nrf
kisti
SourceType Open Website
Open Access Repository
StartPage 607
SubjectTerms 컴퓨터학
Title 딥러닝 기반 침수 수위 예측: 미국 텍사스 트리니티강 사례연구
URI http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO201722163433481&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002230288
Volume 44
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
ispartofPNX 정보과학회논문지, 2017, 44(6), , pp.607-612
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2383-6296
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssib044742769
  issn: 2383-630X
  databaseCode: M~E
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NaxNBFB_anryIn1i1ZVHHS1jZ3czuznibbBJqC3qJ0FvYT1ujCdQWwYOIKIQWb4o9KFJQ8VAxl0L8l7Lb_8H3JrvdrShUL5PfvMy89_a9ycybzXwQcoO5YQDjrKuHTHCdhczXucUCPfQTZvoiMsJIrfK96yzdZ8ur9urM7PXKqqWtzeBW-OyP-0r-x6tAA7_iLtl_8OwRUyAABv9CCh6G9EQ-pq0GFYxKW4E2lR4CDrhZoy1JG5w2DCRBKjiQPNoQVHIEnBckhRAIwEyRIM8VCThIE98aIBfZxjzytalECU3KbcqbiomlpAOQVLLpd0oBrOeUmiHbJgJUTCrF7FqFQQPlcUMp4RaFQJxXjaK9NeqB4Hb_QTCorTz11_ze2iCu9Qf9x1v9h-tFIzqmhGgB26lVGBVmYQzIoKgmgLIaaOOgHqVaea3qOxLTLddyqVaN4oSNVixMhAwkPqHyQV0Jkwp4RWGhgKTcK7tkiG_qulM3VqejZ4Vmieow4Exv8s0jCidfKH7ssO_fBuFjx333wvXug0G3t9GFSc2drgkSHMFnySx0zrg69Xmr6DLx_H3Gyz_GIdiDTrqMeBlzmeVO75DPj7uHDlndJ3j0LDAtw7nKOkRX_Y2kEl11zpDT-bRIk9M2fpbM9AbnyEK-qUa7qeW75vCnpOXD0XnSSd9-ST_tpzsftcl4lI52teznt2wIH8Pd7MMrLdsdZuO921r6Yzw5-K4dvn6TvdzPtj9rh9vj9CvUGx7ujCajdxqQ070X2fvR5GD_Aum0Wx1vSc9vCdF7DuO6GdUD6Iei2E1cI2S4UtaNheXYGBgnccRc27L9wDbqURTYLAhMw_FtMGgCtjITVr9I5qB5xpeIxpJImGEYuo6dsDjCQpYI8QIkx7cE5_NkURmq24-ePOouy5V72NYsC6Y0TG1onyfXwILKfX934-WTFLpCTpXt-CqZ29zYihcg-t0MFpX_fwEF7JRi
linkProvider ISSN International Centre
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%EB%94%A5%EB%9F%AC%EB%8B%9D+%EA%B8%B0%EB%B0%98+%EC%B9%A8%EC%88%98+%EC%88%98%EC%9C%84+%EC%98%88%EC%B8%A1%3A+%EB%AF%B8%EA%B5%AD+%ED%85%8D%EC%82%AC%EC%8A%A4+%ED%8A%B8%EB%A6%AC%EB%8B%88%ED%8B%B0%EA%B0%95+%EC%82%AC%EB%A1%80%EC%97%B0%EA%B5%AC&rft.jtitle=Ch%C5%8Fngbo+Kwahakhoe+nonmunji&rft.au=%ED%8A%B8%EB%9E%80+%EA%B4%91+%EC%B9%B4%EC%9D%B4&rft.au=%EC%86%A1%EC%82%AC%EA%B4%91&rft.date=2017-06-01&rft.pub=%ED%95%9C%EA%B5%AD%EC%A0%95%EB%B3%B4%EA%B3%BC%ED%95%99%ED%9A%8C&rft.issn=2383-630X&rft.eissn=2383-6296&rft.spage=607&rft.epage=612&rft.externalDBID=n%2Fa&rft.externalDocID=oai_kci_go_kr_ARTI_1383698
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2383-630X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2383-630X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2383-630X&client=summon