Streamflow forecasting using artificial neural networks

Kuo lin Hsu, Hoshin Vijai Gupta, Soroosh Sorooshian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

A variety of ANN models are being tested for their performance in forecasting daily streamflow from rainfall measurements. In this study, a new ANN structure, called SOLO (Self Organizing feature map with Linear Output) is compared to the conventional time-delay neural network (TDNN) and recurrent neural network (RNN) structures. Results for the Leaf River watershed in Mississippi indicate that the SOLO structure provides equivalent or superior performance across the full range of flow levels (base flow recessions to peaks). Further, the SOLO structure is considerably less costly (in terms of effort and computational requirements) to identify and train.

Original languageEnglish (US)
Title of host publicationInternational Water Resources Engineering Conference - Proceedings
PublisherASCE
Pages967-972
Number of pages6
Volume2
StatePublished - 1998
EventProceedings of the 1998 International Water Resources Engineering Conference. Part 2 (of 2) - Memphis, TN, USA
Duration: Aug 3 1998Aug 7 1998

Other

OtherProceedings of the 1998 International Water Resources Engineering Conference. Part 2 (of 2)
CityMemphis, TN, USA
Period8/3/988/7/98

Fingerprint

baseflow
artificial neural network
train
streamflow
watershed
rainfall
river

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)
  • Environmental Science(all)

Cite this

Hsu, K. L., Gupta, H. V., & Sorooshian, S. (1998). Streamflow forecasting using artificial neural networks. In International Water Resources Engineering Conference - Proceedings (Vol. 2, pp. 967-972). ASCE.

Streamflow forecasting using artificial neural networks. / Hsu, Kuo lin; Gupta, Hoshin Vijai; Sorooshian, Soroosh.

International Water Resources Engineering Conference - Proceedings. Vol. 2 ASCE, 1998. p. 967-972.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hsu, KL, Gupta, HV & Sorooshian, S 1998, Streamflow forecasting using artificial neural networks. in International Water Resources Engineering Conference - Proceedings. vol. 2, ASCE, pp. 967-972, Proceedings of the 1998 International Water Resources Engineering Conference. Part 2 (of 2), Memphis, TN, USA, 8/3/98.
Hsu KL, Gupta HV, Sorooshian S. Streamflow forecasting using artificial neural networks. In International Water Resources Engineering Conference - Proceedings. Vol. 2. ASCE. 1998. p. 967-972
Hsu, Kuo lin ; Gupta, Hoshin Vijai ; Sorooshian, Soroosh. / Streamflow forecasting using artificial neural networks. International Water Resources Engineering Conference - Proceedings. Vol. 2 ASCE, 1998. pp. 967-972
@inproceedings{84ada3d29e3c4575b9e52f419dc6792f,
title = "Streamflow forecasting using artificial neural networks",
abstract = "A variety of ANN models are being tested for their performance in forecasting daily streamflow from rainfall measurements. In this study, a new ANN structure, called SOLO (Self Organizing feature map with Linear Output) is compared to the conventional time-delay neural network (TDNN) and recurrent neural network (RNN) structures. Results for the Leaf River watershed in Mississippi indicate that the SOLO structure provides equivalent or superior performance across the full range of flow levels (base flow recessions to peaks). Further, the SOLO structure is considerably less costly (in terms of effort and computational requirements) to identify and train.",
author = "Hsu, {Kuo lin} and Gupta, {Hoshin Vijai} and Soroosh Sorooshian",
year = "1998",
language = "English (US)",
volume = "2",
pages = "967--972",
booktitle = "International Water Resources Engineering Conference - Proceedings",
publisher = "ASCE",

}

TY - GEN

T1 - Streamflow forecasting using artificial neural networks

AU - Hsu, Kuo lin

AU - Gupta, Hoshin Vijai

AU - Sorooshian, Soroosh

PY - 1998

Y1 - 1998

N2 - A variety of ANN models are being tested for their performance in forecasting daily streamflow from rainfall measurements. In this study, a new ANN structure, called SOLO (Self Organizing feature map with Linear Output) is compared to the conventional time-delay neural network (TDNN) and recurrent neural network (RNN) structures. Results for the Leaf River watershed in Mississippi indicate that the SOLO structure provides equivalent or superior performance across the full range of flow levels (base flow recessions to peaks). Further, the SOLO structure is considerably less costly (in terms of effort and computational requirements) to identify and train.

AB - A variety of ANN models are being tested for their performance in forecasting daily streamflow from rainfall measurements. In this study, a new ANN structure, called SOLO (Self Organizing feature map with Linear Output) is compared to the conventional time-delay neural network (TDNN) and recurrent neural network (RNN) structures. Results for the Leaf River watershed in Mississippi indicate that the SOLO structure provides equivalent or superior performance across the full range of flow levels (base flow recessions to peaks). Further, the SOLO structure is considerably less costly (in terms of effort and computational requirements) to identify and train.

UR - http://www.scopus.com/inward/record.url?scp=0031642736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031642736&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 967

EP - 972

BT - International Water Resources Engineering Conference - Proceedings

PB - ASCE

ER -