Development of a distributed artificial neural network for hydrologic modeling

Rebecca Muenich, S. G. Bajwa, V. Vibhava

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

Abstract

Hydrological models are used to represent the rainfall-runoff and pollutant transport mechanisms within watersheds. Accurate representation of these dynamic and complex natural processes within a watershed is an important step in managing and protecting a watershed. Artificial neural network (ANN) models are often used in hydrologic modeling. Typical ANN models are trained to use lumped data. However, watershed characteristics used as inputs in hydrological modeling are spatially and often temporally dynamic. Therefore, a lumped model does not have the ability to represent changes in spatial dynamics of a watershed. Therefore, the purpose of this study was to develop and test a distributed ANN model for simulating the rainfall-runoff process in the L'Anguille River Watershed located in Eastern Arkansas. The watershed was divided into nine sub-basins to account for the spatial dynamics of flow within the watershed. Inputs for the model were rainfall, average temperature, antecedent flow and curve number. Output was runoff, collected from gage-stations at Colt and Palestine representing two of the sub-basins. Daily SCS curve numbers were developed and adjusted for crop planting and harvesting dates and crop rotation practices in each sub-basin. The model had nine layers with one neuron each to represent the nine sub-basins. The layers were connected so that if one sub-basin spatially flowed into another, its output would be an input for the downstream sub-basin. The model performed well, showing R 2 values of 0.93 and 0.98 and Nash-Sutcliffe Efficiency values of 0.92 and 0.97 for the validation and test datasets.

Original languageEnglish (US)
Title of host publicationASABE - 7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009
Pages164-169
Number of pages6
StatePublished - Dec 31 2009
Externally publishedYes
Event7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009 - Reno, NV, United States
Duration: Jun 22 2009Jun 24 2009

Other

Other7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009
CountryUnited States
CityReno, NV
Period6/22/096/24/09

Fingerprint

neural networks
Watersheds
Neural networks
basins
Runoff
Rain
runoff
rain
Crops
colts
planting date
harvest date
hydrologic models
gauges
Catchments
Neurons
Gages
neurons
Rivers
pollutants

Keywords

  • Artificial neural networks
  • Hydrologic modeling
  • L'Anguille River Watershed

ASJC Scopus subject areas

  • Agronomy and Crop Science
  • Computer Science Applications
  • Hardware and Architecture

Cite this

Muenich, R., Bajwa, S. G., & Vibhava, V. (2009). Development of a distributed artificial neural network for hydrologic modeling. In ASABE - 7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009 (pp. 164-169)

Development of a distributed artificial neural network for hydrologic modeling. / Muenich, Rebecca; Bajwa, S. G.; Vibhava, V.

ASABE - 7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009. 2009. p. 164-169.

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

Muenich, R, Bajwa, SG & Vibhava, V 2009, Development of a distributed artificial neural network for hydrologic modeling. in ASABE - 7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009. pp. 164-169, 7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009, Reno, NV, United States, 6/22/09.
Muenich R, Bajwa SG, Vibhava V. Development of a distributed artificial neural network for hydrologic modeling. In ASABE - 7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009. 2009. p. 164-169
Muenich, Rebecca ; Bajwa, S. G. ; Vibhava, V. / Development of a distributed artificial neural network for hydrologic modeling. ASABE - 7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009. 2009. pp. 164-169
@inproceedings{e2c34a73c8ec46ff81f46f8221f8b8ad,
title = "Development of a distributed artificial neural network for hydrologic modeling",
abstract = "Hydrological models are used to represent the rainfall-runoff and pollutant transport mechanisms within watersheds. Accurate representation of these dynamic and complex natural processes within a watershed is an important step in managing and protecting a watershed. Artificial neural network (ANN) models are often used in hydrologic modeling. Typical ANN models are trained to use lumped data. However, watershed characteristics used as inputs in hydrological modeling are spatially and often temporally dynamic. Therefore, a lumped model does not have the ability to represent changes in spatial dynamics of a watershed. Therefore, the purpose of this study was to develop and test a distributed ANN model for simulating the rainfall-runoff process in the L'Anguille River Watershed located in Eastern Arkansas. The watershed was divided into nine sub-basins to account for the spatial dynamics of flow within the watershed. Inputs for the model were rainfall, average temperature, antecedent flow and curve number. Output was runoff, collected from gage-stations at Colt and Palestine representing two of the sub-basins. Daily SCS curve numbers were developed and adjusted for crop planting and harvesting dates and crop rotation practices in each sub-basin. The model had nine layers with one neuron each to represent the nine sub-basins. The layers were connected so that if one sub-basin spatially flowed into another, its output would be an input for the downstream sub-basin. The model performed well, showing R 2 values of 0.93 and 0.98 and Nash-Sutcliffe Efficiency values of 0.92 and 0.97 for the validation and test datasets.",
keywords = "Artificial neural networks, Hydrologic modeling, L'Anguille River Watershed",
author = "Rebecca Muenich and Bajwa, {S. G.} and V. Vibhava",
year = "2009",
month = "12",
day = "31",
language = "English (US)",
isbn = "9781615673902",
pages = "164--169",
booktitle = "ASABE - 7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009",

}

TY - GEN

T1 - Development of a distributed artificial neural network for hydrologic modeling

AU - Muenich, Rebecca

AU - Bajwa, S. G.

AU - Vibhava, V.

PY - 2009/12/31

Y1 - 2009/12/31

N2 - Hydrological models are used to represent the rainfall-runoff and pollutant transport mechanisms within watersheds. Accurate representation of these dynamic and complex natural processes within a watershed is an important step in managing and protecting a watershed. Artificial neural network (ANN) models are often used in hydrologic modeling. Typical ANN models are trained to use lumped data. However, watershed characteristics used as inputs in hydrological modeling are spatially and often temporally dynamic. Therefore, a lumped model does not have the ability to represent changes in spatial dynamics of a watershed. Therefore, the purpose of this study was to develop and test a distributed ANN model for simulating the rainfall-runoff process in the L'Anguille River Watershed located in Eastern Arkansas. The watershed was divided into nine sub-basins to account for the spatial dynamics of flow within the watershed. Inputs for the model were rainfall, average temperature, antecedent flow and curve number. Output was runoff, collected from gage-stations at Colt and Palestine representing two of the sub-basins. Daily SCS curve numbers were developed and adjusted for crop planting and harvesting dates and crop rotation practices in each sub-basin. The model had nine layers with one neuron each to represent the nine sub-basins. The layers were connected so that if one sub-basin spatially flowed into another, its output would be an input for the downstream sub-basin. The model performed well, showing R 2 values of 0.93 and 0.98 and Nash-Sutcliffe Efficiency values of 0.92 and 0.97 for the validation and test datasets.

AB - Hydrological models are used to represent the rainfall-runoff and pollutant transport mechanisms within watersheds. Accurate representation of these dynamic and complex natural processes within a watershed is an important step in managing and protecting a watershed. Artificial neural network (ANN) models are often used in hydrologic modeling. Typical ANN models are trained to use lumped data. However, watershed characteristics used as inputs in hydrological modeling are spatially and often temporally dynamic. Therefore, a lumped model does not have the ability to represent changes in spatial dynamics of a watershed. Therefore, the purpose of this study was to develop and test a distributed ANN model for simulating the rainfall-runoff process in the L'Anguille River Watershed located in Eastern Arkansas. The watershed was divided into nine sub-basins to account for the spatial dynamics of flow within the watershed. Inputs for the model were rainfall, average temperature, antecedent flow and curve number. Output was runoff, collected from gage-stations at Colt and Palestine representing two of the sub-basins. Daily SCS curve numbers were developed and adjusted for crop planting and harvesting dates and crop rotation practices in each sub-basin. The model had nine layers with one neuron each to represent the nine sub-basins. The layers were connected so that if one sub-basin spatially flowed into another, its output would be an input for the downstream sub-basin. The model performed well, showing R 2 values of 0.93 and 0.98 and Nash-Sutcliffe Efficiency values of 0.92 and 0.97 for the validation and test datasets.

KW - Artificial neural networks

KW - Hydrologic modeling

KW - L'Anguille River Watershed

UR - http://www.scopus.com/inward/record.url?scp=72749097910&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72749097910&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:72749097910

SN - 9781615673902

SP - 164

EP - 169

BT - ASABE - 7th World Congress on Computers in Agriculture and Natural Resources 2009, WCCA 2009

ER -