Application of artificial neural networks to complex groundwater management problems

Emery Coppola, Mary M Poulton, Emmanuel Charles, John Dustman, Ferenc Szidarovszky

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

As water quantity and quality problems become increasingly severe, accurate prediction and effective management of scarcer water resources will become critical. In this paper, the successful application of artificial neural network (ANN) technology is described for three types of groundwater prediction and management problems. In the first example, an ANN was trained with simulation data from a physically based numerical model to predict head (groundwater elevation) at locations of interest under variable pumping and climate conditions. The ANN achieved a high degree of predictive accuracy, and its derived state-transition equations were embedded into a multiobjective optimization formulation and solved to generate a tradeoff curve depicting water supply in relation to contamination risk. In the second and third examples, ANNs were developed with real-world hydrologic and climate data for different hydrogeologic environments. For the second problem, an ANN was developed using data collected for a 5-year, 8-month period to predict heads in a multilayered surficial and limestone aquifer system under variable pumping, state, and climate conditions. Using weekly stress periods, the ANN substantially outperformed a well-calibrated numerical flow model for the 71-day validation period, and provided insights into the effects of climate and pumping on water levels. For the third problem, an ANN was developed with data collected automatically over a 6-week period to predict hourly heads in 11 high-capacity public supply wells tapping a semiconfined bedrock aquifer and subject to large well-interference effects. Using hourly stress periods, the ANN accurately predicted heads for 24-hour periods in all public supply wells. These test cases demonstrate that the ANN technology can solve a variety of complex groundwater management problems and overcome many of the problems and limitations associated with traditional physically based flow models.

Original languageEnglish (US)
Pages (from-to)303-320
Number of pages18
JournalNatural Resources Research
Volume12
Issue number4
DOIs
StatePublished - 2003

Fingerprint

artificial neural network
groundwater
pumping
climate conditions
aquifer
well
climate
prediction
bedrock
water level
water supply
water resource
limestone
simulation

Keywords

  • Groundwater
  • Groundwater management
  • Groundwater optimization
  • Numerical models

ASJC Scopus subject areas

  • Environmental Science(all)

Cite this

Application of artificial neural networks to complex groundwater management problems. / Coppola, Emery; Poulton, Mary M; Charles, Emmanuel; Dustman, John; Szidarovszky, Ferenc.

In: Natural Resources Research, Vol. 12, No. 4, 2003, p. 303-320.

Research output: Contribution to journalArticle

Coppola, Emery ; Poulton, Mary M ; Charles, Emmanuel ; Dustman, John ; Szidarovszky, Ferenc. / Application of artificial neural networks to complex groundwater management problems. In: Natural Resources Research. 2003 ; Vol. 12, No. 4. pp. 303-320.
@article{0c61996843804bcc99c8224520e6bdac,
title = "Application of artificial neural networks to complex groundwater management problems",
abstract = "As water quantity and quality problems become increasingly severe, accurate prediction and effective management of scarcer water resources will become critical. In this paper, the successful application of artificial neural network (ANN) technology is described for three types of groundwater prediction and management problems. In the first example, an ANN was trained with simulation data from a physically based numerical model to predict head (groundwater elevation) at locations of interest under variable pumping and climate conditions. The ANN achieved a high degree of predictive accuracy, and its derived state-transition equations were embedded into a multiobjective optimization formulation and solved to generate a tradeoff curve depicting water supply in relation to contamination risk. In the second and third examples, ANNs were developed with real-world hydrologic and climate data for different hydrogeologic environments. For the second problem, an ANN was developed using data collected for a 5-year, 8-month period to predict heads in a multilayered surficial and limestone aquifer system under variable pumping, state, and climate conditions. Using weekly stress periods, the ANN substantially outperformed a well-calibrated numerical flow model for the 71-day validation period, and provided insights into the effects of climate and pumping on water levels. For the third problem, an ANN was developed with data collected automatically over a 6-week period to predict hourly heads in 11 high-capacity public supply wells tapping a semiconfined bedrock aquifer and subject to large well-interference effects. Using hourly stress periods, the ANN accurately predicted heads for 24-hour periods in all public supply wells. These test cases demonstrate that the ANN technology can solve a variety of complex groundwater management problems and overcome many of the problems and limitations associated with traditional physically based flow models.",
keywords = "Groundwater, Groundwater management, Groundwater optimization, Numerical models",
author = "Emery Coppola and Poulton, {Mary M} and Emmanuel Charles and John Dustman and Ferenc Szidarovszky",
year = "2003",
doi = "10.1023/B:NARR.0000007808.11860.7e",
language = "English (US)",
volume = "12",
pages = "303--320",
journal = "Natural Resources Research",
issn = "1520-7439",
publisher = "Springer Netherlands",
number = "4",

}

TY - JOUR

T1 - Application of artificial neural networks to complex groundwater management problems

AU - Coppola, Emery

AU - Poulton, Mary M

AU - Charles, Emmanuel

AU - Dustman, John

AU - Szidarovszky, Ferenc

PY - 2003

Y1 - 2003

N2 - As water quantity and quality problems become increasingly severe, accurate prediction and effective management of scarcer water resources will become critical. In this paper, the successful application of artificial neural network (ANN) technology is described for three types of groundwater prediction and management problems. In the first example, an ANN was trained with simulation data from a physically based numerical model to predict head (groundwater elevation) at locations of interest under variable pumping and climate conditions. The ANN achieved a high degree of predictive accuracy, and its derived state-transition equations were embedded into a multiobjective optimization formulation and solved to generate a tradeoff curve depicting water supply in relation to contamination risk. In the second and third examples, ANNs were developed with real-world hydrologic and climate data for different hydrogeologic environments. For the second problem, an ANN was developed using data collected for a 5-year, 8-month period to predict heads in a multilayered surficial and limestone aquifer system under variable pumping, state, and climate conditions. Using weekly stress periods, the ANN substantially outperformed a well-calibrated numerical flow model for the 71-day validation period, and provided insights into the effects of climate and pumping on water levels. For the third problem, an ANN was developed with data collected automatically over a 6-week period to predict hourly heads in 11 high-capacity public supply wells tapping a semiconfined bedrock aquifer and subject to large well-interference effects. Using hourly stress periods, the ANN accurately predicted heads for 24-hour periods in all public supply wells. These test cases demonstrate that the ANN technology can solve a variety of complex groundwater management problems and overcome many of the problems and limitations associated with traditional physically based flow models.

AB - As water quantity and quality problems become increasingly severe, accurate prediction and effective management of scarcer water resources will become critical. In this paper, the successful application of artificial neural network (ANN) technology is described for three types of groundwater prediction and management problems. In the first example, an ANN was trained with simulation data from a physically based numerical model to predict head (groundwater elevation) at locations of interest under variable pumping and climate conditions. The ANN achieved a high degree of predictive accuracy, and its derived state-transition equations were embedded into a multiobjective optimization formulation and solved to generate a tradeoff curve depicting water supply in relation to contamination risk. In the second and third examples, ANNs were developed with real-world hydrologic and climate data for different hydrogeologic environments. For the second problem, an ANN was developed using data collected for a 5-year, 8-month period to predict heads in a multilayered surficial and limestone aquifer system under variable pumping, state, and climate conditions. Using weekly stress periods, the ANN substantially outperformed a well-calibrated numerical flow model for the 71-day validation period, and provided insights into the effects of climate and pumping on water levels. For the third problem, an ANN was developed with data collected automatically over a 6-week period to predict hourly heads in 11 high-capacity public supply wells tapping a semiconfined bedrock aquifer and subject to large well-interference effects. Using hourly stress periods, the ANN accurately predicted heads for 24-hour periods in all public supply wells. These test cases demonstrate that the ANN technology can solve a variety of complex groundwater management problems and overcome many of the problems and limitations associated with traditional physically based flow models.

KW - Groundwater

KW - Groundwater management

KW - Groundwater optimization

KW - Numerical models

UR - http://www.scopus.com/inward/record.url?scp=14644401332&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=14644401332&partnerID=8YFLogxK

U2 - 10.1023/B:NARR.0000007808.11860.7e

DO - 10.1023/B:NARR.0000007808.11860.7e

M3 - Article

VL - 12

SP - 303

EP - 320

JO - Natural Resources Research

JF - Natural Resources Research

SN - 1520-7439

IS - 4

ER -