Simulation of spring flows from a karst aquifer with an artificial neural network

Caihong Hu, Yonghong Hao, Tian-Chyi J Yeh, Bo Pang, Zening Wu

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

In China, 9.5% of the landmass is karst terrain and of that 47,000 km2 is located in semiarid regions. In these regions the karst aquifers feed many large karst springs within basins of thousands of square kilometres. Spring discharges reflect the fluctuation of ground water level and variability of ground water storage in the basins. However, karst aquifers are highly heterogeneous and monitoring data are sparse in these regions. Therefore, for sustainable utilization and conservation of karst ground water it is necessary to simulate the spring flows to acquire better understanding of karst hydrological processes. The purpose of this study is to develop a parsimonious model that accurately simulates spring discharges using an artificial neural network (ANN) model. The karst spring aquifer was treated as a non-linear input/output system to simulate the response of karst spring flow to precipitation and applied the model to the Niangziguan Springs, located in the east of Shanxi Province, China and a representative of karst springs in a semiarid area. Moreover, the ANN model was compared with a previous time-lag linear model and it was found that the ANN model performed better.

Original languageEnglish (US)
Pages (from-to)596-604
Number of pages9
JournalHydrological Processes
Volume22
Issue number5
DOIs
StatePublished - Feb 29 2008

Fingerprint

artificial neural network
karst
aquifer
simulation
groundwater
water storage
semiarid region
basin
water level

Keywords

  • Artificial neural network
  • China
  • Ground water flow
  • Karst hydrology
  • Niangziguan Springs Basin

ASJC Scopus subject areas

  • Water Science and Technology

Cite this

Simulation of spring flows from a karst aquifer with an artificial neural network. / Hu, Caihong; Hao, Yonghong; Yeh, Tian-Chyi J; Pang, Bo; Wu, Zening.

In: Hydrological Processes, Vol. 22, No. 5, 29.02.2008, p. 596-604.

Research output: Contribution to journalArticle

Hu, Caihong ; Hao, Yonghong ; Yeh, Tian-Chyi J ; Pang, Bo ; Wu, Zening. / Simulation of spring flows from a karst aquifer with an artificial neural network. In: Hydrological Processes. 2008 ; Vol. 22, No. 5. pp. 596-604.
@article{baf7c70ebfdb483ea1a860aeea5e4119,
title = "Simulation of spring flows from a karst aquifer with an artificial neural network",
abstract = "In China, 9.5{\%} of the landmass is karst terrain and of that 47,000 km2 is located in semiarid regions. In these regions the karst aquifers feed many large karst springs within basins of thousands of square kilometres. Spring discharges reflect the fluctuation of ground water level and variability of ground water storage in the basins. However, karst aquifers are highly heterogeneous and monitoring data are sparse in these regions. Therefore, for sustainable utilization and conservation of karst ground water it is necessary to simulate the spring flows to acquire better understanding of karst hydrological processes. The purpose of this study is to develop a parsimonious model that accurately simulates spring discharges using an artificial neural network (ANN) model. The karst spring aquifer was treated as a non-linear input/output system to simulate the response of karst spring flow to precipitation and applied the model to the Niangziguan Springs, located in the east of Shanxi Province, China and a representative of karst springs in a semiarid area. Moreover, the ANN model was compared with a previous time-lag linear model and it was found that the ANN model performed better.",
keywords = "Artificial neural network, China, Ground water flow, Karst hydrology, Niangziguan Springs Basin",
author = "Caihong Hu and Yonghong Hao and Yeh, {Tian-Chyi J} and Bo Pang and Zening Wu",
year = "2008",
month = "2",
day = "29",
doi = "10.1002/hyp.6625",
language = "English (US)",
volume = "22",
pages = "596--604",
journal = "Hydrological Processes",
issn = "0885-6087",
publisher = "John Wiley and Sons Ltd",
number = "5",

}

TY - JOUR

T1 - Simulation of spring flows from a karst aquifer with an artificial neural network

AU - Hu, Caihong

AU - Hao, Yonghong

AU - Yeh, Tian-Chyi J

AU - Pang, Bo

AU - Wu, Zening

PY - 2008/2/29

Y1 - 2008/2/29

N2 - In China, 9.5% of the landmass is karst terrain and of that 47,000 km2 is located in semiarid regions. In these regions the karst aquifers feed many large karst springs within basins of thousands of square kilometres. Spring discharges reflect the fluctuation of ground water level and variability of ground water storage in the basins. However, karst aquifers are highly heterogeneous and monitoring data are sparse in these regions. Therefore, for sustainable utilization and conservation of karst ground water it is necessary to simulate the spring flows to acquire better understanding of karst hydrological processes. The purpose of this study is to develop a parsimonious model that accurately simulates spring discharges using an artificial neural network (ANN) model. The karst spring aquifer was treated as a non-linear input/output system to simulate the response of karst spring flow to precipitation and applied the model to the Niangziguan Springs, located in the east of Shanxi Province, China and a representative of karst springs in a semiarid area. Moreover, the ANN model was compared with a previous time-lag linear model and it was found that the ANN model performed better.

AB - In China, 9.5% of the landmass is karst terrain and of that 47,000 km2 is located in semiarid regions. In these regions the karst aquifers feed many large karst springs within basins of thousands of square kilometres. Spring discharges reflect the fluctuation of ground water level and variability of ground water storage in the basins. However, karst aquifers are highly heterogeneous and monitoring data are sparse in these regions. Therefore, for sustainable utilization and conservation of karst ground water it is necessary to simulate the spring flows to acquire better understanding of karst hydrological processes. The purpose of this study is to develop a parsimonious model that accurately simulates spring discharges using an artificial neural network (ANN) model. The karst spring aquifer was treated as a non-linear input/output system to simulate the response of karst spring flow to precipitation and applied the model to the Niangziguan Springs, located in the east of Shanxi Province, China and a representative of karst springs in a semiarid area. Moreover, the ANN model was compared with a previous time-lag linear model and it was found that the ANN model performed better.

KW - Artificial neural network

KW - China

KW - Ground water flow

KW - Karst hydrology

KW - Niangziguan Springs Basin

UR - http://www.scopus.com/inward/record.url?scp=40049099428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40049099428&partnerID=8YFLogxK

U2 - 10.1002/hyp.6625

DO - 10.1002/hyp.6625

M3 - Article

AN - SCOPUS:40049099428

VL - 22

SP - 596

EP - 604

JO - Hydrological Processes

JF - Hydrological Processes

SN - 0885-6087

IS - 5

ER -