Using of pH as a tool to predict salinity of groundwater for irrigation purpose using artificial neural network

Mahmoud Nasr, Hoda Farouk Zahran

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Monitoring of groundwater quality is one of the important tools to provide adequate information about water management. In the present study, artificial neural network (ANN) with a feed-forward back-propagation was designed to predict groundwater salinity, expressed by total dissolved solids (TDS), using pH as an input parameter. Groundwater samples were collected from a 36. m depth well located in the experimental farm of the City of Scientific Researches and Technological Applications (SRTA City), New Borg El-Arab City, Alexandria, Egypt. The network structure was 1-5-3-1 and used the default Levenberg-Marquardt algorithm for training. It was observed that, the best validation performance, based on the mean square error, was 14819 at epoch 0, and no major problems or over-fitting occurred with the training step. The simulated output tracked the measured data with a correlation coefficient (R-value) of 0.64, 0.67 and 0.90 for training, validation and test, respectively. In this case, the network response was acceptable, and simulation could be used for entering new inputs.

Original languageEnglish
Pages (from-to)111-115
Number of pages5
JournalEgyptian Journal of Aquatic Research
Volume40
Issue number2
DOIs
Publication statusPublished - 2014
Externally publishedYes

Fingerprint

artificial neural network
neural networks
groundwater
irrigation
salinity
Arabs
total dissolved solids
back propagation
demonstration farms
Egypt
water management
water quality
farm
monitoring
simulation
city
testing
sampling
parameter
test

Keywords

  • Artificial neural network
  • Groundwater
  • Salinity

ASJC Scopus subject areas

  • Aquatic Science
  • Water Science and Technology
  • Oceanography
  • Ecology, Evolution, Behavior and Systematics

Cite this

Using of pH as a tool to predict salinity of groundwater for irrigation purpose using artificial neural network. / Nasr, Mahmoud; Zahran, Hoda Farouk.

In: Egyptian Journal of Aquatic Research, Vol. 40, No. 2, 2014, p. 111-115.

Research output: Contribution to journalArticle

@article{16eb328b3fc34a7ab2fd3e9fdfc88ac7,
title = "Using of pH as a tool to predict salinity of groundwater for irrigation purpose using artificial neural network",
abstract = "Monitoring of groundwater quality is one of the important tools to provide adequate information about water management. In the present study, artificial neural network (ANN) with a feed-forward back-propagation was designed to predict groundwater salinity, expressed by total dissolved solids (TDS), using pH as an input parameter. Groundwater samples were collected from a 36. m depth well located in the experimental farm of the City of Scientific Researches and Technological Applications (SRTA City), New Borg El-Arab City, Alexandria, Egypt. The network structure was 1-5-3-1 and used the default Levenberg-Marquardt algorithm for training. It was observed that, the best validation performance, based on the mean square error, was 14819 at epoch 0, and no major problems or over-fitting occurred with the training step. The simulated output tracked the measured data with a correlation coefficient (R-value) of 0.64, 0.67 and 0.90 for training, validation and test, respectively. In this case, the network response was acceptable, and simulation could be used for entering new inputs.",
keywords = "Artificial neural network, Groundwater, Salinity",
author = "Mahmoud Nasr and Zahran, {Hoda Farouk}",
year = "2014",
doi = "10.1016/j.ejar.2014.06.005",
language = "English",
volume = "40",
pages = "111--115",
journal = "Egyptian Journal of Aquatic Research",
issn = "1687-4285",
publisher = "National Institute of Oceanography and Fisheries",
number = "2",

}

TY - JOUR

T1 - Using of pH as a tool to predict salinity of groundwater for irrigation purpose using artificial neural network

AU - Nasr, Mahmoud

AU - Zahran, Hoda Farouk

PY - 2014

Y1 - 2014

N2 - Monitoring of groundwater quality is one of the important tools to provide adequate information about water management. In the present study, artificial neural network (ANN) with a feed-forward back-propagation was designed to predict groundwater salinity, expressed by total dissolved solids (TDS), using pH as an input parameter. Groundwater samples were collected from a 36. m depth well located in the experimental farm of the City of Scientific Researches and Technological Applications (SRTA City), New Borg El-Arab City, Alexandria, Egypt. The network structure was 1-5-3-1 and used the default Levenberg-Marquardt algorithm for training. It was observed that, the best validation performance, based on the mean square error, was 14819 at epoch 0, and no major problems or over-fitting occurred with the training step. The simulated output tracked the measured data with a correlation coefficient (R-value) of 0.64, 0.67 and 0.90 for training, validation and test, respectively. In this case, the network response was acceptable, and simulation could be used for entering new inputs.

AB - Monitoring of groundwater quality is one of the important tools to provide adequate information about water management. In the present study, artificial neural network (ANN) with a feed-forward back-propagation was designed to predict groundwater salinity, expressed by total dissolved solids (TDS), using pH as an input parameter. Groundwater samples were collected from a 36. m depth well located in the experimental farm of the City of Scientific Researches and Technological Applications (SRTA City), New Borg El-Arab City, Alexandria, Egypt. The network structure was 1-5-3-1 and used the default Levenberg-Marquardt algorithm for training. It was observed that, the best validation performance, based on the mean square error, was 14819 at epoch 0, and no major problems or over-fitting occurred with the training step. The simulated output tracked the measured data with a correlation coefficient (R-value) of 0.64, 0.67 and 0.90 for training, validation and test, respectively. In this case, the network response was acceptable, and simulation could be used for entering new inputs.

KW - Artificial neural network

KW - Groundwater

KW - Salinity

UR - http://www.scopus.com/inward/record.url?scp=84927563128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927563128&partnerID=8YFLogxK

U2 - 10.1016/j.ejar.2014.06.005

DO - 10.1016/j.ejar.2014.06.005

M3 - Article

AN - SCOPUS:84927563128

VL - 40

SP - 111

EP - 115

JO - Egyptian Journal of Aquatic Research

JF - Egyptian Journal of Aquatic Research

SN - 1687-4285

IS - 2

ER -