Groundwater level prediction using hybrid artificial neural network with genetic algorithm

B. S. Supreetha, K. Prabhakar Nayak, K. Narayan Shenoy

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In recent years, the growth of the economy has led to the increasing exploitation of water resources and groundwater. Due to heavy abstraction of groundwater its importance increases, with the requirements at present as well as in future. Accurate estimates of groundwater level have a valuable effect in improving decision support systems of groundwater resources exploitation. This paper investigates the ability of a hybrid model of artificial neural network (ANN) and genetic algorithm (GA) in predicting groundwater levels in an observation well from Udupi district. The ground water level for a period of ten years and rainfall data for the same period is used to train the model. A standard feed forward network is utilized for performing the prediction task. A groundwater level forecasting model is developed using artificial neural network. The Genetic Algorithm is used to determine the optimized weights for ANN. This study indicates that the ANN-GA model can be used successfully to predict groundwater levels of observation well. In addition, a comparative study indicates that the ANN-GA hybrid model performs better than the traditional ANN back-propagation approach.

Original languageEnglish
Pages (from-to)2609-2615
Number of pages7
JournalInternational Journal of Earth Sciences and Engineering
Volume8
Issue number6
Publication statusPublished - 01-12-2015
Externally publishedYes

Fingerprint

genetic algorithm
artificial neural network
Groundwater
Genetic algorithms
Neural networks
groundwater
prediction
Groundwater resources
well
back propagation
decision support system
Water levels
groundwater resource
Decision support systems
Water resources
Backpropagation
train
Rain
comparative study
water level

All Science Journal Classification (ASJC) codes

  • Environmental Engineering
  • Civil and Structural Engineering
  • Building and Construction
  • Ocean Engineering
  • Earth and Planetary Sciences(all)

Cite this

Supreetha, B. S. ; Prabhakar Nayak, K. ; Narayan Shenoy, K. / Groundwater level prediction using hybrid artificial neural network with genetic algorithm. In: International Journal of Earth Sciences and Engineering. 2015 ; Vol. 8, No. 6. pp. 2609-2615.
@article{1554e792477940dfb01187a3e1ea75d9,
title = "Groundwater level prediction using hybrid artificial neural network with genetic algorithm",
abstract = "In recent years, the growth of the economy has led to the increasing exploitation of water resources and groundwater. Due to heavy abstraction of groundwater its importance increases, with the requirements at present as well as in future. Accurate estimates of groundwater level have a valuable effect in improving decision support systems of groundwater resources exploitation. This paper investigates the ability of a hybrid model of artificial neural network (ANN) and genetic algorithm (GA) in predicting groundwater levels in an observation well from Udupi district. The ground water level for a period of ten years and rainfall data for the same period is used to train the model. A standard feed forward network is utilized for performing the prediction task. A groundwater level forecasting model is developed using artificial neural network. The Genetic Algorithm is used to determine the optimized weights for ANN. This study indicates that the ANN-GA model can be used successfully to predict groundwater levels of observation well. In addition, a comparative study indicates that the ANN-GA hybrid model performs better than the traditional ANN back-propagation approach.",
author = "Supreetha, {B. S.} and {Prabhakar Nayak}, K. and {Narayan Shenoy}, K.",
year = "2015",
month = "12",
day = "1",
language = "English",
volume = "8",
pages = "2609--2615",
journal = "International Journal of Earth Sciences and Engineering",
issn = "0974-5904",
publisher = "Cafet-Innova Technical Society",
number = "6",

}

Groundwater level prediction using hybrid artificial neural network with genetic algorithm. / Supreetha, B. S.; Prabhakar Nayak, K.; Narayan Shenoy, K.

In: International Journal of Earth Sciences and Engineering, Vol. 8, No. 6, 01.12.2015, p. 2609-2615.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Groundwater level prediction using hybrid artificial neural network with genetic algorithm

AU - Supreetha, B. S.

AU - Prabhakar Nayak, K.

AU - Narayan Shenoy, K.

PY - 2015/12/1

Y1 - 2015/12/1

N2 - In recent years, the growth of the economy has led to the increasing exploitation of water resources and groundwater. Due to heavy abstraction of groundwater its importance increases, with the requirements at present as well as in future. Accurate estimates of groundwater level have a valuable effect in improving decision support systems of groundwater resources exploitation. This paper investigates the ability of a hybrid model of artificial neural network (ANN) and genetic algorithm (GA) in predicting groundwater levels in an observation well from Udupi district. The ground water level for a period of ten years and rainfall data for the same period is used to train the model. A standard feed forward network is utilized for performing the prediction task. A groundwater level forecasting model is developed using artificial neural network. The Genetic Algorithm is used to determine the optimized weights for ANN. This study indicates that the ANN-GA model can be used successfully to predict groundwater levels of observation well. In addition, a comparative study indicates that the ANN-GA hybrid model performs better than the traditional ANN back-propagation approach.

AB - In recent years, the growth of the economy has led to the increasing exploitation of water resources and groundwater. Due to heavy abstraction of groundwater its importance increases, with the requirements at present as well as in future. Accurate estimates of groundwater level have a valuable effect in improving decision support systems of groundwater resources exploitation. This paper investigates the ability of a hybrid model of artificial neural network (ANN) and genetic algorithm (GA) in predicting groundwater levels in an observation well from Udupi district. The ground water level for a period of ten years and rainfall data for the same period is used to train the model. A standard feed forward network is utilized for performing the prediction task. A groundwater level forecasting model is developed using artificial neural network. The Genetic Algorithm is used to determine the optimized weights for ANN. This study indicates that the ANN-GA model can be used successfully to predict groundwater levels of observation well. In addition, a comparative study indicates that the ANN-GA hybrid model performs better than the traditional ANN back-propagation approach.

UR - http://www.scopus.com/inward/record.url?scp=84971453997&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971453997&partnerID=8YFLogxK

M3 - Article

VL - 8

SP - 2609

EP - 2615

JO - International Journal of Earth Sciences and Engineering

JF - International Journal of Earth Sciences and Engineering

SN - 0974-5904

IS - 6

ER -