Prediction of groundwater flow in shallow aquifers using artificial neural networks in the northern basins of Algeria

N Guezgouz,D Boutoutaou,A Hani

doi:10.2166/wcc.2020.067

Abstract

Abstract Prediction of groundwater flow fluctuations is considered an important step in understanding groundwater systems at this scale and facilitating sustainable groundwater management. The objective of this study is to determine the factors that influence and control groundwater flow fluctuations in a specific geomorphologic situation, by developing a forecasting model and examining its potential for predicting groundwater flow using limited data. Models for prediction of groundwater flow are developed based on artificial neural networks (ANNs). Neural networks with different numbers of hidden layer neurons were developed using climatic and geomorphological characteristics as input variables, giving predicted groundwater flow as the output. To evaluate enhanced performance models, several regression statistical parameters are compared. As an example, relative mean square error in groundwater flow prediction by ANN and correlation coefficient are 0.015 and 97%, respectively. The results of the study clearly show that ANNs can be used to predict groundwater flow in shallow aquifers of northern Algeria with reasonable accuracy even in the case of limited data.

Highlights

Integrated water resources management is a systematic process for sustainable development, allocation and monitoring of water resources viewed as both a geomorphological influence and a climatic variation
The artificial neural networks (ANNs) models have been successfully applied to hydrological processes, such as rainfall–runoff modeling (Minns & Hall ) and rainfall forecasting (Lallahem & Mania ) and in water resources context, the ANN has been used for water quality parameters (Maier & Dandy ), forecasting of water demand (Liu et al ), stream flow forecasting (Change et al ), prediction of rainfall– runoff relationship (Change et al ; Riad et al ), coastal aquifer management (Albaradeyi et al ), stream flow modeling (Coulibaly et al ) and reservoir operation problems (Hornik et al )
This study aims to establish a modeling relationship between groundwater flow and response variables in shallow aquifers in the north of Algeria, characterizing their priorities, to better manage water resources, especially under climate change and the first rains delay, causing ugly impacts on agricultural activity which uses the rainfall for irrigation

Summary

Introduction

Integrated water resources management is a systematic process for sustainable development, allocation and monitoring of water resources viewed as both a geomorphological influence and a climatic variation. This conceptual model interprets the two systems through three components including the watershed nature, the stream characteristics and the rainfall, influencing groundwater flows. The artificial neural networks (ANNs) models have been successfully applied to hydrological processes, such as rainfall–runoff modeling (Minns & Hall ) and rainfall forecasting (Lallahem & Mania ) and in water resources context, the ANN has been used for water quality parameters (Maier & Dandy ), forecasting of water demand (Liu et al ), stream flow forecasting (Change et al ), prediction of rainfall– runoff relationship (Change et al ; Riad et al ), coastal aquifer management (Albaradeyi et al ), stream flow modeling (Coulibaly et al ) and reservoir operation problems (Hornik et al ). Hornik et al ( ) showed how ANN could be applied to different problems in civil engineering, while Maier & Dandy ( ) reviewed several papers dealing with the use of neural network models for the prediction and forecasting of water resources variables.

Objectives

Methods

Results

Conclusion