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

Nasr, Mahmoud; Zahran, Hoda Farouk

doi:10.1016/j.ejar.2014.06.005

Cited by 51 publications

(18 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent development has targeted to predict groundwater salinity from different parameters using neural network techniques (Maier and Dandy 1996;Nasr and Zahran 2014). However, most previous studies were focused on salinity prediction from a unique type of neural network models.…”

Section: Introductionmentioning

confidence: 99%

“…), bicarbonate (HCO 3 -), and sulfate (SO 4 2-). Moreover, toxic ions such as boron (B), bromide (Br -) and iron (Fe) could be accumulated at higher levels (Nasr and Zahran 2014).…”

Section: Introductionmentioning

confidence: 99%

“…ANNs have been used to simulate the effect of climate change on discharge and the export of dissolved organic carbon and nitrogen from river basins (Clair and Ehrman 1996), predict salinity of groundwater and rivers (Maier and Dandy 1996;Huang and Foo 2002;Nasr and Zahran 2014;Ravansalar and Rajaee 2015), simulate and forecast residual chlorine concentrations within urban water systems (Rodriguez and Serodes 1998), prediction of arsenic, sulfate and nitrate concentrations in groundwater (Yesilnacar et al 2008;Yesilnacar et al 2012;Chang et al 2010), spatial distribution of groundwater quality (Khashei-Siuki and Sarbazi 2013) and determine the leachate amount from municipal solid waste landfill (Karaca and Ozkaya 2006).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combining the advantages of neural networks using the concept of committee machine in the groundwater salinity prediction

Barzegar

Moghaddam

2016

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

Salinity is one of the main factors in groundwater quality monitoring. The main objectives of this study are to investigate and compare the accuracy of three different neural computing techniques, multi-layer perceptron neural network (MLP), radial basis function neural network (RBFNN), and generalized regression neural network (GRNN), in prediction of groundwater salinity of the Tabriz plain confined aquifer, expressed by electrical conductivity [EC (lS/cm)], and to employ an integrated method to combine the advantages of neural network models utilizing the concept of committee machine. To develop the models, 93 data records of groundwater samples were collected from East Azarbaijan regional water company. The data set including Ca 2? , Mg 2? , Na ? , SO 4 2-and Cl -concentrations as the inputs and salinity [EC (lS/ cm)] as an output were divided into two subsets; training and testing based on cross validation approach. After training and testing of the models, the performance of the models were evaluated using root mean square errors (RMSE), determination coefficient (R 2 ) and mean absolute error (MAE). The performance criteria of the constructed neural network models showed that RBFNN model has the best performance in predicting salinity. The committee neural network (CNN) combined the results of salinity predicted from MLP, RBFNN and GRNN, each of them has a weight factor showing its contribution in overall prediction. The optimal weights were derived by a genetic algorithm (GA). The results of salinity prediction derived from CNN showed that the CNN performs better than any one of the individual ANNs acting alone for predicting groundwater salinity.

show abstract

Section: Introductionmentioning

confidence: 99%

“…), bicarbonate (HCO 3 -), and sulfate (SO 4 2-). Moreover, toxic ions such as boron (B), bromide (Br -) and iron (Fe) could be accumulated at higher levels (Nasr and Zahran 2014).…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining the advantages of neural networks using the concept of committee machine in the groundwater salinity prediction

Barzegar

Moghaddam

2016

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

show abstract

“…Artificial neural networks (ANNs) have been applied in hydrological modeling and prediction of nonlinear and randomized time series due to their flexibility (Diaconescu, 2008;Nasr and Zahran, 2014). Some of their merits as articulated by Mishra and Desai (2006) are; 1) The ease to recognize the relation between the input and output variables without explicit physical consideration, 2)The fact that the chaotic time series are easy to train regardless of any measurement errors, 3)The fact that they are easily adapted to solutions over time to compensate for varying conditions and 4)The fact that they possess other memory characteristics and once trained are easy to use.…”

Section: Artificial Neural Network Modelmentioning

confidence: 99%

Modeling Dryness Severity Using Artificial Neural Network at the Okavango Delta, Botswana

2016

Global NEST Journal

View full text Add to dashboard Cite

<div> <p>Water balance studies in the Okavango Delta indicate that more than 90% of inflow into the Delta is lost through evaporation. This coupled with high climatic variability threatens the ecohydrology of the Delta. Trends indicate decreasing rainfall amounts and increasing temperature at the area of the Delta. The main aim of this study was therefore to investigate long term trends and variability in rain onset, cessation, number of rainy days and their impact on the dryness index at the Delta. The impact of the above variables is expressed through the standardized precipitation and evaporation index (SPEI) quantified by aggregating the climate water balance and fitting monthly series to a generalized logistic distribution using L-Moments. The SPEI, determined at windows of different time scales of one, three and twelve months, provided an extensive evaluation of dryness severity and its impact on this sensitive ecosystem. Rain onset and cessation dates were generated from cumulative pentad rainfall–evapotranspiration relationships. Analysis of climatic data showed mean rain onset occurring in November and ceding in March with average of 44 rainy days between 1970/71 and 2013/14. The results revealed a decrease in the number of rainy days at a rate of 0.16 days/yr and of the duration of the rainy season at 0.25 days/yr with high variability. Annual rainfall was found to decrease at the rate of 1.60 mm/yr with 6.8% probability of failure in rainfall onset. Analysis further revealed that both extreme dryness and wetness are rare phenomena with probabilities of less than 1% and near normal conditions for 67% of the time for all SPEI time scales. Although gradual increase in dryness in the Delta is attributed to high climatic variability, simulations undertaken using Artificial Neural Networks did not predict any major changes in the next five years. However, vulnerability to severe droughts is not completely ruled out because of the high variability in rainfall and of the location of the Delta in a semi-arid zone. </p> </div> <p> </p>

show abstract

“…Li et al [10] investigated the electrochemical degradation of BPB dye with BDD anode under a range of major operating parameters. Nasr et al [11] predicted the groundwater salinity (i.e., in terms of TDS) based on alkalinity (i.e., expressed by pH) and proposed the ANN structure for that. Lakshminarayanan et al [12] compared RSM and ANN method for predicting the tensile strength of friction-stir-welded AA7039 aluminum alloy joints.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Artificial Neural Network and Response Surface Methodology for Optimization of Friction Welding of Incoloy 800 H

Anand

Shrivastava

Tamilmannan

et al. 2015

Acta Metall. Sin. (Engl. Lett.)

View full text Add to dashboard Cite

This article deals with the optimization of process parameters for friction welding of Incoloy 800 H rod and compares the results obtained by response surface methodology (RSM) and artificial neural network (ANN). The experiments were carried out on the basis of a five-level, four-variable central composite design. The output parameters were the tensile strength and burn-off length (BOL). They were considered as a function of four independent input variables, namely heating pressure (HP), heating time, upsetting pressure (UP), and upsetting time. The RSM results showed that the quadratic polynomial model depicted the interconnection between individual element and response. For optimizing the process parameters, ANN analysis was used, and the optimal configuration of the ANN model was found to be 4-9-2. For modeling aspect, a requisite trained multilayer perceptron neural network was rooted, and a quick propagation training algorithm was used to train ANN. The purpose of optimization was to decide the maximum tensile strength and minimum burn-off length of the welded joint which was done by varying the friction welding process variables. The order of importance of input parameters for friction welding of Incoloy 800 H was HP [ UP [ N [ BOL. After predicting the model using RSM and ANN, a comparison was made for predicting the effectiveness of two methodologies. By analyzing the results, it was observed that as compared to RSM, ANN model was more specific.

show abstract

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

Cited by 51 publications

References 6 publications

Combining the advantages of neural networks using the concept of committee machine in the groundwater salinity prediction

Combining the advantages of neural networks using the concept of committee machine in the groundwater salinity prediction

Modeling Dryness Severity Using Artificial Neural Network at the Okavango Delta, Botswana

A Comparative Study of Artificial Neural Network and Response Surface Methodology for Optimization of Friction Welding of Incoloy 800 H

Contact Info

Product

Resources

About