Fariborz Bahrami; Aslan Egdernezhad
Abstract
Background and Purpose: Due to the complexities in the nature of ground water systems, it sounds like a demanding job to model either the time or the location of ground water. However, artificial neural networks have a high capability to model both complicated and non-linear models. Besides, Geostatistic ...
Read More
Background and Purpose: Due to the complexities in the nature of ground water systems, it sounds like a demanding job to model either the time or the location of ground water. However, artificial neural networks have a high capability to model both complicated and non-linear models. Besides, Geostatistic Methods are, to a good extent, accurate in modelling ground water.Material and Methods: The aim of this study is to simulate groundwater quality parameters (SAR, TDS and EC) of Dezful Andimeshk plain using ANN-PSO and geostatistical models. For this purpose, information from 61 observation wells in Dezful-Andimeshk plain has been used. Neural network model inputs including qualitative parameters SO42- ، pH ، HCO32-، Na+، Mg2+، Ca2+، TDS، SAR and EC were considered.Results: The results of simulation with intelligent model showed that the highest accuracy of ANN-PSO model in simulation is related to EC, SAR and TDS parameters, respectively. The results of interpolation by geostatistical method showed that the highest accuracy of Kriging model in simulation is related to EC, TDS and SAR parameters, respectively. The general results obtained from the simulation of groundwater quality parameters showed that the ANN-PSO model is more accurate in simulating the groundwater quality parameters of the plain in Andimeshk than the Kriging model. So that the value of R2 for simulating SAR, TDS and EC parameters using ANN-PSO model in the test phase is 0.92, 0.918 and 0.955 respectively and using kriging model is 0.902. 0.915 and 0.931 were estimated.Conclusion: The results of this study also showed that the combination of intelligent models with optimization algorithms is used as a useful tool to simulate groundwater quality parameters.
Seyed Ali Mohammadi Nezhad; Aslan Egder Nezhad
Abstract
The present study stimulated the groundwater quality parameters of Zeidoun plain including Sodium Adsorption Ratio (SAR), Electrical Conductivity (EC), Total Dissolved Solids (TDS), using ANN and ANN-GA models and in the end compare their results with measured data. The input data for TDS quality parameter ...
Read More
The present study stimulated the groundwater quality parameters of Zeidoun plain including Sodium Adsorption Ratio (SAR), Electrical Conductivity (EC), Total Dissolved Solids (TDS), using ANN and ANN-GA models and in the end compare their results with measured data. The input data for TDS quality parameter consist of Na, EC, Ca, Mg, SO4 and SAR, for SAR including the Na, TDS, Hco3, Ca and Mg and quality parameter of EC contains Ca, Mg, SO4, Na and SAR, gathered from 2011 to 2018.The results showed that in ANN and ANN-GA models, the highest accuracy of SAR simulation in the model with sigmoid tangent function, in EC simulator model, the highest accuracy in ANN and ANN-GA models, respectively, related to logarithm stimulus functions. Sigmoid and tangent is sigmoid. Also in ANN and ANN-GA models, the highest accuracy of TDS simulation was obtained in the model with sigmoid tangent stimulus and sigmoid logarithm, respectively. so that the MAE and RMSE statistics have the minimum and R^2 has the maximum value for the model. In general, according to the obtained results, the accuracy of ANN-GA model is higher than ANN model, to simulate the groundwater quality parameters of Zeidoun plain. Therefore, the use of artificial neural network model along with genetic algorithm is a good tool to simulate high quality groundwater quality parameters, without the need for measurement and laboratory work, which requires high time and cost.
Maryam Sayadi; Mojtaba G.Mahmoodlu
Abstract
Background and purpose: The present study was performed to investigate trend and prediction of changes in some quality parameters of Gamasyab river water using multivariate statistical methods and time series. Materials and methods: In this research, the annual means of some qualitative parameters ...
Read More
Background and purpose: The present study was performed to investigate trend and prediction of changes in some quality parameters of Gamasyab river water using multivariate statistical methods and time series. Materials and methods: In this research, the annual means of some qualitative parameters related to a 6-year statistical period in two Pol-Chehr and DoAb stations were used. At first, the factors controlling chemistry of Gamasyab river were determined using Ternary and Gibbs diagrams. Then, to determine a linear relationship between multidimensional variables, Canonical correlation coefficients were used. Finally, the changing trend of water quality parameters in next 5-years was predicted. Results: At Pol-Chehr station, qualitative parameters show an upward trend except for pH. While at DoAb, all qualitative parameters show a downward trend except for Mg and SO4. Based on Ternary and Gibbs diagrams, water dominant facies are Ca-Mg-HCO3 and the main factor controlling water chemistry is water-rock reaction at both stations, respectively. Results showed that the chemical parameters of HCO3 and Mg at Pol-Chehr with canonical coefficients of 0.938 and 0.933 are in the first group and Na with coefficient of 0.845 is situated in the second category. While in DoAb station, chemical variables HCO3 and Ca with coefficients of 0.945 and 0.0789 are placed in the first group, and Na and Cl with the coefficients of 0.930 and 0.800 are in the second group, respectively. First and second group origins of canonical variables can be related to dissolution of limestone and evaporative deposits. Prediction results of the water quality parameters changes in Gamasyab river for the next 5 years showed that an increase in all the parameters except for pH at Pol-Chehr station. While except for Mg and SO4, all quality parameters will decrease at the DoAb station. Conclusion:Water-rock reaction is the most important factor affecting Gamasyab river water chemistry. Document Type: Research article
Mohammad Soleimani; kivan khalili; javad Behmanesh
Abstract
Introduction : More than three decades, hydrologists , using multivariate models to describe complex data modeling. While recently the importance of multivariate models have been proposed in hydrology.Indeed, the results of multivariate models can improve the results of description, modeling, and prediction ...
Read More
Introduction : More than three decades, hydrologists , using multivariate models to describe complex data modeling. While recently the importance of multivariate models have been proposed in hydrology.Indeed, the results of multivariate models can improve the results of description, modeling, and prediction of different parameters by involving other influential factors. Methods: In this study, univariate models (ARMA) and auto-correlated multivariate models with simultaneous autoregressive moving average model (CARMA) were evaluated for modeling EC and TDS parameters of the Southern stations of Urmia Lake Basin. In order to employ CARMA models, annual flow rate timeseries, EC, TDS, SAR, and pH values measured across 3 hydrometric stations (Kotar- Balqchy- Gerdyaghob ) within 1992-2013 were used. Findings: The results of the qualitative parameters of the West River basin of Lake Urmia Showed that in the period under review the flow of the studied rivers in the south of Lake Urmia decrease And the EC and TDS values have experienced an increasing trend. EC and TDS values modeling results showed that the average error (RMSE) EC in modeling values equal to 16/60 mho / cm into the teaching and 13/26 mho / cm in the testing phase and for the TDS parameter values 19/84 and 12/71 in the testing phase is the phase of training. The estimated values of the calculation error and accuracy of the model is located entirely within the confidence interval. Conclusion: The results of multivariate modeling EC and TDS values showed that the involvement of the parameters listed in the model , modeling accuracy will be satisfactory.