An increasing need to water causes the importance of planning management in order to control water consumption in the future. River flow prediction, in addition to the management of water resources, can predict natural disasters such as flood and drought. Therefore, an accurate estimation of river flow using different models is an issue which has been considered by different water resource researchers. Intelligent models have been used to predict river flow. One of these models, which have shown appropriate performance, is Gene Expression Programming (GEP). A use of intelligent models in combinations has been lately accepted and for this purpose, the wavelet transform is usually used.
In this study, the GEP model was used for modeling flow in the daily and monthly scale in Gamasiyab River. For this purpose, data of precipitation, temperature, evaporation and flow Gamasiyab River in Varayeneh Station was used during the period from 1970 to 2012. To increase the accuracy of the model, two methods of data pre-process, called Wavelet transform, and principal components analysis (PCA) and were used in such a way that the primary signal of each input parameter was decomposed using the wavelet transform. Then, to determine main sub-signals, the principal components analysis was used and main sub-signals as inputs were entered into the GEP model to produce Wavelet- Gene Expression Programming (WGEP).
Detection of different structures of the GEP model showed that the performance of the model was good on the daily scale, but in the monthly scale, the performance was reduced. The comparison of the WGEP model with The GEP model showed that the performance of the hybrid model in both of the daily and monthly scale was better than the simple model. It’s because of a pre-process which was done on data. The results of the hybrid model, based on the coefficient determination, was increased by 4% on the daily scale, and by 23% in the monthly scale. Also, regarding too many sub-signals, using the Principal Components Analysis increased the speed of running.
Using pre-process of data has increased the performance of the model and using the PCA, as an auxiliary tool for the wavelet transform, increased the speed and accuracy of the model. Totally, the results showed that it’s possible to use the GEP model with the wavelet transform as a suitable tool for modeling and predicting the flow of Gamasiyab River.

Predicting rivers flow, as one of the main resources of water for human beings, has always been one of the important issues discussed in hydrology and water resources. So, different models have been used for modeling and predicting rivers flow.
 In this study, two genetic models, Gene Expression Programming (GEP) and genetic programming (GP) were evaluated. Flow, temperature, precipitation, and evaporation data were used to model the daily flow in Tale Zang station. The results showed that GEP model, with R2=0.86 and RMSE=0.0030 m3/s, had the better performance than GP model, with R2=0.85 and RMSE=0.0037 m3/s. Moreover, the speed of GEP was more than GP and had ability to present results in a short time. By increasing the number of data, the speed of GP decreased and sometimes it couldn’t present results, while GEP had the ability to work with more data and model the river flow.

The pan evaporation is used as a practical parameter in various fields, such as estimating water loss from lakes and dams, as well as estimating the Plant water requirement, especially in areas where there is no lysimeter information. Modeling this parameter can be useful in the estimation of missing data and long-term planning of water resources and agricultural development. In this research, by using an artificial intelligence model (Gene Expression Programming, GEP) and two time series models (Fourier and ARIMA), evaporation from the pan at Zayanderud dam station, was modeled in the period from 1344 to 1396 (53 years). The time series of pan evaporation on daily scale for the months of June (Khordad), July (Tir), August (Mordad), September (Shahrivar), and October (Mehr) as input to the Fourier and ARIMA models and 4 different patterns including the use of daily evaporation data 1 month, 2 months, 3 months and 4 months ago, were used as input for gene expression programming model. The results showed that the GEP model has acceptable results only in Mehr, and for other months the results are not acceptable in terms of statistical indicators. The daily evaporation estimated error was found to be 0.38 mm in Mehr. This error was acceptable based on the coefficient of determination of 0.84, the Nash-Sutcliffe coefficient of 0.83 and the Willmott's index of  agreement of 0.95. Unlike the gene expression programming model, the Fourier model provided acceptable results in all the studied months. The error values were obtained between 1.02 and 0.7 mm per day in all the studied months, which is equivalent to 5.2 to 8.8 percent. Comparing the results of the above two models with the ARIMA model showed that, the error values of the ARIMA model in all months are higher (9.4 to 19.6%) than the Fourier model, and Gene Expression Programming model. Therefore, the best model for estimating pan evaporation in October (Mehr) is the Gene Expression Programming model and in the rest of the months, the Fourier model. The evaluation of the model in estimating the extremes daily evaporation data also showed that the highest and lowest accuracy is in October (Mehr) and June (Khordad), respectively. In total, according to the statistical indices, the ability of the Fourier model to estimate the daily evaporation in the Zayanderud dam station was proved. Therefore, this model can be recommended to estimate the daily evaporation and also to reconstruct the missing data in this station

Forecasts of streamflows are required for many activities associated with the planning and operation of components in a water resource system. This paper demonstrates the application of two different intelligent approaches including adaptive neuro-fuzzy (ANFIS) based on grid partition and Gene Expression Programming (GEP) for the prediction of monthly streamflows. In the first part of the study, ANFIS and GEP models were used in one-month ahead streamflow forecasting and the results were evaluated. Monthly run-off data of 21 years from two stations, the Safakhaneh Station on the Sarough-Chay Stream and the Senteh Station on the Kherkherh-Chay Stream in the Zarrineh-rud Basin of Iran were used in the study. The effect of periodicity on the model’s forecasting performance was also investigated. By application of periodicity coefficient in GEP model, determination coefficient in the case of the best input combination for Safakhaneh and Senteh increased 0.19 and 0.25, respectively. In the second part of the study, the performance of the ANFIS and GEP techniques was tested for streamflow estimation using data from the nearby river. The results indicated that the GEP and ANFIS models could be employed successfully in forecasting streamflow. In this case, for the best input combination, root mean square error (RMSE) for ANFIS and GEP obtained equal to 4.88 and 4.89 respectively. However, GEP is superior to ANFIS in giving explicit expressions for the problem.

Groundwater is a prominent source of drinking and domestic water in the world. In this context a reliable water supply policy, specifically during the dry season necessitates accurately acceptable predictions of water table depth fluctuations. The inter-comparison of three artificial intelligence (AI) techniques are presented using the results of water table depth fluctuation time series. These models comprise Artificial Neural Network (ANN), Adaptive Nero-Fuzzy Inference System (ANFIS) and GeneExpression Programming (GEP), which are for water table predicting of Zarringol basin in Golestan province, Iran. The monthly mean water table data with a period between 1980 and 2010 were used for training and testing the models. Statistical parameters, namely, the root mean square error (RMSE) and determination coefficient (R2) were used to measure their performance. Overall, the results indicate that ANN, ANFIS and GEP models could be employed successfully in forecasting water table fluctuation. The best performing model, The highest coefficient of determination for Salakhgheib well (R2=0.83), Kochak Khortom well (R2=0.80) and Imeretaremola well (R2=0.84) calculated that these values are related to gene expression programming method. However, the performance of GEP displayed a better edge over the other two modeling approaches in most of the respects especially in giving explicit expression for the problem.

Modeling and prediction of groundwater level is one of the basic tasks to achieve optimal management of water resources. One way to predict the groundwater level is using artificial intelligence techniques such as neural networks and gene expression planning. The aim of this study was to evaluate the effectiveness of artificial neural network (ANN) and gene expression methods in predicting groundwater level of Jiroft plain aquifer. For this purpose, the data from 65 piezometric wells in the Jiroft plain aquifer was used for a period of eleven years. The level of piezometric wells by each of the techniques of gene expression and neural network were simulated separately and at the end, the root mean square, mean absolute error, and R2 were used to determine the accuracy of the predictions of each of the methods.The results of this study showed the higher efficiency and accuracy of both neural network techniques and gene expression in predicting the groundwater level region. The correlation coefficient in the artificial neural network method gene expression method was equal to 0.96 and 0.72, respectively, indicating the higher efficiency of artificial neural network in the simulation of Jiroft plain groundwater data over the period studied.

In rivers spatially ephemeral rivers، volume of water in downstream reduced due to transmission losses. Thus the modeling such process is important in water resources management and river engineering. In this study، using gene expression programming، transmission losses in zangmar River that is located in northwest Iran، based on observations input and output hydrographs in Mako and Poldasht stations has been calculated. After the introduction of various terminals and commen function in gene expression programming model، the output hydrograph in downstream stations were simulated. Statistical indices showed that the gene expression programming model predict output hydrograph acceptable so that the estimated output losses in comparison with the observed values is 7/4%.

Rate of water hardness is an important factor in hydrogeology, particularly in groundwater quality researches. In recent decades, the artificial intelligence systems such as artificial neural networks have many applications in various sciences, including management of water resources. In this study, estimated rate of groundwater hardness in Mazandaran plain, using Gene expression programming have been studied and the results is compared with other intelligent methods such as artificial neural network and Anfis. For this purpose the hydrogen carbonate, chloride, sulfate, magnesium and calcium monthly time scale of the period (1994-2014) was selected as inputs and water hardness as output. Standard deviation of the correlation coefficient, root mean square error, and coefficient of Nash Sutcliff were used to assess various methods. The results showed that Gene expression programming model has the maximum correlation coefficient 0.960, minimum root mean square error 0.112, mean absolute error 0.171 coefficient of Nash Sutcliff 0.880 was in the verification phase. In overall, the results showed that the Gene expression programming model has high performance in estimating some maximum and intermediate values of groundwater hardness.

Precipitation is considered as one of the most important factures in water cycle. Prediction of monthly Precipitation is important for many purposes such as estimating torrent, drought, run-off, sediment, irrigation programming and also management of drainage basins.In this study we studied and evaluated gene expression programming to predict the Precipitation of the Kakareza river (in lorestan), and the results were compared with results of anfis and artificial neural network model. For this purpose, mean temperature, relative humidity, evaporation, wind speed rate at monthly scale during the period (2005-2015) as input and output parameters were selected as Precipitation . The criteria of correlation coefficient, root mean square error and of mean absolute error were used to evaluate and performance compare of models. The results showed that gene expression programming model has the highest correlation coefficient (0.978), the lowest root mean square error (0.026 mm) and the lowest mean absolute error (0.017mm) became a priority in the validation phase. The results showed that the gene expression programming model to estimate high minimum and maximum values of Precipitation .

Prediction of evaporation as a key component of the hydrological cycle is one of the most important issues in water resources management and meteorology studies. In this study, the performance of ARIMA, SARIMA, gene expression programming, multiple linear regression, Monte Carlo and Thomas Fairing models in prediction of monthly evaporation values of Ekbatan Dam station, west of Iran in a 47 years period (1971-2017) were evaluated. For calibration of these models, 40 years data (1971-2010), and for validation, data from 2011-2017 (7-year) were used. The statistical metrics of the correlation coefficient, root mean square error, standard error, the Akaike information criterion, and NSE were selected for evaluation and comparison of models. The results showed that the SARIMA model has more accurate performance in predicting monthly evaporation. The GEP model, ARIMA, and MLR are ranked second to fourth. However, since the GEP model is easier to use than the SARIMA model and requires fewer variables than the SARIMA model, it shows promise to generate faster results, therefore, the GEP models can be the preferred option compared to others.