mohsen najarchi

Due to the location of Iran in an arid and semi-arid climate, the optimal use of water resources systems and better management in water shortage conditions are necessary. One of the appropriate tools in the field of water resources management is the use of simulation, optimization techniques and the combination of simulation and optimization methods. The main goal of this research is to provide a solution in which, according to the capacity of the reservoir, in addition to achieving the acceptable reliability of supplying demands in the whole period, the percentage of meeting the needs in dry months also increases.

To achieve the optimal operation of the water resources in the Marun and Jareh dams located in the south of Iran, the multi-objective particle swarm optimization (MOPSO) algorithm is linked to the WEAP model to provide a new structure for the water resources management, especially in periods of low water by obtaining the optimal values of water release from the reservoir.In this structure, the WEAP simulator is called directly in the MATLAB environment and executed by the optimization algorithm. In this research, for optimal operation of the system, the amount of water released from the reservoir every month is considered as a decision variable. However, due to the large number of available variables and the high volume of calculations, in the body of the MOPSO optimization model, the flow release coefficients that are considered on a monthly basis are used. Based on these coefficients, every month, a percentage of the water volume in the Marun and Jareeh reservoirs is released to supply the needs of the downstream uses, and the rest is stored for the better management of the reservoir, especially in water shortage conditions. Therefore, according to the application of these coefficients on a monthly basis, 12 variables are considered for each dam and 24 decision variables in the whole multi-dam system in the entire next 30-year operation period.

The optimization process is carried out using the MOPSO multi-objective algorithm. The number of iterations of the algorithm to reach convergence is considered to be around 1000. Finally, after the optimization, according to the population size of 48 and the implementation of the MOPSO model for 1000 iterations, the solutions close to to optimal are obtained, and the optimal exchange curve (Pareto-optimal front) between the optimization objectives (the function of maximizing the supplying percentage and the function of minimizing the violation of the minimum operation level) is achieved (Figure (1)). In Pareto curve the solution with the least amount of penalty due to the violation of the reservoir operation capacity and the highest supplying percentage is chosen as the best answer. Then, these optimal variables are entered in the WEAP surface water model.The average percentage of supplying the needs and the level of reliability of meeting the needs according to Table (1) for different uses in optimization scenario. According to this table, in this scenario, the drinking and industrial demands are fully provided in all months. Also, the average percentage of meeting the agricultural demands of the Marun and Jarrahi basins for August, September, October and November was improved by about 15 to 16%, which is significant and shows a decrease in the severity of failure in these low water months. The supplying percentage in July also increases by about 7%.

The results obtained from the implementation of the optimizer model showed that the percentage of demand supply in the months that was 0% in the reference scenario reached 30-60% and in most of the dry months, it was calculated around 45%. This showed that the optimizer model was able to reduce the failure severity in the worst case and in years with three to eight consecutive dry months. The results showed that according to the application of hedging in the model, some of the need is stored in the high water months to be consumed in the low water months. This research showed that planning water resources and allocating them to existing uses only by relying on maximizing the reliability of supplying needs in the entire period, especially in areas with dry climates where we inevitably face severe water shortages in several months of the year, is not a suitable solution and leads to irreparable financial losses and social consequences. Instead, using the solution of this research will lead to better management of the reservoir and reduce the severity of the failure to supply the needs in the dry months of low water.

In Iran, due to warming and severe precipitation variation along with development in recent decades, more attention should be paid to comprehend the role of climatic factors in water resources. Therefore, this study aims to analyze the trend and heterogeneity of the climatic variables as well as their impact on hydrological processes.

Material and Methodology :

The stations with long-term data were analyzed for trend analysis (Mann-Kendall tests) and homogeneity (Pettitt test) of climatic variables in a 30-year statistical period (1984-2014). The impacts of climatic variables on the basin's runoff were investigated using the Soil and Water Assessment Tool (SWAT) for two climatic time periods (1984-2001 and 2001-2014).

The homogeneity investigation in the stations demonstrated that only in Soleiman Tangeh Station, the year 1998 was determined as the turning point. This case was not observed in other stations. Regarding the investigation of temperature associated with Gharakhil station, the turning point was obtained in 1997 and the trend was increasing and meaningful. The results of the coefficient of determination and Nash-Sutcliffe achieved from the calibration and validation of the SWAT were quite satisfactory.

In general, climate change over the past three decades has led to decline in the runoff of the basin, which may be partly due to the increased evapotranspiration as a result of increased temperature or reduced precipitation in most months. The present study attempts to indicate the significance of climate change and its consequences in the water resource management of the Tajan basin.

The aim of this research is to predict fluctuations in the equivalent thickness of groundwater using GRACE satellite data and modeling it using artificial intelligence hybrid models. The study area of this research is the basin area of Lake Urmia located in the northwest of Iran. For this purpose, 180 GRACE satellite data between April 2002 and March 2017 were used. The output of GRACE satellites includes 6 pixels located on the selected watershed, of which 2 points that overlapped the most with the watershed area were selected for modeling with artificial intelligence tools. The GA-ANN, ICA-ANN and PSO-ANN hybrid models were used for this purpose. The results showed that the output of the ICA-ANN model had the best fit with the observation data with a correlation coefficient equal to 0.915 and 0.942 in the two selected pixels 2 and 5 in the test phase, and the results of this model had the best and closest distribution of points. Considering the importance of knowing the changes in the equivalent thickness of groundwater as one of the most important parameters of the water budget, the artificial intelligence models used in this research can be recommended, especially for areas without basic statistics or in situations where it is not possible to use mathematical models. Without the need for complex relationships and equations to investigate the effect of surface and groundwater interaction and only based on satellite data, the equivalent thickness of groundwater can be predicted in the studied plain in dry and wet periods with great accuracy.

The Dez River, as the third largest river in the country, plays an essential role in the economic, social and environmental life of North Khuzestan. Also, it is very important because it supplies water to more than 125 thousand hectares from the Dez plain and the lands downstream of this plain to the place of Bituminous Dam and provides a significant part of the environmental needs of the Karun River. The purpose of this research is to investigate the trend of quality and pollution along the Dez River and evaluate the effects of urban, agricultural and industrial wastewater discharges on the trend of pollution and quality of the Dez River in 131 intervals based on the QUAL2KW model.

The QUAL2Kw model simulates the river in one dimension (one dimension along the length of the river) along with non-uniform permanent flow and can consider the effect of loading both point and non-point. In this model, in order to determine the concentration of qualitative parameters, the finite difference method is used to numerically solve the displacement-diffusion equation (Chapra et al., 2006). In this research, the QUAL2KW model was used to simulate the process of pollution and quality in Dez River. This model is able to solve the equations related to the river in both permanent and quasi-dynamic conditions. Also, simulate parameters such as dissolved oxygen, biochemical oxygen demand, temperature, ammonia nitrogen, etc. in the river network. In this model, the qualitative simulation is done based on the river course spacing. Spacing is done according to the hydraulic conditions of the river and the place of discharge of pollutants. Therefore, the distance between the regulatory dam and Bandaghir was divided into 131 intervals with variable lengths. In the calibration and validation stages of the model, it was determined that wide parameters such as flow geometry, river hydraulic conditions, water flow rate, aeration coefficients, pollutant entry points, nitrification rate, oxygen demand, etc. in the river are involved in qualitative modeling results.

The results showed that QUAL2KW water quality model is highly accurate in simulating quality parameters and pollution in Dez River. The trend of changes in quality parameters and pollution in the Dez River showed that this river is better in terms of BOD pollution due to the discharge of urban and industrial sewage, in terms of EC pollution due to the discharge of agricultural land drains (mainly sugarcane plan) and in terms of N-NH4 pollution It is in a critical condition due to urban and industrial sewage and drainage of agricultural land. Therefore, it is suggested that all sewage of Dezful city, sewage of fish farming, Haft Tepe complex and Pars paper factory be treated and then discharged, but regarding agricultural drains, corrective measures such as improvement in the type of irrigation systems, fertilizers , the cultivation pattern of the area, etc., should be done at the source.

The construction of a treatment plant as a solution for all polluting sources seems to be expensive and impossible. Therefore, it is suggested that all sewage of Dezful city, sewage of fish farming, Haft Tepe complex and Pars paper factory be treated and then discharged, but regarding agricultural drains, corrective measures such as improvement in the type of irrigation systems, fertilizers , the cultivation pattern of the area, etc., should be done at the source.

The Dez-River's surface water resources system between the Dez regulatory dam and Bandar-e-Ghir is the focus of the current study to create a qualitative-quantitative-model that can be used to determine the best operating strategies. for replicate the existing operational state, a dynamic link between quantitative and qualitative models is built under the "reference-scenario" such that hydraulic linkages are generated between all of the system's components in the coupled system. The monthly environmental demands of the river are one of the choice factors in the optimization-scenario. The goals are to maximize the percentage of needs met and minimize quality standard violations. The implementation of the optimization scenario increased the reliability of providing all the needs of the plain with any priority. This problem illustrates how the reservoir should operate in an ideal state. In many places along the river, particularly the agricultural water withdrawal sites, the minimum violation of water quality standards has happened, according to a comparison of the pollution and quality parameters in the optimization scenario and the reference scenario. The amount of pollution and quality parameters has also improved. The findings show that it is possible to plan more effectively for the appropriate use of currently available water resources by taking into account all stakeholders and utilizing the qualitative-quantitative dynamic connection method of water resources to develop a coupled model using the MOPSO-algorithm. This will ensure that, in addition to meeting needs, the quality and pollution of the river remain close to the standard limits during the operation period.

The fluctuation of underground water level is one of the important criteria required for decision-making in many water resources exploitation models. The lack of reliable and complete data is one of the most important challenges in analyzing the decline and predictions of the underground water level in water management. In recent years, the use of different numerical models has been noticed as a reliable solution. These models are able to estimate based on extensive statistics and information and based on various land maps and measurements such as pumping tests, geophysics, soil and land use maps, topography and slope data, different boundary conditions and using complex equations. The level of underground water in any region.The studied area is Sanghar plain in the west of Iran, located at a distance of 100 km northwest of Kermanshah city (Figure (1)). Sanghar plain is one of the fertile plains in Kermanshah province, whose needs are provided by two systems of surface water and underground water. Part of the water needed in the plain is provided by Suleimanshah Dam (Shahda) and the rest is provided by 278 deep wells dug in the south and west of the plain. 

In the present research, first, by using available statistics and information and maps, the fluctuations of the underground water level of Sanghar Plain were simulated by the GMS model, and the accuracy of the model was evaluated in two stages of calibration and validation. Then, due to the need for much less data volume in machine learning methods, GWO-ANN and PSO-ANN hybrid methods and LSTM and SAELM models were used. Based on the general direction of the underground water flow in the entire Sanghar plain, the grid direction was considered to be 250x250 meters in the north direction. Therefore, the model network was built with 2596 cells (44 rows and 59 columns) with 250 meters intervals, which included 908 active cells and 1688 inactive cells. In this study, the general load boundary package was used to simulate the entry and exit borders of Sangar plain. In this package, the inlet or outlet flow is affected by the hydraulic gradient at the boundary and the conductance of the boundary cell. Using the prepared geophysical sections and the data log of the wells, a rock map of the plain was prepared. Also, the DEM map of the plain was used to determine the upper limits of the layer in the groundwater model. In the GMS model, the WELL package was used to simulate exploitation wells in Dasht Sangar (278 wells) and well cells were identified. The feeding of the plain is one of the important parameters in the groundwater model. Usually, due to the different characteristics of soil, geology, vegetation, rainfall intensity and the slope of the land, the amount of groundwater recharge is different in different places. In the GMS model, the RCH package is used to consider the feeding. The zoning method was used to estimate the hydrodynamic parameters of the aquifer. The zoning of the area for hydraulic guidance and special drainage was done based on the drilling logs of observational, exploratory and piezometric wells, as well as geophysical sections prepared from the area. According to the type of soil and sediments of each zone, the initial values of hydraulic conductivity and specific drainage were estimated. Finally, after performing the calibration process, for each zone, the optimized value of hydraulic conductivity and specific drainage was taken into account. In the underground water simulation section, after the calibration and validation tests of the model in two permanent and non-permanent modes and ensuring its accuracy, the final zoning of the main parameters of the model, i.e. hydraulic conductivity and specific drainage, was prepared so that the model can predict the changes in the underground water level for 6 years. Simulate consecutively. Because all the required information was available for 6 years (October 2019 to September 2015). 

The results showed that the output of the SAELM model had the best fit with the observational data with a correlation coefficient equal to 0.97, and it also had the best and closest distribution of points around the 45 degree line, and in this sense, it is considered the most accurate model. Therefore, to predict the level of underground water in the whole plain, instead of using the complex GMS model with a very large volume of data and also a very time-consuming calibration and validation process, SAELM model can be used with confidence.  

This approach greatly helps the researchers of the underground water sector to predict the changes of the underground water level in dry and wet years without using numerical models with a complex and time-consuming structure using artificial intelligence with high accuracy

Given the application of hydrological response in a watershed, various methods have been used to determine this response and the results have shown a high degree of accuracy and accuracy variability depending on the data used. By reviewing and summarizing the results of research carried out in the modeling of rainfall-runoff, particularly the time-area method, it was found that in most of these studies, the concept of watershed time concentration was used, which in most of the formulas used, the physical properties of the watershed were used and the dependence of time concentration on rainfall conditions was not studied. Therefore, this study was conducted to evaluate these methods using the kinematic wave method in the GIS environment, the HEC-1 method, and optimization methods using genetic algorithms in a V-shaped experimental watershed.

Observational data available in the V-shaped experimental watershed of the University of Illinois was used for rainfall-runoff modeling. The studied watershed had an impermeable aluminum surface and two uniform side sheets with a one-sided slope towards the channel with a constant value of 1%. In addition, a central channel with a one-sided slope towards the outlet of the watershed with a constant value of 1% was present. The roughness coefficient in this watershed was determined based on trial and error at 0.014.

After preparing the time-area histogram of the watershed using each of the mentioned methods, the corresponding outflow hydrographs of the watershed were determined. Then, the results were compared with observational data, and various components of the computational hydrographs were also examined. The results showed that the performance of the genetic algorithm in determining the peak time of the hydrograph with a 15% relative error was better than the performance of the kinematic wave and HEC-1 models. Additionally, the genetic algorithm model had the highest correlation coefficient with observational hydrographs with an average Nash-Sutcliffe Index of 0.968 and an average correlation coefficient of 0.983. Furthermore, by fitting the curve to the modeling results, an equation was obtained to determine the equilibrium time of the watershed relative to rainfall intensity, with a determination coefficient of 0.999. This equation expresses the inverse relationship between equilibrium time and rainfall intensity (with a power of 0.33), i.e., doubling the rainfall intensity reduces the equilibrium time by 20%. Finally, the coefficient of the equation determining the equilibrium time for this watershed was found to be 495.2, and for each rainfall intensity, its corresponding equilibrium time can be calculated with high accuracy.

In this study, under experimental watershed conditions, rainfall-runoff modeling was performed with three categories of events and three categories of different rainfall durations, each event category having four different rainfall intensity sizes. Corresponding hydrographs were obtained for each event by examining the computational hydrographs and comparing them with observational hydrographs, and it was found that the three models had one to two percent relative error in determining the maximum runoff, but in determining the time to reach the hydrograph peak, the kinematic wave and HEC-1 models had an average error of 44%. Finally, using the correlation and Nash-Sutcliffe coefficients, it was determined that the computational hydrographs produced by the genetic algorithm method were closer to the observational hydrographs and had a higher degree of correlation. It is worth mentioning that in this experimental watershed, the dependence of equilibrium time on rainfall intensity in impermeable conditions was confirmed. It is recommended that the effect of infiltration or changes in surface roughness and the determination of the dependence size be investigated.

In recent years, the groundwater resources of Arak plain have been under severe stress, so in some areas, due to the drying up of wells, they have increased the depth of wells to access water. In some areas, the groundwater depth (GWD) is high, which will lead to the salinization of those lands in the future. Regional modeling was used to organize and measure the response of the groundwater resources of Arak plain against the implementation of different management and implementation scenarios. This study aims to investigate the effective factors in the GWD to provide a regional model with multiple linear regression (MLR) method for Arak plain aquifer. For this purpose, the average GWD in the Arak plain, as a dependent variable, and the transmissivity of the aquifer formations, groundwater exploitation values, altitude, average precipitation of the region, the amount of evaporation, and the distance from water resources  are considered independent variables and regression analysis is done in SPSS software media. It was done to present a linear model. In the next stage, the presented model was evaluated by applying it to places where its statistics and information were not used to present the model, and finally, by applying this model in the GIS environment, the GWD map for the region was created. The study was prepared. Also, an artificial neural network (ANN) was used to simulate the depth of underground water. The performance of the ANN was measured through parameters such as root mean square error (RMSE) and correlation coefficient between real and desired outputs (R). The results of both methods indicate that factors such as the transmissivity of aquifer formations, GWD drawdown, topography (the height of the well site on the level of the watershed), the groundwater exploitation values ​​at the maximum operating radius of the well, and the distance from water resources are the main factors of GWD drawdown. But the effectiveness of ANN in estimating GWD drawdown is higher than the MLR method.

Runoff production is due to watershed response to rainfall event. Various researches have been performed in order to accurately determine the watershed response. In most response models, as in kinematic wave-based models, require detailed input data such as cover characteristics, slope, initial moisture, and soil infiltration properties. In this study, a time-area histogram extraction technique was presented via genetic algorithm optimization and deconvolution methods and results were evaluated in theoretical and real watersheds. In the model presented, a set of rainfall-runoff events in matrix form were called as inputs while the corresponding time-area diagrams were extracted. The results showed that the accuracy of the model in estimating the response of a theoretical watershed was 99%, while similar accuracy in direct approach was 74%. The accuracy of the model in estimating the response of the V-shaped geometric watershed and the real Walnut Gulch watershed reached an average of 99%. Therefore, the model introduced in this research is effective in determining the time-area diagram of the V-shaped watershed and may be used in other basins.

Hydrological response is one of the most important issues in watershed studies. Various researches have been performed in order to determine the hydrological response, including the kinematic wave model, and the results indicate the advantages and disadvantages of the models. In this paper, the numerical and analytical methods of solving the kinematic wave equation were investigated and the results were evaluated in a laboratory watershed. So, the finite difference method was used in the framework of HEC-HMS software, and to evaluate the analytical method, by the kinematic wave equation and using GIS software, the flow routing in the laboratory watershed were investigated. The results of the two mentioned methods were placed next to the results of the time-area method in the HEC-1 model, and finally the results of these three methods were compared with the observational results of the rainfall-runoff events in the laboratory watershed. The error of the kinematic wave analytical model, the kinematic wave numerical model and the HEC-1 model in determining the maximum flow rate, according to the relative error index, was about one percent. Also, according to Nash-Sutcliffe index, the kinematic wave analytical model had the best performance with a value of 0.926 and the numerical solution of the kinematic wave with a value of 0.838 was weak compared to the other two models in derivation of the hydrograph. However, the regression index of the HEC-1 model was 0.944 and analytical method with a value of 0.932 ranked second, and the numerical model of the kinematic wave with a value of 0.899 was ranked third.

The use of coupled simulation-optimization models to extract the optimal role curve of dams is one of the effective strategies for optimal management of reservoirs. In certain optimization techniques, historical data of the inflow to the reservoir is usually used to extract the optimal role curve of the dam. It is possible that in the coming years, with the change of the inflow to dams, the parameters based on which the optimal role curve was extracted may no longer work and the results may be unexpected. The objective of this research is to provide a solution for extracting the optimal role curve in real time so that by changing the inflow to the dam in the future without re-executing the optimization algorithm and using artificial intelligence techniques in the shortest time, the optimal role curve compatible with the new conditions can be obtained. In this research, the integration of the NSGA-II multi-objective algorithm and the WEAP simulation model is used to derive optimal policies based on historical data. Then, using the support vector machine method and the results obtained from the output of the optimization algorithm, a new structure is developed so that the optimal role curve can be obtained in real time and based on new inputs. The results indicate that the average error of the optimal role curve extracted from support vector machines is less than 2.5% compared to the role curve obtained from the NSGA-II algorithm in the calibration and validation stages. Therefore, the developed support vector machine model has the ability to quickly provide optimal operation policies in such a way that provides the possibility of optimal management of the system in real time, according to the new data of the inflow to the dam.

Direct soil water retention curve (SWRC) measurement is laborious, time-consuming, and expensive. To estimate its parameters, mathematical models and optimization approaches are applied. In this study, an improved alternative method to solve the optimization problem was introduced and developed. To evaluate the efficiency of this method, 12 soil samples with 6 different textures from 9 different regions of the world were used. The optimization equations were solved using a genetic algorithm (GA) and standard mathematical models, and the best model was chosen based on Taylor diagrams, R2, and computing time. The Bimodal versions of Fredlund-Xing (FX-b) and Brooks-Corney (BC) mathematical models represented the best and poorest findings of this stage, with R2 values of 0.913 and 0.825, respectively. Then, the optimization problem is solved with differential evolution (DE), Salp Swarm Algorithm (SSA), Jaya, and improved Jaya (I-Jaya) method, and the mean values of R2 were obtained 0.919, 0.931, 0.921, and 0.958, respectively. The results indicated a 16% improvement in the average R2, by selecting the suitable mathematical model and also using the I-Jaya.

Water-crop production functions indicate an increase or a decrease in harvest for the plant’s consumed water (evaporation-respiration). To assess production functions of wheat and barley products, linear and second-order methods are used in numerous researches. On the other hand, since the mentioned relationships for some products may not have an acceptable correlation, third-order, logarithmic, and polynomial functions are used in various deficit irrigation treatments of 50, 60, 70, 80, and 90 percent.

Farm data were evaluated and validated with resulted data from discussed equations. In order to study the proposed functions, statistical indices such as root mean square error (RMSE), normalized root mean square error (NRMSE), mean absolute error (MAE), Wilmott index (d), and F-test were used via measurement data in every scenario.

All statistic values of both winter wheat and barley were in permissible range, indicating properness and acceptance of the equations. All functions were acceptable at a significance level of 5 percent for both products. According to the results of studying irrigation depth in terms of winter wheat and barley yield, it can be argued that third-order functions provide more accurate prediction in comparison with logarithmic and polynomial functions in both winter wheat and barley crops, and therefore, third-order function is prioritized over other functions

Nowadays, machine learning models are able to make good predictions based on pattern extraction between data. In this study, a neural-fuzzy network (ANFIS) was used to predict the inflow to the reservoirs of a dam namely, the Mahabad dam located in the northwestern part of Iran. A new Harris Hawk (HHO) optimization algorithm was also used to improve the ANFIS (HHO-ANFIS) structure. Monthly precipitation and temperature and inlet flow data to the reservoir one to three months ago were used as input parameters as 6 different input patterns. About 70% of the data was used for training and 30% to test the models. The results showed that the ANFIS model has good accuracy in training data although, for test data, its accuracy was greatly reduced. The development of the HHO-ANFIS model improved the accuracy of the prediction. The patterns with all input parameters had the highest prediction accuracy. In this pattern, values ​​of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Nash Sutcliffe Efficiency coefficient (NSE) for test data were 3.9 MCM, 2.41 MCM, and 0.86, respectively. Due to the good performance of the model used, it can be recommended for time series predictions.

Daily streamflow prediction is very important for many hydrological applications in providing information for optimal use of water resources. Developing an efficient predictive technique for both long- and short-term streamflow is a challenge in hydrology which is crucial for resource planning and management. This is because streamflow is influenced by various dynamic nonlinear processes, such as rainfall, runoff yield and confluence, evaporation, topography, and anthropic activities. In addition, streamflow forecasting has attracted more attention because of reservoir operations and irrigation management decisions. Over the past decades, researchers have carried out different attempts to forecast daily streamflow. Artificial intelligence modeling has been widely used for streamflow forecasting in recent years because of the availability of long-term gauging data, the ever-increasing computational power.In this study, according to the nonlinear, random distribution, complex characteristics of hydrological parameters such as streamflow, an integrated method including decomposition technique based on the ensemble empirical mode decomposition (EEMD) combined with model tree (MT) was carried to forecast daily streamflow. To assess the validity of the proposed ensemble EEMD-MT model, a hydrometry gagging station, Gachsar station located on Karaj river, was considered for a 28 years period (1984-2012) at daily scale. Accordingly, a total of 9672 daily streamflow time series dataset given from Gachsar gagging station is employed for developing ensemble EEMD-MT model for daily steamflow forecasting. Among total daily streamflow dataset, 75% as calibration dataset were selected to construct the model and remaining of them were selected as validation dataset. One of the important steps in hydrological molding is to determine the optimum number of time delays from the river flow. In this way, two popular metrics, partial autocorrelation function (PACF) and auto-correlation function (ACF) for the time series dataset were calculated to detect the important input variables which have the highest effect on the target variable for modeling. In this study, for Gachsar station, three antecedent values were selected as the input paramater to simulate daily streamflow. Then, all input and output variables should be decomposed by EEMD into several intrinsic mode functions (IMFs) and one residual. IMFs, then, were modeled by MT model separately and all the forecasted results related to each IMF were aggregated. MT and adaptive neural-fuzzy inference system (ANFIS) as the benchmark models are compared with an ensemble EEMD-MT model. Several evaluation metrics such as correlation coefficient, root mean square error, relative square error, mean absolute error, and relative absolute error are considered to check the accuracy of the standalone and proposed ensemble models for streamflow forecasting at Gachsar station. The results obtained from the proposed standalone and ensemble models showed that the accuracy of EEMD-MT method compared to MT method increased by about 7.5% and modeling error for this station in the term of RMSE error index decreased by 6.8% in the validation phase. At this station, the MT with the combination of EEMD algorithm has the best accuracy (R = 0.96) in predicting the daily streamflow of Karaj river. According to the scatter plots, MT model shows an under-predicted performance in the validation stage for Gachsar station, although this drawback improved by considering decomposition process of streamflow integrating with EEMD algorithm. This reflects that a hybrid-based AI approach is a robust and useful tool for simulating daily streamflow over the mountainous region. However, most of the models could not successfully predict the extreme (high and low) flow events. The reason is the developed models are not predominantly trained on extreme events. This can be overcome in the future by the flexibility to incorporate auxiliary information and soft data, such as expert knowledge, into the algorithmic framework, which could provide more flexibility in simulation and assist water managers and dam operators. In summary, this research presents a novel study of testing various AI-based algorithms for streamflow prediction and gives a comprehensive comparison among popular AI methods in hydrologic simulation. The authors believe this unique feature of the AI methods, especially the EEMD-MT algorithm, is to be able to be further employed in the study region and provide more flexibility by adding desired decision variables for reservoir management. However, the proposed methodologies in this study are universally applicable to other mountainous regions, and are flexible to incorporate and test for other hydrologic time series data, such as flood records.

An important issue in the operation of the Gotvand reservoir is the presence of salt formation in this reservoir. The present study has sought to identify whether it is possible to modify the operation curve of the Gotvand Dam to reduce the destructive effects of the Anbal salt dome and increase the operation of this reservoir. To achieve this goal, the performance of the Gotvand Dam reservoir was modeled from the time it was used (from August 2011 to March 2017), as well as the behavior of active salt karstic activity inside the reservoir with the dynamic system tools. The results showed that during the simulation period, the average amount of corrosion of the salt dome in contact with the reservoir water was 20.1 cm per day. Besides, 43.72 million tons of salt has been accumulated in the reservoir. Analysis of the results showed that 39% of the reservoir salinity is due to the dissolution of the salt formation. The rest of the salinity enters the reservoir with the upstream runoff. Based on the results of sensitivity analysis, changes in water level in the reservoir is the most important factor determining the salinity distribution parameters in the reservoir and the best remaining solution to reduce the effects of the salt dome inside the Gotvand Reservoir is to implement the curve of the optimal use of the reservoir for water released through the Gotvand Dam and the upstream basin of this dam.

At the present time, population growth in the world has led to increasing need for water resources in agriculture, industry and urban, and it is necessary to planning for optimal and sustainable use of limited available water resources. In this paper, supply water demands with controlling changes in groundwater level, especially in agricultural lands with maximizing economic profits, has been defined as objectives of Numerical simulation and multi-objective nonlinear optimization modeling. In the model, combined use of optimization and simulation techniques has been used as a useful and powerful way to determine management strategies for optimal utilization of water resources. The optimization approach shows that the amount of water allocated to the agricultural sector decreased by nine percent, and this amount of savings in water consumption led to raised only one percent crop cost in the cultivation. Environmental sustainability and Aquifer saving improved in the amount of 3/03 million cubic meters per year, and this has been achieved while maintaining profits in addition to agricultural economy, supply of drinking water and industry in the region that has been fully provided

In this research, an evolutionary based Neuro-fuzzy technique was utilized to estimate the discharge coefficient of labyrinth weirs. In order to optimize the parameters of the adaptive Neuro-fuzzy inference system (ANFIS), the Firefly Algorithm (FFA) was implemented. In modeling the ANFIS-FFA and ANFIS methods, the Monte Carlo simulation was used to evaluate uncertainty of the model. Furthermore, several models with significant flexibility and generalizability were provided using the k-fold cross validation method. First, the input dimensionless parameters including the Froude number (Fr), ratio of the head above the weir to the weir height (HT/p < /em>), cycle sidewall angle (α), ratio of length of the weir crest to the channel width (Lc/W), ratio of length of the apex geometry to the width of a single cycle (A/w) and the ratio of width of a single cycle to weir height (w/p < /em>) were defined. After that, seven different models were introduced for ANFIS and ANFIS-FFA. Then, using a sensitivity analysis, the superior models (ANFIS-FFA 5 and ANFIS 5) and the most effective input parameter (Froude number) were identified. In addition, the error distribution results showed that about 70% of the superior model (ANFIS-FFA 5) results had an error less than 5%. In other words, the superior model had a high statistical significance. Ultimately, the uncertainty analysis for the superior models was carried out.

Combined triangular crested weir-rectangular gate is one of the most important structures which controlling the level of water surface, measuring discharge and avoiding the sedimentation behind the weir. In this study, 4 models with different geometric conditions were simulated via Flow-3D software. Then, dimensional analysis was done to evaluate the effect of involved dimensionless parameters on the discharge coefficient. These parameters are h/b, h/d and h/y, where h is the water head over the weir, b is the gate width, d is the gate height and y is the distance between the top of the gate to the bottom of weir. Moreover, four different intelligent system models prepared and the accuracy of these models for estimation of discharge were evaluated and compared with each other. Results show that Flow-3D is very accurate in 3D simulation of this structure. Besides, Statistical indices are good for simulation the water head and discharge coefficient, in this study (RMSE, MAE and MRAE for discharge coefficient are 0.0673, 0.221 and 0.295, respectively). Moreover, results show that in all models the dimensionless parameters of h/b, h/d and h/y has inverse proportion with discharge coefficient. Discharge coefficient of combined weir-gate of this study is in the range of 0.3-0.9. On the other hand, the results of four intelligent system models of MLP, M5P, RBF and GRNN show that the MLP model is the superior model among others and respectively M5P, RBF and GRNN are in the next grade.

In this study the influence of water-cement ratio on the mechanical properties (compressive, abrasion, tensile, flexural strength and permeability) of Nano-silica concrete reinforced with polypropylene fibers is evaluated. The specimens contain 4% of Nano-silica, 0.30, 0.35, 0.40, 0.45 and 0.50 of water-cement ratios and 0, 0.10, 0.15, 0.25 and 0.35 percent by volume of polypropylene fibers. Other design features remained fixed in all concrete samples. The results of the experiments showed that with decreasing the ratio of water to cement from 0.50 to 0.30, all the mechanical properties of the concrete were improved. In addition, the test results showed a significant increase in mechanical properties improvement of concrete by using polypropylene fibers. Tensile strength, flexural strength and abrasion resistance of concrete increased up to 22%, 40%, and 27% respectively for 28 days age specimens. Also, considerable reduction of hydraulic conductivity coefficient to 51% indicates high durability of these types of concrete. Compressive strength had increment of 22%, 15% and 14% for 7, 28 and 90 days age specimens respectively.

In this paper, salinity, total dissolved solids (TDS), groundwater level (GWL) and electrical conductivity (EC) of the Arak Plain, located in Markazi Province, Iran, were simulated using four novel artificial intelligence models including extreme learning machine (ELM), wavelet extreme learning machine (WELM), online sequential extreme learning machine (OSELM) and wavelet online sequential extreme learning machine (OSELM) as well as the MODFLOW software (MT3D model). In order to develop the hybrid artificial intelligence models, the wavelet transform was employed. First, the effective lags in estimating the quality and quantity parameters of the groundwater were identified using the autocorrelation function (ACF) and the partial autocorrelation function (PACF) analysis. After that, four different models were developed using the effective lags for each of the artificial intelligence methods. Then, the superior models in simulating the groundwater quality and quantity parameters were detected by conducting a sensitivity analysis. Subsequently, the most effective lags in estimating these parameters were introduced. In addition, the results of The MODFLOW model were compared with the artificial intelligence models, and it was concluded that the latter were more accurate. For instance, the scatter index and Nash-Sutcliffe efficiency coefficient values for TDS simulation by the superior model were 5.34E-03 and 0.991, respectively. Additionally, RMSE and MAE for estimating groundwater level using the superior model were obtained 0.078 and 0.061, respectively. Finally, uncertainty analysis for the superior models was carried out.

Generally, labyrinth weirs pass more water compared to their equivalent rectangular weirs. Thus, these types of weirs are popular amongst hydraulic and environmental engineers. In this paper, for the first time, a novel artificial intelligence (AI) technique called "outlier robust extreme learning machine (ORELM)" is used to estimate the discharge coefficient of labyrinth weirs. The ORELM method has been proposed in order to overcome the difficulties of the classical ELM in predicting datasets with outliers. In this method, the concept of “sparsity characteristic of outliers” is used. Also, in this study, to verify the results of the numerical models the experimental measurements conducted by Kumar et al. (2011) and Seamons (2014) are employed. The experimental model established by Kumar et al. (2011) is composed of a rectangular channel with a length of 12m, a width of 0.28m and a depth of 0.41m. The weir is made of steel sheets and placed at an 11m distance from rectangular channel inlet. Also, Seamons (2014) experimental model has been set up in a rectangular channel with the length, width and height of 14.6m, 1.2m and 0.9m, respectively. First, the number of the hidden layer neurons initials from 5 and continues to 45 and the most optimal number the hidden layer neurons are taken into account equal to 5. In this study, the Monte Carlo simulations are used for examining the abilities of the numerical models. The main idea of this method is based on solving problems which might be actual in nature using random decision-making. The Monte-Carlo methods are usually implemented for simulating physical and mathematical systems which are not solvable by means of other methods. In this paper, the K-fold cross validation method is employed for validating the results of the numerical models. To this end, the observational data are divided into five equal sets and each time one set of these data is used for testing the numerical model and the rest for training it. This procedure is repeated five times and each test is used exactly once to train and once to test. This method increases the flexibility of the numerical model when dealing with the observational data, and it can be said that the numerical model has the ability to model a greater range of laboratory data. For instance, the maxim value of R2 is obtained for the K=4 case (R2=0.954), while for the K=5 case the values of RMSE and MARE are estimated 0.034 and 4.408, respectively. After that, different activation functions are evaluated in order to detect the most accurate one for the numerical model. Subsequently, six different ORELM models are developed using the parameters affecting the discharge coefficient of labyrinth weirs. Also, the superior model and the most effective input parameters are identified through a sensitivity analysis. For example, the values of R2, RMSRE and NSC for the superior model are calculated 0.943, 5.224 and 0.940, respectively. Furthermore, the ratio of the head above the weir to the weir height (HT/P) and the ratio of the width of a single cycle to the weir height (w/P) are introduced as the most important input parameters. Also, the results of the ORELM superior model are compared with the artificial intelligence models including the extreme learning machine, artificial neural network and the support vector machine and it is concluded that ORELM has a better performance. Then, an uncertainty analysis is conducted for the ORELM, ELM, ANN and SVM models and it is proved that ORELM has an overestimated performance.

This study investigated the effects of climatic changes on temperature, rainfall, and runoff in the Doroudzan catchment in the northeast of Fars province, Iran. Temperature and rainfall changes in two future middle and far period downscaled and studied using 15 CMIP3 climatic models, under emission scenarios A2, B1and A1B, from the database of the LARS WG5.5 model. The difference in the amount of variations in temperature and rainfall in the periods and the observational amounts under the 15 models indicated the uncertainty of the changes values. To reduce this uncertainty and limit the results to the management and planning of water resources, an ensemble approach was considered. For the preparation of the ensemble approach, the parameters from the files of the 15- models file scenarios were averaged so that a climatic ensemble model could be obtained for each period. Then, the runoffs of the next two periods were produced using the FEEDFORWARD neural network. The results indicated an increase in the average monthly maximum temperature and the minimum temperature. The results also showed a decrease in the rainfall in the early months of the year as well as an increase in the rainfall in the spring in most scenarios. Generally, results showed a reduction in the average annual rainfall. The maximum amount of reduction was in far future far period. Besides, a reduction occurred in the average runoff of the catchment in the periods, values in the most years.

The objective of this research was to save water resources, using nonlinear programming model to optimize the crop pattern under full and deficit irrigation techniques in eight observation fields for eleven predominant irrigated crops, including winter wheat, barley, rapeseed, autumn sugar beet, corn, sorghum, tomato, onion and potatoes, bean and autumn watermelon in the downstream lands of Doyraj Dehloran reservoir located in the southwest of Iran. The yield reduction and net income of each crop were calculated for 50, 60, 70, 80, 90 and 100% of water requirements during the growing season. The objective function for maximizing net profit with different constraints including constant cultivated area was determined for the existing cropping pattern, the policies of the Ministry of Agriculture Jihad and the proposed pattern. In the case of full irrigation, the results showed that the net profit of the Ministry of Agriculture Jihad cropping pattern was increased 1.33, 1.19 and 1.05% for 100, 90 and 80% of water requirement, respectively. Under deficit irrigation conditions (90 and 80%), water resources are saved 18 and 34%, respectively. The proposed cropping pattern, including four crops of wheat, canola, autumn sugar beet and grain corn increased the net profit of 60, 70, 80 and 90% of the crop water requirement treatments by 14.4, 33.6, 54 and 74.7%, respectively, as compared to the existing cropping pattern. In the proposed deficit irrigation treatments, the water resources were saved 60%, 49%, 35% and 19%, respectively. The results of nonlinear programing model showed that the optimization of cropping pattern with deficit irrigation technique, not only increases the net profits, but also it can be effective in conserving surface and ground water resources.

Due to the increasing need for water and the lack of access to its sources, it is essential to maintain and use groundwater resources. So, identifying and exploiting these resources has particular importance. Investigating interflows requires geo-electric and geotechnical studies, both of which require a lot of time and cost. Therefore, it is necessary to provide a method or model that can minimize the cost of investigating interflows as much as possible. In this research, two types of artificial neural networks- multi-layer perceptron (MLP) and radial base function (RBF) were used to study the relationship between hydro-geomorphological characteristics of the watershed basin and interflows in seven watershed sub-basins in Kerman province. Hydro-geomorphological characteristics of subsurface dams were considered as input independent variables, and the discharge of interflow in the watershed basin outlet was considered as dependent variable. The results of this study show that radial base function (RBF) with determination coefficient of 0.9182 and mean squares error of 0.0289, has more accurate results in estimating the discharge of interflow, compared to artificial neural network method of multilayer perceptron (MLP) with determination coefficient of 0.5288  and mean squares error of 0.725. Regarding the determination coefficient in the used methods, it can be concluded that the model of the neural network is the appropriate solution and low cost to check this connection in the watershed.