فهرست مطالب seyed morteza seyedian

One of the important topics in river engineering is the design of stable alluvial channel geometry in the regime mode (dynamic balance between erosion and sedimentation) including the width, depth and slope. In this research, the ANFIS and ANFIS-PSO models were used to model the geometry parameters of stable channels. To achieve this objective, we utilized a comprehensive dataset comprising 410 data series sourced from 15 different channels, encompassing various types such as straight and meandering, as well as natural and laboratory. In each measurement, information on the flow rate (Q), average particle diameter (d), shear stress (τ), top width of the channel (W), average depth of flow (h) and longitudinal slope of the channel (S) was collected. Randomly, 70% of the data was used for training, and the remaining 30% was used for validation of the ANFIS and ANFIS-PSO models. Totally, 42 models were derived from the combination of 7 input data sets (Q, d, and τ) and employed both ANFIS and ANFIS-PSO, models to estimate the W, h, and S as the three types of outputs. In modeling of the W and h parameters, the best input was the Q, which the R2, CRM and NRMSE for all data with the ANFIS model were equal to 0.954, -0.029, 0.567 and with ANFIS-PSO model were 0.912, -0.042, and 0.487, respectively. Also, to estimate the S, the modeling results had error. In general, the modeling results with the ANFIS-PSO model were more accurate than the results of the ANFIS model.

Nowadays, demand for water is increasing especially in arid and semi-arid regions (e.g., Iran) due to population growth, economic development, higher standard of living, and changes in consumption patterns. Hence, optimal management of water resources in these areas is essential. Furthermore, climate change and increasingly extreme weather events have caused a surge in natural disasters (e.g., floods) over the past 50 years in arid and semi-arid regions. Thus, forecasting and modeling of runoff data is extremely necessary for planning and managing of water resources. Water flow forecasting plays a key role in flood reduction, reservoir optimization, and reservoir management. These models are mostly developed and applied for simulation and prediction. Therefore, different types of forecasting methods have been proposed over the decades including: Box and Jenkins (SARIMA), Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), and Genetic Algorithm (GA) models. Forecasting hydrological reactions invariably involves uncertainty. So far, numerous studies have been performed to improve the reliability and accuracy of hydrological forecasts, resulting in reduced risk error. Therefore, the main objective of current research was to use artificial intelligence methods consisting of ANN, ANFIS, GA, and SARIMA models to predict monthly runoff data and also select the best model for the efficient management of water resources in the Gharasou River basin.

Gharasou river basin with an area of 1624 square kilometers is located in the west of Golestan province and has an important role in providing water resources required in this province. In this research, to model and forecast the runoff process, the monthly runoff time series of 4 hydrometric stations of Pol-Tuskestan, Naharkhoran, Ghazmahale, and Siah-ab over Gharasou River basin were used for a period of 36 years (1982-2018). The time series homogeneity was examined using the Chow`s method. Runoff data are time dependent, so initially these data were arranged in time series. After sorting the data, four models consisting of Box and Jenkins (SARIMA), Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), and Genetic Algorithm (GA) models were used to forecast monthly runoff. To increase the prediction accuracy of other methods, the far time series of monthly runoff were first ignored based on to neural network method and then the number of effective years for modeling was determined. Later, the monthly runoff was forecasted for the next 12 months using four models consisting of SARIMA, ANN, ANFIS, and GA. Lastly, based on the forecasted values and using MAD, RMSE and MAPE indices, the accuracy and precision of SARIMA, ANN, ANFIS and GA models were compared. Modeling and forecasting were done using Minitab, R and SPSS software packages.

Based on the type of distribution of monthly runoff and the presence of zero data, log(1+Yt) conversion was used in the models to stabilize the variance. The results according to the autocorrelation diagrams revealed that the time series in all stations have seasonal trend with a period of 12 months. Then, the monthly runoff of the next 12 months was forecasted using four models including SARIMA, ANN, ANFIS and GA. Model validation results using three indicators of MAD, RMSE and MAPE revealed that the ANN model in the three hydrometric stations of Naharkhoran, Pol-Tuskestan and Siah-ab had the best performance. In these three hydrometric stations, after ANN model, the ANFIS model has been selected as the most suitable model. However, the performance of these two models has been very similar. In the Ghazmahaleh hydrometric station, two models of ANFIS and ANN had the best performance, respectively. In this study, it was also found that in four selected hydrometric stations, the GA model had a good performance after the two models of ANN and ANFIS. Although SARIMA model performed very well in identifying the trend of monthly runoff changes, it had the weakest performance among the methods. The forecast data using SARIMA model were overestimated compared to the actual data for March and April, but in other months, the forecast data using this model were relatively appropriate.

In this research, to model and predict the monthly runoff process, four models including SARIMA, ANN, ANFIS, and GA models were used for four selected hydrometric stations in Gharasou River basin. The results of model validation using three indicators of MAD, RMSE and MAPE showed that the ANN and ANFIS models had the best performance among the four models used. It was also found that time series of runoff data in hydrometric stations have undergone structural changes due to the physical and climatic alterations in the upstream of rivers. Therefore, the distant past of time series may cause deviations in modeling and forecasting results. To overcome this problem, making use of an algorithm to select the number of effective years in modeling and forecasting can be useful. Artificial neural network provides a suitable criterion for selecting the number of effective years due to its high accuracy in modeling and forecasting. Based on the effective years identified by this model, other models can be modified and provide more appropriate input data for forecasting from other models.

Fertilizer use is cost-effective until the higher yield supply the cost of consuming more fertilizer. In other words, like any other investment, fertilizer use should have a reasonable return because the law of diminishing returns also applies to fertilizers (Khajehpour, 2008). Application of nitrogen increased Seed yield and Protein percentage but nitrogen agronomic efficiency decreased (Doaei, 2018). In many crops, topping reduces vegetative growth and transfers more and better photosynthetic materials to specific organs, especially seeds. This increases the penetration of light into the canopy and the lower leaves of the plant can use more light. Therefore, increases the photosynthesis of the lower leaves, transfers more photosynthetic materials to growing organs and as a result, productivity will increases. It seems that earlier topping will reduce the number of pods per plant and will improve the conditions for photosynthetic material to be transferred to the pods. Thus, more seeds per pod will be produced. Furthermore, the flowers that will be set in late, have no opportunity to form a large pod and consequently, the fewer seeds will be set in the pod. Delay in topping will reduce the number of seeds per pod of faba bean (Nakhzari Moghaddam, 2013).

In order to study the effect of topping, nitrogen and supplemental irrigation on green pod yield, protein percentage, proline rate and agronomic efficiency of nitrogen in faba bean, a factorial experiment based on Randomized Complete Block Design was conducted with three replications at research farm of Gonbad Kavous University during growing season of 2016-2017. Planting date was 11.13.2016 and harvest date was 5.6.2017. Topping factor was in three levels of non- topping, topping at beginning of flowering and topping at beginning of seed filling, nitrogen in three levels including 0, 50 and 100 kg nitrogen per hectare and supplementary irrigation in two levels of non irrigation and irrigation at the filling stage. Each plot had four rows with 50 cm width and four meter length. Seed planted in depth of three cm. one third of nitrogen were used in sowing date, one third in branching and other one third in seed filling stage. Supplemental irrigation was done in 5.24.2017, first topping in 4.30.2017 and second in 5.13.2017.

The results showed that the effect of topping on green pod yield, proline rate and agronomic efficiency of nitrogen was significant but on protein percentage was not significant. Effect of nitrogen and supplementary irrigation on green pod yield, proline rate, protein percentage and agronomic efficiency of nitrogen were significant. Green pod yield in none topping treatment, topping at the beginning of flowering and seed filling stages was 21523, 29118 and 27737 kg.ha-1, respectively. The highest yield of green pod with 29118 kg.ha-1 was related to consumption of 100 kg N.ha-1 and the least was related to treatment of non application of nitrogen with 22149 kg ha-1. Although application of nitrogen increased green pod yield but agronomic efficiency of nitrogen was decreased. Reducing of nitrogen use efficiency was due to increasing nitrogen loss through leaching and sublimation and the lack of effective absorption by the plant. Supplemental irrigation increased green pod yield 5143 kg ha-1 (21.83%). Topping by reducing top dominance transfered more nutrients into pods and therefore pod yield increased. Agronomic efficiency of nitrogen in treatment of topping at beginning of seed filling was 89.85 and at beginning of flowering was 55.96 seed grain/kg nitrogen. Nitrogen consumption increased protein percentage of the seed so that in treatment of 100 kg Nha-1 protein percentage was 22.65 (7.65% more d the protein cont than non consumption). Proline rate and protein percentage in none irrigation treatment was greater than irrigation treatment but green pod yield and agronomic efficiency of nitrogen was lower.

Topping, nitrogen consumption and irrigation increased green pod yield. Therefore, for obtaining more yield of faba bean it is nessesary to remove head of plant, use enough nitrogen and irrigate plans at least one time in reproductive stage.

The study area in this research is Dasht village located in North Khorasan Province and Besh Oily Village in Golestan Province. The purpose of this study was to investigate and compare the various flood management practices in two flood plain villages (with a set of structural and non-structural measures) and Besh Oily village (displacement of settlement and resettlement). So, as with most surveys, by focusing on a limited sample of the entire community and using the questionnaire, the required data was gathered. The statistical population of this study is the residents of Dasht plain located in North Khorasan province (a set of managing and structural measures for flood control) equal to 391 households and also residents of Besh Oily village in Golestan province (displaced in a limited extent) equal to 129 households. The questionnaires include four variables related to the subject of research, including social (9 components), economic (9 components), psychological (5 components) and bioenvironmental dimensions (6 components). Questionnaires have been basically formed of closed questions with answers in the five-point Likert scale. In the next step, after filling in the questionnaires and removing probable deficiencies, the required information was extracted from the questionnaires and analyzed to achieve the objectives of the research. For this purpose, the statistical method of comparing the means and the panel design based on the attitude of the sample population in the two periods before and after the implementation of flood management measures were used. The results of the analysis of the single-sample t-test of the studied patterns showed a significant difference in both patterns in terms of social, psychological and bioenvironmental dimensions. Also, the findings from the aggregation of the explanatory items of the economic dimension indicate a significant difference in this dimension in the structural and nonstructural model and the average level of the items. Also, the results of independent samples t-test revealed that there is no significant difference in social and bioenvironmental dimensions, however there is a significant difference in the economic and psychological dimensions between the two studied patterns.

The scour depth estimation is of great importance. Researchers have provided many empirical relationships based on laboratory and field work, but so far no relationship has been found to be satisfactory in different situations. In this study, the accuracy of different experimental (individual) relationships was evaluated in two stages before and after the correctional correction. The results show that before and after the bias correction, the individual relations of the National Institute and Mason with the mean square error of 0.87 and 0.23 meters are the most accurate. The combination of individual relationships with combined methods models shows that the GRA and EWA methods with a mean square error of 0.25 and 0.23 meters were the most accurate among the direct methods in before and after bias correction stage. The error of the AICA and BICA indirect methods in before and after bias correction is similar to the best single relation and could not improve the results of the individual relationships. The results of local method (KNN) and artificial intelligence (LS-SVM) method before and after bias correction are equal and estimate scour depth more accurately than individual relations. Comparison of different combinational methods in before and after bias correction shows that individual relationships with maximum scour depth using different combinational methods can improve predictive accuracy.

Because of incomplete model input and imperfections of the model structure there is not any single hydrological model that has the best performance in different conditions and present outputs without uncertainty. In this situation by combining individual models outputs, the strengths of each single model are used to make a new model that performs better than each single model. In this study the efficiency of nonparametric K nearest neighbor and the Fuzzy C-Means clustering based methods were compared with BGA (Bates Granger Averaging), GRA (Granger Ramanathan Averaging), AICA (Akaike Information Criterion), BICA(Bayes Information Criterion), equal weights averaging and lasso methods in averaging output of hydrological models GR5J, SimHyd , SACRAMENTO and SMAR. Firstly, using the amount of rainfall, evapotranspiration, temperature, and the daily discharge of the Kasilian Watershed in Pol Sefid city at the Bon Koh Station was simulated by each hydrological model. Then different model averaging methods were used to combine the output of each single model. Results indicated that for the calibration period, the GR5J and SACRAMENTO, and the correlation coefficient, Nash Sutcliffe efficiency and RMSE were 0.83, 0.69 and 0.24 respectively. The models SimHyd and GR5J performed better for the validation period; the correlation coefficient, Nash Sutcliffe efficiency and RMSE were 0.73, 0.27 and 0.52 respectively. The lasso and GRA model averaging had the best performance for the calibration period and for the validation data equal weights averaging and BGA had the best performance. For calibration data K nearest neighbor performed better than fuzzy K means clustering based method and the best performance for two methods was obtained at 20 neighbors and for validation data fuzzy K means clustering based method performed better and it observed model performance was improved as the number of neighbors was increased.

Rivers and streams was eroded by flood flows and destroy bridges, farmland, and in some cases homes every year. Study of rivers hydraulic pattern is necessary to control and manage rivers to make better decisions in critical situations. Irregular gravel mining is one of the most important factors to unbalance river hydraulic. The aim of this study is to evaluate the sand and gravel minig in river Qurchay that gravel mining operation was conducted in the range of 6 km. Therefore, collected of data contain sediment, discharge and map 1:1000. After entering data into the HEC-RAS model, hydraulic and sediment was simulate in period of 2005-2015. Yang relationship was predicted sediment transport very well. Bed slope changes in 6 km river in sections show that fluctuations of bed slope decreases in 2015 compared to 2005. It also shows the average speed is also reduced in 2015. The results of the simulation show that the rate of erosion and sedimentation at first 5 km is almost in equilibrium and does not cover gravel mining. The best area for gravel mining is final 720 meters of the river because flow velocity decreased due to slope and shape of cross section and sediment deposited with an average depth of 90 cm. Calculations show that the amount of gravel was mined almost 0.4 million tons per year.

Despite modern scientific knowledge and computational power in hydrology, the key to properly addressing hydrologic uncertainty remains a critical and challenging one. Here, we applied lumped HBV hydrological model to describe the uncertainty in runoff prediction in Chehl-Chay watershed in Golestan province. We applied a new framework for uncertainty analysis that is rooted on ideas from predicting model residual uncertainty. The uncertainty calculated by local Errors and Clustering (EEC) is compared with estimates from two non parametric methods (quantile regression (QR) and random forest (RF)) and a parametric method (GLUE). Firstly, the model parameters were optimized by Shuffled Complex Evolution approach and model residuals of test data were computed. Fuzzy clustering in EEC is carried out by the fuzzy c-means method and employs four clusters, predictive discharges, observed discharges, rainfall values and residuals in study basin. The results of this case study show that the uncertainty estimates obtained by EES which is trained by SVM gives wider uncertainty band and RF gives narrower uncertainty band. The best overall uncertainty estimates according to the PICP, MPI and ARIL indices were obtained with QR and then EEC. In comparison with non-parametric, with respct to all indices nonparametric methods had better performance than GLUE method.

IIn many semiarid regions of Iran, soil erosion has become a serious environmental problem affecting land productivity, nutrient loss, water quality, and freshwater ecosystems. Rates of soil loss differ according to erosion type and land degradation processes. Rill erosion is commonly observed when rainstorms occur on steep slopes and sediment transport in rill flows exhibits the characteristics of non-equilibrium transport. In this paper, sediment concentration of rill flow is estimated by adaptive neuro-fuzzy inference system (ANFIS). A series of mathematical equation and parameters effecting on` rill hydrodynamics and soil detachment were used for well-defined rill sediment concentration. A series of filed experiments were performed to evaluate the model. The stepwise method was used to selecting the most important and effective input variables from measured input parameters of soil properties, topographic and vegetation attributes affecting sediment concentration of rill flow. Based on the stepwise procedure the most significant parameters in the model predications were steep slope, vegetation percentage, clay percentage and shear stress parameters. The values of sediment concentration simulated by the model were in agreement with observed values with Coefficient of Correlation (R2), Root Mean Square Error (RMSE) and Mean Bias Error (MBE) of 0.697, 30.5 and 1.0, respectively. The results of the investigation show that the data-driven ANFIS modeling approach can be a powerful alternative technique for correctly estimating rill sediment concentration.

In recent decades following the massive increase in computational power, considerable progress has been made in hydrological models. As the complexity of the model increases, model parameters increases and this lead to increasing the chances of overfitting and difficulty in identifying both model parameter values and model structure. One possible way to mitigate over-parameterization/non-identifiability is reducing the number of parameters to a small number that can be sufficiently calibrated with limited data. Sensitivity analysis (SA) is a commonly used approach for identifying important parameters that dominate model behaviors. Overall, they can be categorized into two groups: local SA and global SA. The local SA explores the changes of model response by varying one parameter while keeping other parameters constant . On the other hand, the global SA examines the changes of model response by varying all parameters at the same time. No general rule has yet been defined for verifying the convergence of the General SA methods. In order to fill this gap this paper presents a convergence analysis of three widely used SA methods (Morris screening, Sobol and Entropy index) for two rainfall-runoff models, TOPMODEL and HBV. The simulations are carried out over ChehlChay watershed within Gorganrood River Basin.
The sensitivity and interaction analysis based onSobol, Morris screen and Entropy methods were applied. The Morris method has been proposed as a screening method to identify a subset of inputs that have the greatest influence on the outputs.Sobol SA is a global, variance-based method that attributes variance in the model output to individual parameters and their interactions.Mutual entropy analysis is a sensitivity analysis method in which the mutual entropy of two variables is regarded as the correlative extent between these two variables. The distribution character of data (X, Y) can be expressed by contingency tables. The HBV model and TOPMODEL are used as a test problem. There are thirteen and nine parameters in the HBV model and TOPMODEL models, respectively. In each model, samples of the model parameter space are obtained using a latin-hypercube. The convergence analysis has been performed by increasing the number of simulations until there was no significant change of the sensitivity measure. In addition, the three SA methods are evaluated and compared in terms of convergence, the related evolution of the parameter ranking results and required computation cost.
Results of the quantitative convergence analysis for Morris screen was achieved at 700 and 1000 number of simulations for HBV and TOPMODEL models, respectively. Results for the Sobol method deviated considerably from the other methods by 22000 and 28000 for the TOPMODEL and HBV models, respectively. In Entropy method need about 6000 samples for the same purpose in both hydrological models. The ranking of parameters sensitivity indices in TOPMODEL for the first two most sensitive parameters for the three methods are similar. In general, the ranks of sensitive parameters are the same for all methods. Meanwhile for Entropy method, M and Srmax as the third and fourth ranking are vice versa than other two methods. In HBV model, Sobol and Morris screen methods provide similar results for those model parameters having the highest influence. For the parameter P, the sensitivity obtained from Entropy method was 3rd rank but in two other methods the parameter ranking varies from 3rd to sixth. In Entropy parameter FC becomes the most important parameter but in Morris screen and Sobol methods, the model parameter BETA selected as the parameter with the highest importance.
There is no single best strategy for all problems. Therefore in general use of two or more methods, preferably with dissimilar theoretical foundations, may be needed to increase confidence in the ranking of the key inputs.This study conducted a comprehensive evaluation of the effectiveness and efficiency of three SA methods by using the HBV and TOPMODEL models as test problem. The strengths and limitations of qualitative and quantitative SA methods are explored.For the Sobol method, a comparatively large number of simulations (>20 000) were required to sufficiently cover the parameter space. Hence, performing Sobol method for complex models is often becoming problematic. The Morris method, instead, is computationally cheap and needed only

In all stations the least amount of P was related to seasonal Mann-Kendall method that series data has autocorrelation. The stations have first-order correlation MK-PW method have highest amount of P. TFPW method has shown different behavior because of calculating the autocorrelation after removing trend. Comparisons of methods showed MK-VC, MK-BB and HERISH methods better than others and able to reduce the probability of first error. To further trend study and relationship between climate and hydrological parameters, rainfall and river flow in Nodehkhandooz station was studied using MASH approach in different months. The results showed that river flow has decreasing trend in the months when withdrawal of river is high. Most of climatic and hydrological data has autocorrelation, which makes Kendall method detect trend the series data without trend. In this study the effect of different removal aoutocorrelation methods were studied in Kendall trend detection of rainfall and runoff in 4 hydrometric stations in Golestan province. The methods used to remove the autocorrelation was MK, MK-PW, TFPW, MK-VC, MK-BB, SEAS and HERISH. The results showed that rainfall in Nodehkhormaloo station and river flow in Ghazaghly and Gholitapeh stations have significant increasing and decreasing trend respectively.

Watershed structures are among of expensive projects that are constructed to decrease erosion and sediment load and decreasing flood in watershed. Constructing any structures in flood bed can change the flood behavior. This research tries to study check dam effects on flood and water way properties in Gorgandooz watershed. For this goal, HEC-RAS model is used to simulate hydraulic in 4 Scenarios: without structure, 20 structures with 1.5, 10 structures with 3 and 8 structure with 3.75 meter for comparing of specified plan effects with each other. The results of this research show that the influence of 1.5, 3 and 3.75 meter check dam on pick flow comparing with structure was not created on the upstream of the watershed is 0, in the middle 1 and at the downstream is 2.49, 8.8 and 17.5% respectively. Also the effect of 1.5, 3 and 3.75 meter structure on decreasing of flood volume in respect of without structure is 1.16, 8.1, 13.9, respectively. The study of flow velocity shows that the construction of higher structure cause that the flow velocity decrease that shows the power of flow erosion in water way become less. Shear stress parameter that shown friction rate between flow and water way confirm the velocity results and show that shear stress decrease with increasing of structure height. The multiplying of shear stress on speed is another important parameter that is studied. This parameter shows the sediment transport power of flow. This parameter indicates the strength of sediment transport by flow that showed strength of sediment transport is less in higher structural. Not only reduce of sediment transport will cause less damage to the waterway but also sedimentation into check dam was occur soon and sediment balancing gradient is reached. As whole various Scenarios of check dam shows that the influence of structure on flood and water way become more by increasing of structure height and cause that the condition in deal with flood become well.

When a stream is partially obstructed by a bridge pier, the flow pattern around the pier is significantly changed. Changes in flow pattern are the cause scour around piers. Bridge pier scouring estimates, is an important parameter in the design of bridges because inattention to it may cause damage or reduce the life of the bridge [1-4]. The safe and economical design of bridge piers requires accurate prediction of the maximum scour depth around their foundations [5].
Mathematical Principles of SVM is based Russian mathematician researches [6]. Ghazanfari Hashemi and Etemad Shahidi had predicted bridge pier scour using SVM method in a laboratory model. They showed that this method is more accurate than empirical relationship. Although extensive studies have been conducted on the pier scour, but a valid relationship does not exist that gives satisfactory results in different conditions [5].
Bates and Granger is one of the first research works in the field of hybrid approach [7]. Shamseldin et al. was used combination methods such as simple average, weighted average and neural network to predict floods [8].
Studying literature reveals that there is a lack of reliable formulas for prediction of the scour depth to cover different condition. The aim of this study is combination of the various pier scour relationships to predict the scour depth using conventional and intelligent (SVM) methods and combination of effective parameters of this phenomenon.

When watershed input, evatransporation and ground water usage be limitated, recession curve showed storage–output relationship for basin. This relationship can help us in low flow forecasting, decision and management of water resources; hydrological models calibration and etc. In this study recession curve were modelled in Taleghan, Jajrod and Khoramdare rivers. At the first by consideration of annul hydrographs, recession lamb were separated then by doing some pre-processing recession curve get prepared for fitting various models. For each recession eight models were fitted. Result showed that for Jajrod and Talaghan, Barnes, Drogue, Coutagne and Wittenberg had better application, respectively. For Khoramdare river Horton, Barnes and Drogue had better performance with compared to others models. For Barnes model average value of K coefficient for Jajrod 0.97, 0.975 and 0.99, for Taleghan 0.967, 0.974 and 0.987 and for Khoramdare river 0.931, 0.945, 0.972 were obtained.

Estimating of bridge piers scouring is essential for engineers. Since many empirical formulas to predict the scour depth is presented and this formula used various dimensionless and dimensional parameters. In this study, two series dimensional and dimensionless parameters that are expected to be effective on pier scour were selected. Then, parameters affecting the scour were selected using three different gamma test (GT), principal component analysis (PCA) and stepwise regression (FS). Findings indicated that using GT critical velocity and pier length to width ratio are most important dimensional and dimensionless parameters respectively and pier shape is less effective. Furthermore, 360 amounts of training data are required to ensure robust model estimation. Finally, we examine the use of support vector machines (SVMs) for estimating the scour depth using selected input parameters by three methods. The results showed that the accuracy of dimensionless parameters set by all three methods is low, but SVM technique was estimate the scour depth using dimensional parameters successfully. The coefficient of determination of the GT, PCA and FS parameters in test phase is 0.76, 0.69 and 0.73 respectively and RMSE is 0.63, 0.55 and 0.50 respectively. In this study, in order to increase accuracy, two different combinations of input parameters to estimate the scour depths were determined. The performances of SVM and empirical formula for scour depth prediction were compared and results showed that SVM model can be used for predicting scour depth more accurately compared to empirical formula using dimensional parameters.

Accurate forecasting of streamflows has been one of the most important issues as it plays a key role in allotment of water resources. River flow simulations to determine the future river flows are important and practical. Given the importance of flow in the coming years, in this research three stations: Haji Qooshan, Ghare Shoor and Tamar in Gorganrood cachment were simulated in 2002-2011. To simulate river flow, time series (Auto Regression) and data driven based on support vector machine (SVM) was used for both monthly and weekly. The results showed that both methods in Tamar have low precision and Haji Qooshan station have good precision in monthly simulation. SVM increase 0.29 coefficient determination and decreases 0.35 RMSE error in Ghare Shoor station and perform more accurate than time series. Both methods simulate weekly discharge in low precision in Tamar and Ghare Shoor. Coefficient determination of time series is 0.91 and SVM is 0.86 in weekly simulation. DDR statistics show that the SVM has greater precision than time series in monthly simulation and equal precision in weekly simulation in Haji Qooshan station. The results of this study show that the SVM method is more accurate than time series in monthly and weekly simulation. The accuracy of both methods is on monthly basis rather than weekly. The accuracy of both methods is greater on monthly rather than weekly.

In lateral intakes a portion of stream flow which enters the intake is divided from the upstream of the intake and is called stream tube. Past researchers have proved that the amount of flow and sediment discharge entering the intake as well as design of submerged vane to control sediment depends on determination of stream tube dimensions. In this study experimental and numerical investigation of the flow patterns at a 90° open-channel diversion is presented. In the experimental tests three components of velocity data obtained for different flow conditions. Then numerical SSIIM 2 model was calibrated and verified using tests data. More flow conditions were run using SSIIM 2 model to get enough hydraulic data. From analysis of these data it was found that the dividing stream tube dimensions depends upon directly to the ratio of diversion flow discharge to the main flow discharge. The strength of a secondary circulation was found to vary with inverse value of the main channel Froude number. Relations for predicting the stream tube dimensions and the strength of secondary circulations have been presented in this paper.