جستجوی مقالات مرتبط با کلیدواژه "الگوریتم ژنتیک" در نشریات گروه "آبخیزداری، بیابان، محیط زیست، مرتع"

One of the methods for estimating the amount of runoff resulting from precipitation is the use of hydrological models. The SWAT model is one of the widely used tools for simulating the quantity and quality of water at the watershed level. This model is a conceptual model that is capable of simulating large watersheds with different management scenarios. One of the major challenges of this model and many other hydrological models is the calibration of effective and sensitive parameters for estimating the amount of runoff. In general, calibration methods can be divided into two groups: manual and automatic. Manual calibration of a model requires the modeler to have a good understanding of the model's physics. On the other hand, due to the time-consuming nature, existing complexities and the development of new optimization algorithms, nowadays automatic calibration has gained more attention. Automatic calibration is based on three components: the objective function, the optimization algorithm, and the station information. The use of a single objective function in model calibration may lead to an increase in error in other aspects of the simulation. Scientific experience in single-objective calibration has shown that no single objective function, even with high efficiency, can accurately represent all the characteristics and properties of a watershed. Therefore, the use of an appropriate optimization algorithm to improve calibration results includes the use of multiple objective functions to identify a set of efficient solutions.

The study area is located in the western part of Iran, in Kermanshah Province, with an area of 5467 square kilometers. The minimum and maximum elevations in the area are 1275 and 3360 meters, respectively. The average precipitation in the watershed is about 505 mm, with the highest rainfall occurring in the months of November and Decemeber, and the lowest rainfall in the months of Julay and August. The main rivers in this watershed are Mark, Gharehsoo, and Razavar. In this study, the SWAT rainfall-runoff model was calibrated using the NSGA-II algorithm under three calibration scenarios. For model calibration, the first scenario used the NSE objective function, which focuses on maximum flows. In the second scenario, to focus on minimum flows, the logarithmic transformation of the simulated and observed streamflow series was used, and the NSE efficiency coefficient was adopted as the objective function, represented as LogNSE. The third scenario was a combination of the first and second scenarios, where the non-concordant objective functions NSE and LogNSE were used simultaneously.

The results of this study showed that based on the NSE evaluation index values (0.83, 0.74 and 0.83 for the first to third scenarios) and the model overestimation and examination of the flow graph in the first scenario, which showed a tendency towards higher flows, this scenario would be more efficient in estimating maximum flows. Additionally, considering the LogNSE evaluation index (0.69, 0.74 and 0.72 for the first to third scenarios), the second scenario with the LogNSE single objective performed better in minimum flows. However, the model constructed using two non-concordant objective functions aimed to achieve a balance and showed satisfactory performance in simultaneously estimating maximum and minimum flows.

In general, it can be concluded that if the objective of the study is to investigate maximum and minimum flows, such as flood or drought studies, single-objective algorithms will perform better. However, if the objective is to control the water balance and achieve satisfactory performance of a model in both maximum and minimum flows, a two-objective scenario with a non-concordant approach can yield better results compared to single-objective algorithms.

Excessive exploitation of groundwater in Damghan plain has caused many problems such as land subsidence in the study area, along with the reduction of the groundwater level and the loss of a part of the aquifer and the reduction of the specific yield of aquifer. Therefore, in order to control the withdrawal from the aquifer and as a result to reduce the drop in the groundwater level in that plain, it was investigated. For this purpose, in this research, the mathematical modeling of Damghan Plain was done for the optimal management of exploitation and providing the optimal cultivation pattern in order to save water consumption with the focus on controlling the groundwater level and limiting land subsidence.

In this research, Damghan plain aquifer was first simulated using MODFLOW mathematical model. Then, taking into account different scenarios of aquifer exploitation, using the NSGAII genetic algorithm, optimization of multi-objective exploitation of water resources and optimal management of water supply and demand in the agricultural sector was done. The results of the model were evaluated based on statistical error parameters to predict the ground water level.

The results of this research showed that the MODFLOW numerical model was able to simulate the groundwater level of the studied plain well in steady and unsteady conditions in the calibration and validation stages. Also, the results of the simulation-optimization algorithm showed that by changing the cultivation pattern and also by changing the type of irrigation system from traditional to modern irrigation and as a result of increasing the irrigation efficiency (90 percent), the average drop of the groundwater level of the plain can be reduced. It reduced the groundwater level of the study area from 0.49 m in existing conditions to 0.07 m in optimal conditions. This will compensate the deficit of the aquifer from 31.90 to 5.1 million cubic meters per year.

Using management strategies such as changing the cultivation pattern, increasing irrigation efficiency, and also by controlling surface water and injecting it into groundwater, the process of reducing the groundwater level in the studied plain can be completely controlled and provided 100% of the water needs of the plain.

One of the landscape management approaches is the construction of bridges along the rivers. On the other hand, the bridge scouring is a serious damage to river engineering as the main source of water and sustaining planet life. Accordingly, in this research, using field data, the accuracy of empirical methods, genetic algorithm (GA), least squares support vector machine (LSSVM), and combined method were compared in estimating scour depth of simple bridge piers. In the GA method, a number of empirical relationships were modified and the results of these modified relationships were compared with the measured scour values. In the LSSVM method, through the input of different independent parameters, model training was performed, and scour depth was predicted. In the combined method, using the LSSVM model from combining the results of different individual relations, the scour depth of the bridge piers was estimated. The results showed that modified relationships by genetic algorithm and LSSVM model have higher accuracy than empirical methods. Also, if only the parameters used in the empirical relationships are included as input parameters to the LSSVM model, the modified relationships have less error than the LSSVM model. The statistical evaluation criteria of RMSE, E, R2, and NSE for the best state of the combined method were 0.4 m, 49%, 0.88, and 0.58 respectively in the training stage and 0.52 m, 50%, 0.7, and 0.38 respectively in the test stage. In general, the combined method estimates scouring depth with higher accuracy than other methods.

Due to the growing development of meta-models and their combination with optimization algorithms for modeling and predicting meteorological variables, in this research four metaheuristic optimization algorithms of Particle Swarm Optimization (PSO), Genetics Algorithms (GA), Ant Colony Optimization for Continuous Domains (ACOR) and Differential Evolutionary (DE) were combined with the adaptive neural-fuzzy inference system (ANFIS) model. The performance of four combined models developed with ANFIS model to predict the Frequency variables of Dust Stormy Days (FDSD) on a seasonal scale in Khuzestan province in the southwest of Iran was evaluated. For this purpose, hourly dust data and codes of the Word Meteorological Organization were used on a seasonal scale with a statistical period of 40 years (1980-2019) in seven synoptic stations of Khuzestan province. The results of good fit indices in the training and testing phase showed that there is no significant difference between the ANFIS method and other combined models used. R and RMSE values of the best combined model (ANFIS-PSO) from 0.88 to 0.97 and 0.10 to 0.19, respectively, and in the ANFIS model from 0.83 to 0.94 and 0.11 to 21, respectively, were variable. The results also showed that the combination of optimization algorithms used with the ANFIS model does not significantly improve the results of the model compared to the individual ANFIS model.

Abstract In dry and semi-arid areas, water is the most factor of limiter in agriculture. In these areas, due to the lack of surface flows, major pressures enter on groundwater. Groundwater resources in the studied area (Dashte-Abbas plain) also suffered a severe drop in surface water due to unplanned use. In this study, we compared four different models of evolutionary neural network, a multi-layered perceptron neural network with Genetic Algorithm (ANN-GA), a multilayered perceptron neural network with particle swarm optimization (ANN-PSO), a multilevel perceptron neural network with Imperialism competitive algorithm (ANN-ICA) and multi-layered perceptron neural network with ant colony optimization (ANN-ACOR) for estimating groundwater level according to groundwater inflow, effective penetration of rainfall, effective penetration of surface flow and flood, effective penetration of return water Agriculture, underground outflow, withdrawal from aquifer for agriculture, evaporation from groundwater level and past groundwater data Were used. groundwater level comparisons are the combination of inputs has been prepared using Auto-correlation analysis, partial Auto-correlation and cross-correlation for each model. Optimal models are obtained by changing the control parameters. The best results are obtained from the input models (GWLt-1, GWLt-2, Qint, Qpt-1, Qrt-1, Qit-1, Qoutt-1, Qwt-1, and Qet-1). The accuracy of the mean squared error in the test phase for ANN-PSO, ANN-ICA, ANN-ACOR models was 1.2208, 0.9456 and 1.7720, respectively, and for the ANN-GA model, it was 0.8739. The mean relative error of ANN-GA model is 3.6% and its determined coefficient is 0.9388. According to the results, the ANN-GA model showed better performance than the other three models for estimating groundwater level.

  Groundwater is one of the main sources of drinking water, agriculture and industry. It is worth noting that groundwater is considered as reserve resources in some areas, while in other areas it may be used for supplying potable water due to their availability (Daliakopoulos et al., 2005; Nayak et al., 2006). Groundwater analysis is an essential factor in maintaining its access. Modeling and predicting the groundwater level for environmental protection, maintaining the balance of the groundwater system, controlling changes in groundwater levels and protecting the escalation of land subsidence are important. Groundwater management techniques and solutions, and control measurements by researchers and operators to address the long-term problems of land subsidence and groundwater conservation (Affandi and Watanabe 2007; Mohanty et al., 2015). The main aim of this study is to evaluate the accuracy of evolutionary neural network models in the monthly groundwater level estimation. In this study groundwater level, precipitation, evaporation, annual average temperature and effective influence between 1993 and 2016 were used. The purpose of this study is applying neural networks to estimate the groundwater level. To use the neural network, we must optimize the weights and biases of the network. In this research, weights and network biases were obtained using optimization algorithms such as genetic algorithm, particle swarm algorithm, Imperialist Competitive algorithm and ant colony algorithm. Different control parameters have been used for models, and they are compared with each other based on the mean square error and the coefficient of determination. All four models showed the best accuracy for input combinations. Comparison of the results shows that the ANN-GA model has a better performance than the other three models for groundwater level estimation. The advantages of GA are: 1) The nature of the random search of this algorithm in the problem space is in some way a parallel search. Because each of the random-generated chromosomes generated by the algorithm is considered as a new starting point to search for part of the problem-space and searches in all of them simultaneously. 2) Due to the breadth and dispersion of the points to be searched, it yields a satisfactory result in issues of great search space. 3) A kind of random search is targeted and will come from different paths to different answers. In addition, there is no limit to the search and selection of random answers. 4) Because of the competition, the answers and the selection of the best among the population, with a high probability, will reach the optimal level. 5) Its implementation is simple and does not require complex problem-solving procedures. It can be said that this algorithm may be a good candidate for hydrological modeling. Investigating the trend of groundwater level changes in the plain over a period of 22 years shows that from 1993 to 2006, due to excessive withdrawal and droughts, the level of stagnation with a steep slope has fallen. Since then, with the arrival of the water of the Karkheh Dam and the reduction of withdrawal, the groundwater level of the plain table has risen and reaches 14 meters in 2015. Most commonly used methods for training neural networks from descending gradients using back propagation are to calculate real gradients. In recent years, some researchers have developed evolutionary techniques for estimating groundwater level changes, including genetic algorithms (Dash et al. 2010, Jalakamali and Jalakamali 2011), Imperialist competition algorithm (Tahershamsi and Sheikholeslami 2011), particle swarm optimization (Xi et al. 2012, Gaur et al. 2013) and comparing these methods with each other (Kisi et al., 2017). In addition to the above-mentioned models, the ANN-ACOR model was also used. Comparison of the results shows that the ANN-GA model has a better performance than the other three models for estimating groundwater level, which contradicts the results of (Xi, 2012) and (Gaur, 2013), and matches with the research (Jalalkamali, 2011) and (Dash, 2010).

Area-volume-elevation (AVE) curves of dams pose one of the most important tools for water resource planning and reservoir management. Area reduction method is one of the methods which was developed to modify these curves after reservoir sedimentation based on the conditions, statistics and information recorded in reservoirs abroad; however the application of the same methods for domestic dams without optimizing the coefficients is not bug-free, and associates sometimes with a great deal of error. This study aims to calibrate automatically the area reduction method based on its three influencing parameters using two genetic and particle swarm optimization algorithms and to compare the results with reservoir hydrographic studies. So that, predicting the trend of reservoir sedimentation in area reduction method with its hydrographic results at the end of the period has the least difference. Results indicate the excellence of particle swarm algorithm in calibrating the area reduction method. In this algorithm, by selecting the initial population of 50, the time of convergence and the value of the objective function (RMSE of the predicted volume-elevation curve and actual reservoir) in the last iteration was 4.7 minutes and 7 MCM, which it represents 92.6% and 48% improvement, respectively compared with the genetic algorithm. Finally, the optimal values of area reduction method parameters were used to match further the estimated and actual volume values of Dez dam reservoir. The results revealed that the predicted error value is less than 1%, which is assessed negligible according to the volume of the reservoir. Accordingly, the developed model can be employed without any change in the optimal parameters of the area reduction method by entering information of reservoir’s new hydrography to predict the sedimentation trend during the coming years. This will be very helpful in light of the importance of knowing the reservoir’s useful volume variation in the coming years and its role in future water resource planning.

The rivers sediment load is determined using hydrologic methods. In the statistical methods, by measuring the rivers discharge and suspended sediment load in a long-term period, the relationships between the suspended sediment load and discharge is obtained. The aim of this study is to compare different estimation methods of suspended load and select the most appropriate relationship for the prediction of suspended sediment load which results in more accurate prediction of sediment load discharge in the studied rivers. In this research, by using the daily river flow rate and corresponding suspended sediment discharge in four hydrometric stations in West Azerbaijan, the rating curve power equation for the middle limit of the data was used. The optimum coefficients of the mentioned equation ware obtained by using genetic algorithm (GA) and the ordinary regression, and the necessary programs ware written in Matlab® software. Since GA does not require any restrictive assumptions on input data, so it showed better performance in real data validation phase. This improvement in the rating curve coefficients causes to decrease up to 25 percent Root Mean Squared Error (RMSE). Therefore using GA as an appropriate tool was proposed to estimate the sediment rating curve for the studied stations.

Sedimentation on the rivers beds causes many difficulties not only for an orderly and sustainable flow of water, but also by altering the river's hydraulics, which in certain cases drastically changes the flow direction by opening new channels that inundate farm fields, municipalities and infrastructures. As various models developed for the suspended load (SL) estimation are often site specific, therefore, it is prudent to test and calibrate them for the intended river. As the Hirmand River is the lifeblood of Sistan, therefore, the 70 km terminal reach, the Sistan River, was selected for this project. The monthly and seasonally discharge of the river and its SL contents for the period 1970–2015 were analyzed statistically using six models, namely: linear, double-linear, mean value, FAO, parametric factor and non-linear. As the determination of the break point is very important in the application of the double linear method, the genetic optimization algorithm was used in this process.Two criteria for choosing the correct method for estimation of the SL were used: relative mean error and root mean square error. It is concluded that the double linear method proposed in this research gives the best result in all forms without any delineation, seasonal and monthly classification with the relative mean error of 154.46, 142.7 and 116.15, respectively. Monthly classification of data increased accuracy and reduced the root mean square error in the Sistan River

Fast and accurate estimation in Peak flow is one of the major issues in water resources management that have basic role in the design of hydraulic structures and biological activities in drainage basins. So that a proper assessment has a basic role in the success of administrative tasks. In this paper, using artificial intelligence methods (Multi-layer Perceptron Neural Network and the mixture of Multi-layer Perceptron Neural Network with genetic algorithm) to estimate yalfan river, s peak discharge in Yalfan,s sediment and hydrometer local gaging station. For these two models, 8 variables have been considered as the inputs that includes rainfall related to day of peak flow,5 days rainfall that occurs before of the flooding day, curve number of the basin(CN) and base discharge and finally peak discharge is considered as the output. With artificial intelligence after preprocessing of the data, the optimal structure of the model is determined with input and output data by evaluation criteria and trial and error. In the final, with the mixture of artificial network and genetic algorithm model, the optimum neural network model was determined which results were an input to genetic algorithm model, this has been a good performance in runoff forecasting in Yalfan Basin.

Watershed management practices (WMPs) include methods to create, enhance, and maintain vegetation to reduce surface runoff in the watershed. The implementation of WMPs at the watershed scale is an ongoing challenge that needs to take into account trade-offs between hydrological and economic objectives using optimization algorithm. This research demonstrate a methodology and decision support tool that suggests the optimal location of biological watershed management practices (including improvement rangeland cover) which minimize the cost and simultaneously reduce surface runoff to target levels cases (i.e. 10%, 15%, 20% and, 25%) at watershed scale. The decision support tool (SWAT-GA) consists of a semi-distributed hydrologic model, Soil and Water Assessment Tool (SWAT) which simulation of runoff in watershed, a genetic algorithm (GA), which serves as the optimization engine for the location of biological watershed management practices across the rangeland of the watershed. The proposed method was then applied to Taleghan watershed with an approximate area of 900 km2 that located in Alborz Mountain, Iran. Results indicate watershed management practices should use in 22%, 35%, 48% and 62% of total area of watershed to reduction 10%, 15%, 20% and 25%, respectively. The maximum decrease and increase runoff after the implementation of WMPs have been occurring in the spring and summer, respectively. Using this decision support tool, for each level of target goals, decision makers can select the optimal combination of watershed management practices.

Soil hydraulic properties have key role in sugar cane cultivation management. The purpose of this study is to estimate soil moisture characteristic curve using an artificial neural network and its optimization with genetic algorithm. Therefore, based on the cultivation operations management and soil properties included: organic matter content, soil texture, electrical conductivity, sodium adsorption ratio, 4 land unit tracts in Debel-Khozaii, Amir-Kabir, Karoon and Haft-Tapeh agro-industries were selected. A total of 310 soil samples from both 0-40 and 40-80 cm of soil profiles were collected. In this study, five models were arranged in hierarchy to estimate soil hydraulic properties with ANNs. The performances of the models were evaluated using Spearman's correlation coefficient (r) between the observed and the estimated values, normalized mean square error (NMSE), and mean absolute error (MAE). Owing to the fact that the selection of each of the variable parameters of neural network necessitated recurring trails and errors, and consequently teaching a large number of networks with various topologies, genetic algorithm method was utilized for finding the optimization of these parameters and the efficiency of this method was examined in terms of the optimization of neural network. Results showed that the neural network has a high degree of accuracy in modeling and estimating soil moisture characteristic curve (R =0.943, MAE=0.019, NMSE=0.054). Also, combining artificial neural networks with genetic algorithm for optimizing the conditions of the artificial neural networks implementation was positive and combining approach indicated its superiority over non-optimized implementation of artificial neural networks in all cases (R=0.985, MAE=0.01, NMSE =0.0151).

Well designed monitoring networks are essential for the effective management of groundwater resources but the costs of monitoring well installations and sampling can prove prohibitive. The challenge is to obtain adequate water quality and quantity information with a minimum number of wells and sampling points, a task that can be approached objectively and effectively using numerical optimization methods. Unfortunately, aquifer systems tend to be complex and monitoring can be very expensive, particularly when it requires the installation of a dedicated network of monitoring wells. In recent years, the challenge has been to design monitoring networks that are both efficient and cost effective. With regards to groundwater monitoring systems, where the challenge is to maximize the availability of good quality data while minimizing the number of sampling sites and thereby limiting costs, optimization techniques clearly have a potentially valuable application. In this paper we use a site in northern Iran to test the ability of GA, when used in combination with Kriging, in comparison with PSO to lower the cost of a monitoring network by reducing the number of monitoring wells without compromising the quality of the interpolated data. The results of the optimization showed that the number of observation wells in the Astaneh aquifer monitoring network could be reduced by 26% from 57 to 42 without a significant loss of information. The root mean square error (RMSE) for the final optimized network in GA was 0.2025 m, that in PSO 0.3222 m. A comparison of RMSE values determined using the GA algorithm with those calculated using PSO algorithm technique showed good agreement and provides strong support for more efficient GA approach.

Sediment fingerprinting is a method for identifying sediment sources and determining the rate of contribution of each source. In this method, the natural tracer technology is used, that combined from samples collection, laboratory analyzing and statistical modeling. The natural tracers are measured in both the sources and suspended sediment to determine the rate of contribution each sources. The suspended sediment traps were constructed and used for the first time in country. In this research sediment fingerprinting was used in the loess area. 27 tracers were measured in all samples. Data were evaluated about outlier. The capability of each tracer in separating the sources was evaluated with kruskal-wallis test. All tracers were accepted. Then the best combination of tracers was determined with discriminate analysis. This combination is total carbon, Na, organic carbon, Pb, Co, Sr, Al, C/N and Rb. Then, the rate of contribution of each source was determined with normal method and optimized method. Among all the sediment sources, Gully and forest have the highest and lowest rates, respectively. The field observations were confirmed the results. The use of genetic algorithm increased the accuracy of determination of contribution of each source in comparison to normal method.

Soil hydraulic properties have key role in sugar cane cultivation management. The purpose of this study is to estimate soil moisture characteristic curve using an artificial neural network and its optimization with genetic algorithm. Therefore, based on the cultivation operations management and soil properties included: organic matter content, soil texture, electrical conductivity, sodium adsorption ratio, 4 land unit tracts in Debel-Khozaii, Amir-Kabir, Karoon and Haft-Tapeh agro-industries were selected. A total of 310 soil samples from both 0-40 and 40-80 cm of soil profiles were collected. In this study, five models were arranged in hierarchy to estimate soil hydraulic properties with ANNs. The performances of the models were evaluated using Spearman's correlation coefficient (r) between the observed and the estimated values, normalized mean square error (NMSE), and mean absolute error (MAE). Owing to the fact that the selection of each of the variable parameters of neural network necessitated recurring trails and errors, and consequently teaching a large number of networks with various topologies, genetic algorithm method was utilized for finding the optimization of these parameters and the efficiency of this method was examined in terms of the optimization of neural network. Results showed that the neural network has a high degree of accuracy in modeling and estimating soil moisture characteristic curve (R =0.943, MAE=0.019, NMSE=0.054). Also, combining artificial neural networks with genetic algorithm for optimizing the conditions of the artificial neural networks implementation was positive and combining approach indicated its superiority over non-optimized implementation of artificial neural networks in all cases (R=0.985, MAE=0.01, NMSE =0.0151).

In the management water resources science, optimal Operation of existing water systems, such as dams, every day is more important. Due to budget and operational water resources limitations and environmental problems, optimize operation of these systems are gradually replaced by new systems are constructed. Optimal Operation of water resources is a Complex, nonlinear, multi-constraint and multidimensional optimization Problem, so to solve them robust optimization techniques needs are needed. In this study Genetic Algorithm optimization has been used in operation of the Mahabad reservoir Dam in Northwest of Iran. The objective function is minimization of difference between downstream monthly demand and release. Early; Sensitivity analysis of GA model performed by considering of various parameters. Then the method was applied considering the reduce probability of inflow to dam for period 24months in the different scenarios. The results show that, the critical condition of drought could managed by the GA model, the optimized model could satisfy downstream watery demand.

The appropriate use of a conceptual rainfall-runoff model depends on how well its parameters are calibrated. Generally, rainfall-runoff models deal with numerous parameters that cannot be measured directly and should be estimated through optimization tools. The purpose of the optimization approach is to finalize the best set of parameters associated with a given calibration data set that optimize the evaluation criteria. In this paper, a continuous genetic algorithm calibration method has been used to estimate the NASH conceptual model parameters (n, k).The efficiency of the method was evaluated using the estimated parameters to simulate different rainfall - runoff events that happened in the Kasilian watershed in Mazandaran province during previous years. The calibration and validation results have shown that the suitability and efficiency of this model for auto calibrating of Nash conceptual rainfall-runoff model is more accurate and favorable.

In order to reduce sediment and soil conservation plan generation، the design and calculation of the exact size of the dam at dams، evaluation and estimation of sediment yield in the watershed of the dam، is essential. In general erosion and sediment transport of the most complex issues that determine the exact hydrodynamic equations for the various variables، it is not easy. The aim of this study was to simulate suspended sediment load using a neural-fuzzy model is combined This is necessary for the various input combinations using stepwise regression، genetic algorithm model and gamma test and then determine the most suitable model for the input. Karaj Dam Sierra station data in the period 1974-2011 (37 years) was used so that the 15 variables as input and output variables as was considered. Results indicated neuro-fuzzy models in a suitable combination of the number of training data to select the most appropriate modeling of the genetic algorithm to be achieved. It should be noted that in the case of all input variables، modeling neuro-fuzzy model was not appropriate Therefore، methods are necessary to determine the appropriate combination of inputs. Finally، the Genetic Algorithm model as the most appropriate method and stepwise regression، second، and third order gamma test as appropriate methods to determine combination of neuro-fuzzy model inputs selected. The neuro-fuzzy model when using a selected combination of genetic algorithms to simulate suspended sediment load 99/0 correlation coefficient and the mean square error as the most appropriate modeling 0000009/0 has been selected.

In the past decades، much effort has been devoted to simulation of the rainfall-runoff process. Hydrological models are simplified representations of the natural hydrologic system. In each case، the choice of the model to be applied depends mainly on the objective of the modeling but also on the available information. The relative performances of two lumped conceptual-based hydrology models (Tank and SYMHYD) were compared based on daily data of Chehel_Chay catchment in the northeast region of Golestan province. As in Tank and SIMHYD models، parameter spaces are high dimensional، it is difficult to obtain optimal parameters using manual trial and error procedure. These parameters need to be estimated through an inverse method by calibration. Therefore، an automatic optimization procedure based on the Genetic Algorithm (GA) was tested for parameter calibration of two models. For testing the applicability of the model in gauged basin، the model was calibrated for a period of 1992–1996 and validated for a period of 2002–2005. The result showed that RMSE of discharge predictions were as low as 0. 821 for a Nash-Sutcliffe coefficient of 0. 599 for the Tank model، against 0. 819 for a Nash-Sutcliffe coefficient of 0. 602 for the SYMHYD model in calibration period. When evaluating the model performance in validation period، SYMHYD model is performing most accurately with RMSE=0. 490 and E=0617. It was found the RMSE for Tank model is 0. 522، which is slightly higher than SIMHYD (RMSE=0. 490). SIMHYD is performing most accurately with E equal to 0. 602 and 0. 607 in calibration and validation periods، respectively.

Annual maximum 24-h rainfall is the meteorological parameters with the more stochastic nature of rainfall in comparison with other related rainfall data، including monthly and annual precipitation data. Considering to unavailable Intensity-Duration-Frequency (IDF) data and more availability of Annual maximum 24-h rainfall data، a common method of estimating short time rainfall in watershed management operation and studies is based on Annual maximum 24-h rainfall data. Sometimes mentioned data is incomplete and use of them causes an error in the results. This research carried out in order to evaluate the performance of artificial neural network with genetic algorithm (GA-ANN) for reconstruction of annual maximum 24-h rainfall data in Chaharmahal va Bakhtiyari province. To evaluate the model RMSE، P%، and R2 were used as statistical indices. The GA-ANN was compared with simple artificial neural networks. The RMSE indices between observed and predicted values by ANN model were 38. 0، 25. 9، 11. 8 and 11. 4 (mm) for very-humid، semi-humid، Mediterranean and semi-arid climate zones، respectively. Considering the results of GA-ANN method، the RMSE were 19. 2، 14. 3، 10. 8 and 6. 4 (mm)، respectively. The results of reconstructed data show that GA-ANN method has significant preference related to ANN method in all the four climates in the studied region.