JWSS - Journal of Water and Soil Science

---

In mountainous basins, snow water equivalent is usually used to evaluate water resources related to snow. In this research, based on the observed data, the snow depth and its water equivalent was studied through application of non-linear regression, artificial neural network as well as optimization of network's parameters with genetic algorithm. To this end, the estimated values by artificial neural network, neural network-genetic algorithm combined method and regression method were compared with the observed data. The field measurement were carried out in the Samsami basin in February 2006. Correlation coefficient (r) mean square error (MSE) and mean absolute error (MAE) were used to evaluate efficiency of the various models of artificial neural networks and nonlinear regression models. The results showed that artificial neural network and genetic algorithm combined methods were suitable to estimate snow water equivalent. In general, among the methods used, neural network-genetic algorithm combined method presented the best result (r= 0.84, MSE= 0.041 and MAE= 0.051). Of the parameters considered, elevation from sea level is the most important and effective to estimate snow water equivalent.

---

Estimating spatial distribution of precipitation is vital to execute water resources plans, drought, land-use plans environment, watershed management, and agricultural master plans. High variation in amount of precipitation in various parts, lack of measurement stations, and the complexity of relationship between precipitation and parameters affecting it have doubled the importance of developing efficient methods in estimating spatial distribution of precipitation. Artificial neural network has been proved to be efficient as a new way for modeling and predicting the processes for which no solution and explicit relationship has been available in accurately identifying and describing them. The purpose of this study is to investigate the efficiency of artificial neural network in estimating spatial monthly precipitation. To achieve this objective, neural network with multilayer perceptorn topology was employed for preparing model for spatial monthly precipitation in five synoptic and rain-gauge stations located in Kurdistan province. In order to design the topology of the model in each station, as the adjustable parameters (including transfer function, learning rule, amount of momentum, number of hidden layers, number of neurons of the hidden layers, and the number of epochs) changed, different neural networks were made and carried out. In each case, the topology with the minimum amount of root mean square error (RMSE) was selected as the optimal model. 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 the efficiency of this method, too, was examined in terms of the optimization of neural network. The findings indicated that neural network enjoys a high degree of accuracy in modeling and estimating spatial distribution of monthly precipitation. In addition, combining it with genetic algorithm method was positively evaluated in optimizing the requirements for executing neural network. In most cases, mixed method proved its superiority over executing neural network without optimization. The most precise model in all of the stations under study was achieved by the use of transfer function, sigmoid, learning rule of Levenberg Marquardt in the selected models, the determination coefficient (R2) observed between the model output amounts and the data observed in station were found to be 0.86 0.89 0.94 0.77 and 0.94.

---

The conventional application of nitrogen fertilizers via irrigation is likely to be responsible for the increased nitrate concentration in groundwater of areas dominated by irrigated agriculture. This requires appropriate water and nutrient management to minimize groundwater pollution and to maximize nutrient use efficiency and production. To fulfill these requirements, drip fertigation is an important alternative. Design and operation of drip fertigation system requires understanding of nutrient leaching behavior in cases of shallow rooted crops such as potatoes, which cannot extract nutrient from lower soil depth. This study deals with neuro-fuzzy modeling of nitrate leaching from a potato field under a drip fertigation system. In the first part of the study, a two-dimensional solute transport model (HYDRUS-2D) was used to simulate nitrate leaching from a sandy soil with varying emitter discharge rates and various amounts of fertilizer. The results from the modeling were used to train and validate an adaptive network-based fuzzy inference system (ANFIS) in order to estimate nitrate leaching. Radii of clusters in ANFIS were tuned and optimized by genetic algorithm. Relative mean absolute error percentage (RMAEP) and correlation coefficient (R) between measured and obtained data from HYDRUS were 0.64 and 0.99, respectively. Results showed that ANFIS can accurately predict nitrate leaching in soil. The proposed methodology can be used to reduce the effect of uncertainties in relation to field data.

---

Non-linear Muskingum model is an efficient method for flood routing. However, the efficiency of this method is influenced by three applied parameters. Therefore, efficiency assessment of Imperialist Competition Algorithm (ICA) to evaluate optimum parameters of non-linear Muskingum model was addressed in this study. In addition to ICA, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) were also used to find an available criterion to verify ICA. In this regard, ICA was applied for Wilson flood routing then, routing of two flood events of DoAab Samsami River was investigated. In case of Wilson flood, the target function was considered as the sum of squared deviation (SSQ) of observed and calculated dischargem. Routing two other floods, in addition to SSQ, another target function was also considered as the sum of absolute deviations of observed and calculated discharge. For the first floodwater based on SSQ, GA indicated the best performance however, ICA was in the first place, based on SAD. For the second floodwater, based on both target functions, ICA indicated a better operation. According to the obtained results, it can be said that ICA could be recommended as an appropriate method to evaluate the parameters of Muskingum non-linear model.

---

Nowadays, urbanization is a common process which replaces vegetation cover with impervious areas. This process increases urban stormwater. A new tendency in urban stormwater management endorses ‘source control’, whereby distributed water sensitive urban design systems are built throughout the subdivisions to alleviate the effects of land use changes. Various costs and functions are considered for different urban stormwater treatment measures methods. The present study introduced a legal optimization approach, to minimize the costs of urban stormwater treatment measures. For this purpose, the MUSIC model and Genetic Algorithm were combined in the Matlab environment. The Results of application of MUSIC-GA model, to optimize urban stormwater treatment systems, at 2.8 hectares of industrial areas near Rowzehchay River in Lake Urmia basin, showed that the developed MUSIC-GA model has an efficient performance for finding the optimal urban stormwater control. The results also indicated that the optimized treatment measure in the post development scenario decreased at least 45 percent of pollutants from urban stormwater runoff. Moreover, very small values of coefficient of variation (0.00007) among different results of multiple runs indicated that there was a high convergence between result of MUSIC-GA and the global optimal solution.

---

---