moslem servati; Hamidreza Momtaz
Abstract
Introduction: Cation Exchange Capacity (CEC) refers to the amount of negative charges available on the soil colloids surface. Clay and organic colloids carry a negative charge on their surfaces. Cations are attracted to the colloids by electrostatic bonds. Therefore, the charge of the soil is zero. For ...
Read More
Introduction: Cation Exchange Capacity (CEC) refers to the amount of negative charges available on the soil colloids surface. Clay and organic colloids carry a negative charge on their surfaces. Cations are attracted to the colloids by electrostatic bonds. Therefore, the charge of the soil is zero. For fertility map planning and commonly indicator of soil condition, CEC is an essential property. CEC is commonly measured on the fine earth fraction (soil particles less than 2 mm in size). CEC could be obtained directly but its measurement is difficult and expensive in the arid and semi-arid regions with high amounts of gypsum and lime. Pedotransfer functions (PTFs) are appropriate tools to estimate CEC from more readily measured properties such as texture, organic carbon, gravel, pH and etc. Regression PTFs, artificial neural networks (ANN), and hybrids technique (HA) could be used to developing pedotransfer functions. The prior research revealed that could provide superior predictive performance when developed ANN model. Furthermore, ANN technique has no comprehensive method to select network learning algorithm and stopping algorithm in the minimum local. Therefore, application of optimization algorithms such as Genetic (GA) and firefly (FA) is necessary. The Purpose of the present study was to evaluate the performance of FA and GA to predict the soil cation exchange capacity by ANN technique based on easily-measured soil properties.
Materials and Methods: 220 soil samples were collected from 39 soil profiles located in Golfaraj (Jolfa) area of East Azarbaijan province. The study site lies from 45° 30ʹ to 45° 53ʹ east longitudes and from 38° 42ʹ to 38° 46ʹ north latitudes. Then, soil samples were air-dried and passed through a 10 mesh sieve for removing gravels and root residues. Soil textural class, organic matter content and CEC were, respectively, determined by hydrometer, Walkley and Black, and bower methods. The artificial neural network (ANN), artificial neural network-Genetic algorithm (ANN-GA) and artificial neural network-Firefly algorithms (ANN-FA) models were applied to predict the soil cation exchange capacity on the basis of the easily-measured soil properties. In ANN-GA and ANN-FA models, soil CEC was estimated via an artificial neural network and were then optimized using a genetic algorithm and firefly algorithm. The Genetic algorithms are commonly used to generate high-quality solutions to be optimized by relying on crossover, mutation and selection operators. The firefly algorithm is modeled by the light attenuation over fireflies’ mutual gravitation, instead of the phenomenon of the fireflies light. The schema of flashes is frequently unique for specific types. The techniques’ results were then compared by four parameter, i.e., correlation coefficient (R2), root mean square errors (RMSE), Nash–Sutcliffe (NES) and Geometric mean error ratio (GMRE).
Results and Discussion: The correlation coefficients of soil characteristic factors with CEC were analyzed through correlation matrix analysis. According to this analysis, the factors which had insignificant influence on the CEC were excluded. The clay, silt, sand and organic matter content were selected as input data. The parameter of the best deployment for MLP network could be used to predict CEC in the studied site. This model comprised 4 neurons (sand, silt, clay percentage and OM) in input layer. The optimum number of neurons in hidden layer was estimated to be 5. Additionally, the most efficient activity function in hidden layer was Axon sigmoid. Results showed that three CEC models performed reasonably well. ANN-FA model had the highest R2 (0.94), lowest RMSE (1.31 Cmol+ Kg-1) and highest Nash–Sutcliffe coefficient (0.53) in training stage and high R2 (0.97), lowest RMSE (1.06 Cmol+ Kg-1) and highest Nash–Sutcliffe coefficient (0.59) in test stage. ANN-GA model had also higher R2 (0.91), lower RMSE (1.77 Cmol+ Kg-1) and higher Nash–Sutcliffe coefficient (0.45) in training stage and higher R2 (0.93), lower RMSE (1.50 Cmol+ Kg-1) and higher Nash–Sutcliffe coefficient (0.48) in test stage indicating good performance of the model as compared with ANN models. The results showed that both ANN and Hybrid algorithm methods performed poorly in extrapolating the minimum and maximum amount of CEC soil properties data. In addition, the comparison of ANN-FA, ANN-GA results with ANN models revealed that ANN-FA was more efficient than the others.
Conclusions: The results of present study illustrated that ANN model can predict CEC with acceptable limits. Therefore, FA and GA algorithms provide superior predictive performance when is combined with ANN model. Firefly algorithm as a new method is utilized to optimize the amount of the weights by minimizing the network error. Final results revealed that this suggested technique improves the modeling performance.
Alireza Moghaddam; Majid Montaseri; Hossein Rezaei
Abstract
Introduction: The reservoir operation is a multi-objective optimization problem with large-scale which consider reliability and the needs of hydrology, energy, agriculture and the environment. There were not the any algorithms with this ability which consider all the above-mentioned demands until now. ...
Read More
Introduction: The reservoir operation is a multi-objective optimization problem with large-scale which consider reliability and the needs of hydrology, energy, agriculture and the environment. There were not the any algorithms with this ability which consider all the above-mentioned demands until now. Almost the existing algorithms usually solve a simple form of the problem for their limitations. In the recent decay the application of meta-heuristic algorithms were introduced into the water resources problem to overcome on some complexity, such as non-linear, non-convex and description of these problems which limited the mathematical optimization methods. In this paper presented a Simple Modified Particle Swarm Optimization Algorithm (SMPSO) with applying a new factor in Particle Swarm Optimization (PSO) algorithm. Then a new suggested hybrid method which called HGAPSO developed based on combining with Genetic algorithm (GA). In the end, the performance of GA, MPSO and HGAPSO algorithms on the reservoir operation problem is investigated with considering water supplying as objective function in a period of 60 months according to inflow data.
Materials and Methods: The GA is one of the newer programming methods which use of the theory of evolution and survival in biology and genetics principles. GA has been developed as an effective method in optimization problems which doesn’t have the limitation of classical methods. The SMPSO algorithm is the member of swarm intelligence methods that a solution is a population of birds which know as a particle. In this collection, the birds have the individual artificial intelligence and develop the social behavior and their coordinate movement toward a specific destination. The goal of this process is the communication between individual intelligence with social interaction. The new modify factor in SMPSO makes to improve the speed of convergence in optimal answer. The HGAPSO is a suggested combination of GA and SMPSO to remove the limitation of GA and SMPSO. In this paper the initial population which caused randomly in all metha-heuristic algorithms consider fixing for the three mentioned algorithms because the elimination of random effect in initial population may make increase or decrease the convergence speed. The objective function is the minimum sum of the difference between the downstream demand reservoir and system release in the period time. Also the constrains problem is continuity equation, minimum and maximum of reservoir storage and system release.
Results and Discussion: The performance of GA, SMPSO and HGAPSO evaluated based on the objective function for Dez reservoir in the south east of Iran. In this study the programming of GA, SMPSO and HGAPSO was written in Matlab software and then was run for the time period with a maximum of 400 iterations. The minimum of the objective function for GA, SMPSO and HGAPSO was obtained 1.19, 1.05 and 0.9 respectively, and the maximum of objective function was calculated 1.66, 1.26 and 1.10 respectively. The results showed that the minimum of the objective function by HGAPSO was estimated 32 and 16 percent lower than the counts which calculated by GA and SMPSO. The standard deviation of SMPSO and HGAPSO were near to each other and less than GA which shows the diversity between solutions for SMPSO and HGAPSO are much less than GA. Also the HGAPSO had the better performance rather than previous method in terms of minimum, maximum, average and standard deviation. The convergence speed of HGAPSO for finding the optimal solution is much faster of GA and SMPSO. The difference graphs between system release and monthly demand in HGAPSO is much less than GA and SMPSO. Also the storage calculated in HGAPSO and SMPSO is highly close to each other but in GA method the storage calculated more in the first and second years.
Conclusions: The convergence speed in finding the optimal solution in SMPSO in more than GA but in other hand the probability of caughting in local optima for SMPSO is great whereas GA can make the diverse optimal solutions. For this reason, in this paper was trying to improve the performance of the GA and SMPSO and remove their disadvantage based on combining them and presenting a new hybrid method. The results showed the HGAPSO method which presented in this paper to use without any complexity and additional operator to GA and SMPSO has the ability to use for reservoir operation with large-scale. In addition it is suggested which the HGAPSO apply to other water resources engineering problems.
