E. Mehrabi Gohari; H.R. Matinfar; Ruhollah Taghizadeh-Mehrjardi; A. Jafari
Abstract
Introduction: Soil texture is the most important environmental variable because it plays a very important role in reducing the quality of land and water transfer processes, soil quality control and fertility. On the one hand, soil texture components are the basis of environmental predictive models and ...
Read More
Introduction: Soil texture is the most important environmental variable because it plays a very important role in reducing the quality of land and water transfer processes, soil quality control and fertility. On the one hand, soil texture components are the basis of environmental predictive models and digital mapping of soil and on the other hand, soils are temporally and spatially variable, thus distinguish zoning and their monitoring with traditional sampling methods and laboratory analysis is very costly and time consuming. As a result, the development of methods for analyzing the soil and for required information has become very important. Visible and near infrared spectroscopy (VIS-NIR) is widely used to estimate soil physical properties and estimate soil texture. The present study aims to predict soil texture using spectral measurements and artificial neural network models and partial least squares regression.
Materials and Methods: The study area in southeastern Iran is approximately 70 km from Kerman. In the study area, based on the hypercube technique, 115 profiles were identified and then horizons were sampled. In this way, for each point of study, the necessary information, including the location of the profile on the ground, the type of geomorphic unit and the type of materiel, were recorded and taken from the horizons of each profile. In all soil samples, after drying and passing through 2 mm soil, the soil texture was measured by hypercube. Spectral radiometer was used to measure the spectral reflection of soil samples. The soil samples were air dried and sieved and then placed in a petri dish with an approximate diameter of 10 cm and transferred to the dark room for spectral analysis. Each specimen was tested four times (for each 90 degree sequential rotation) to remove the effects of a change in the radiation geometry. Soil samples were scanned, and absolute reflections at a spectral range of 2500-350 nm yielded 2150 spectral data points (SDPs) per soil sample with a spectral resolution of one nanometer. Finally, to construct a suitable model for forecasting the percentage of clay, sand, and silt, the least squares model was used with the number of factors 1 to 10 by Artificial Neural Network (ANN) modeling using JMP software Work.
Results and Discussion: The reflectance spectrum of the visible range - near infrared - was measured for specimens. Since preprocessing of spectral data has an effective role in improving the calibration, in order to perform spectral preprocessing, two first nodes of the first and the end of the spectra were first removed in the range of 350-400 and 2450-2500 nm. In addition, the interruption due to the change in the detector in the range of 900 to 1000 nm was also eliminated. Types of preprocessing methods were performed on spectral data. Then, using partial least squares regression analysis, the best model was produced when the first derivative was fitted to reflection values. The explanation coefficients for this low and unacceptable model were obtained. Therefore, using partial least squares regression analysis, the best wavelengths were selected to predict the percentage of clay, sand, soil, and extracted from the model. Then it was used as input in the neural network model. To determine the best combination, root error index and error coefficient were used. The results of artificial neural network showed that the number of neurons 9.8 and 10 had the best composition for predicting clay, sand and soil silt. The root-squared error results for clay, sand, and soil silt were 3.42, 6.94, and 4.383 respectively. Also, the results of the explanatory factor were 0.84, 0.83 and 0.81, respectively. After obtaining the optimal structure in the artificial neural network training phase described above, the trained network has been tested on the test data to determine the accuracy of this model to predict clay, sand and silt of surface soil. The root-squared error results for clay, sand and silt components were obtained at 5.54.9.14 and 7.01. Also, the results of the explanatory factor were 0.76.0.70 and 0.73 respectively. The best result of the prediction for partial least squares regression was obtained for the sand sample. The results indicate that the neural network performance is better than partial least squares regression, which is consistent with Mouazenet. al (2010) and also ViscarraRossel R. et. al (2009). Acceptable performance of the artificial-neural network can be attributed to the ability of this model for non-linear behavior of soil texture in visible spectroscopy. In this study, specific wavelengths, which Ben Finder et al. (2003) obtained in the study on the soils of Israel, were used. This conclusion confirms that various types of soil can be modeled using specific wavelengths. The advantage of this study is that, when using the artificial neural network, no pre-processing of reflection data is required before applying the model. Since the relationship between the percentage of soil particles (clay and gravel) and the reflection of the soil is not linear, the neural network method is very useful for analyzing the relationship between soils. Finally, the map of clay, sand and silt and map of soil texture was prepared by artificial neural network method in GIS environment.
Conclusion: The results of this study showed that the neural-dynamic network has a better performance than partial least squares regression. Calibration models designed and used in this study can be transported for use with other soils. When the partial least squares regression model was implemented, it had a very low accuracy (R2 ~ 0.1-0.3); on the contrary, the neural network-based method had high accuracy and less error. Note that although neural-dynamic modeling estimates higher precision results from soil texture, both approaches depend on wavelength selections, and so wavelengths should be selected before using any of the two models. To be finally, a meaningful relationship between the selected wavelengths and the percentage of clay, sand and silt in the present study indicates that soil texture is not only possible but also reliable by reflection spectroscopy.
F. Ahmadi; S. Ayashm; K. Khalili; J. Behmanesh
Abstract
Introduction Crop evapotranspiration modeling process mainly performs with empirical methods, aerodynamic and energy balance. In these methods, the evapotranspiration is calculated based on the average values of meteorological parameters at different time steps. The linear models didn’t have a good ...
Read More
Introduction Crop evapotranspiration modeling process mainly performs with empirical methods, aerodynamic and energy balance. In these methods, the evapotranspiration is calculated based on the average values of meteorological parameters at different time steps. The linear models didn’t have a good performance in this field due to high variability of evapotranspiration and the researchers have turned to the use of nonlinear and intelligent models. For accurate estimation of this hydrologic variable, it should be spending much time and money to measure many data (19).
Materials and Methods Recently the new hybrid methods have been developed by combining some of methods such as artificial neural networks, fuzzy logic and evolutionary computation, that called Soft Computing and Intelligent Systems. These soft techniques are used in various fields of engineering.
A fuzzy neurosis is a hybrid system that incorporates the decision ability of fuzzy logic with the computational ability of neural network, which provides a high capability for modeling and estimating. Basically, the Fuzzy part is used to classify the input data set and determines the degree of membership (that each number can be laying between 0 and 1) and decisions for the next activity made based on a set of rules and move to the next stage. Adaptive Neuro-Fuzzy Inference Systems (ANFIS) includes some parts of a typical fuzzy expert system which the calculations at each step is performed by the hidden layer neurons and the learning ability of the neural network has been created to increase the system information (9).
SVM is a one of supervised learning methods which used for classification and regression affairs. This method was developed by Vapink (15) based on statistical learning theory. The SVM is a method for binary classification in an arbitrary characteristic space, so it is suitable for prediction problems (12).
The SVM is originally a two-class Classifier that separates the classes by a linear boundary. In this method, the nearest samples to the decision boundary called support vectors. These vectors define the equation of the decision boundary. The classic intelligent simulation algorithms such as artificial neural network usually minimize the absolute error or sum of square errors of the training data, but the SVM models, used the structural error minimization principle (5).
Results Discussion Based on the results of performance evaluations, and RMSE and R criteria, both of the SVM and ANFIS models had a high accuracy in predicting the reference evapotranspiration of North West of Iran. From the results of Tables 6 and 8, it can be concluded that both of the models had similar performance and they can present high accuracy in modeling with different inputs. As the ANFIS model for achieving the maximum accuracy used the maximum, minimum and average temperature, sunshine (M8) and wind speed. But the SVM model in Urmia and Sanandaj stations with M8 pattern and in other stations with M9 pattern achieves the maximum performance. In all of the stations (apart from Sanandaj station) the SVM model had a high accuracy and less error than the ANFIS model but, this difference is not remarkable and the SVM model used more input parameters (than the ANFIS model) for predicting the evapotranspiration.
Conclusion In this research, in order to predict monthly reference evapotranspiration two ANFIS and SVM models employed using collected data at the six synoptic stations in the period of 38 years (1973-2010) located in the north-west of Iran. At first monthly evapotranspiration of a reference crop estimated by FAO-Penman- Monteith method for selected stations as the output of SVM and ANFIS models. Then a regression equation between effective meteorological parameters on evapotranspiration fitted and different input patterns for model determined. Results showed Relative humidity as the less effective parameter deleted from an input of the model. Also in this paper to investigate the effect of memory on predict of evapotranspiration, one, two, three and four months lag used as the input of model. Results showed both models estimated monthly evapotranspiration with the high accuracy but SVM model was better than ANFIS model. Also using the memory of evapotranspiration time series as the input of model instead of meteorological parameters showed less accuracy.
M. Ghamghami; J. Bazrafshan
Abstract
Today, there arevarious statistical models for the discrete simulation of the rainfall occurrence/non-occurrence with more emphasizing on long-term climatic statistics. Nevertheless, the accuracy of such models or predictions should be improved in short timescale. In the present paper, it is assumed ...
Read More
Today, there arevarious statistical models for the discrete simulation of the rainfall occurrence/non-occurrence with more emphasizing on long-term climatic statistics. Nevertheless, the accuracy of such models or predictions should be improved in short timescale. In the present paper, it is assumed that the rainfall occurrence/non-occurrence sequences follow a two-layer Hidden Markov Model (HMM) consist of a hidden layer (discrete time series of rainfall occurrence and non-occurrence) and an observable layer (weather variables), which is considered as a case study in Khoramabad station during the period of 1961-2005. The decoding algorithm of Viterbi has been used for simulation of wet/dry sequences. Performance of five weather variables, as the observable variables, including air pressure, vapor pressure, diurnal air temperature, relative humidity and dew point temperature for choosing the best observed variables were evaluated using some measures oferror evaluation. Results showed that the variable of diurnal air temperatureis the best observable variable for decoding process of wet/dry sequences, which detects the strong physical relationship between those variables. Also the Viterbi output was compared with ClimGen and LARS-WG weather generators, in terms of two accuracy measures including similarity of climatic statistics and forecasting skills. Finally, it is concluded that HMM has more skills rather than the other two weather generators in simulation of wet and dry spells. Therefore, we recommend the use of HMM instead of two other approaches for generation of wet and dry sequences.
B. Shabani; M. Mousavi Baygi; Mehdi Jabbari Nooghabi; B. Ghareman
Abstract
Nowadays, modeling and prediction of climatic parameters due to climate change, global warming and the recent droughts is inevitable. Maximum and minimum temperatures are including climatic parameters that are important in water resources management and agriculture. In order to model the maximum and ...
Read More
Nowadays, modeling and prediction of climatic parameters due to climate change, global warming and the recent droughts is inevitable. Maximum and minimum temperatures are including climatic parameters that are important in water resources management and agriculture. In order to model the maximum and minimum monthly temperatures of Mashhad plain, the long- term data of Mashhad and Golmakan were used for the joint period from 1987 to 2008. The SARIMA(0,0,0)(0,1,1)12 model for maximum monthly temperature and the SARIMA(0,0,0)(2,1,1)12 model for minimum monthly temperature were determined as the final models using time series. High correlation coefficientsindicate acceptable adaptation of modeling and actual values in the calibration and validation of models. Finlay, predictions were performed based on models fitted for the next 10 years (2009-2018). Comparison of results for future period (2009-2018) and the base period (1987-2008) represents maximum temperature mean 1 °c increase and minimum temperature mean 1.4 °cincrease.
A.A. Keikha; M. Mosannan Mozafari; M. Sabouhi; Gh. Soltani
Abstract
River flow modeling has special importance in water resources management. Since the actual river flow data are often low and they correlate and depend yearly and monthly, making the data similar to historical data is so difficult and complex. In this study, 50 year data and Seasonal Auto Regressive Moving ...
Read More
River flow modeling has special importance in water resources management. Since the actual river flow data are often low and they correlate and depend yearly and monthly, making the data similar to historical data is so difficult and complex. In this study, 50 year data and Seasonal Auto Regressive Moving Average (SARMA) and Clayton and Frank Copulas which are the prediction and simulation methods of the river flow molding, were used to generate random flow data of Helmand River. Results show, SARMA model forecasts minimum river flow data very good, but the generated data hasn’t correlation of historical data and usually the maximum river flow is greater than real data. Otherwise, Copula preserved concordance of real data and make the data that are similar to real river flow. Therefore it is proposed that Copula is used for Helmand river flow modeling. Also this method use for simulating other river flows and also using other Copulas for river flow modeling could have the subject of future researches.
Sajjad Abdollahi Asadabadi; yaghoub dinpazhoh; Rasoul Mirabbasi
Abstract
Forecasting of river discharge is a key aspect of efficient water resources planning and management. In this study, two models based on Wavelet Analysis and Artificial Neural networks (ANNs) were developed for forecasting discharge of Behesht-Abad River. For this purpose, mean daily discharge data of ...
Read More
Forecasting of river discharge is a key aspect of efficient water resources planning and management. In this study, two models based on Wavelet Analysis and Artificial Neural networks (ANNs) were developed for forecasting discharge of Behesht-Abad River. For this purpose, mean daily discharge data of mentioned river as well as precipitation data of 17 meteorological stations were used in the period 1999-2008. In the first method, called Cross Wavelet (CW), complex Morlet wavelet was used as analyzer function. Wavelet analyzing was performed for every daily rainfall and average discharge time series, separately. Initial phase, phase differences of subseries obtained from wavelet analysis, and calibration coefficients were calculated. Then structural series were reconstructed and average of structural components calculated. The river discharges were predicted for 1, 2, 3 and 7 days ahead forecasting horizon. In the second method, called Wavelet Neural Networks conjunction (WNN), a preprocessing was done on the initial input matrix using Meyer wavelet. Then the elements of the initial input matrix were normalized and the second input matrix was created. A three layer Feed Forward Back Propagation (FFBP) was formed based on the second input matrix and target matrix. After training the model using Levenberg–Marquardt (LM) algorithm, the river discharges were predicted for short term time horizons. The results showed that the WNN method had higher accuracy in short-term forecasting of river discharge in comparison with CW and ANN methods.
sarvin ghavidel; sarvin zamanzad ghavidel
Abstract
Forecasts of streamflows are required for many activities associated with the planning and operation of components in a water resource system. This paper demonstrates the application of two different intelligent approaches including adaptive neuro-fuzzy (ANFIS) based on grid partition and Gene Expression ...
Read More
Forecasts of streamflows are required for many activities associated with the planning and operation of components in a water resource system. This paper demonstrates the application of two different intelligent approaches including adaptive neuro-fuzzy (ANFIS) based on grid partition and Gene Expression Programming (GEP) for the prediction of monthly streamflows. In the first part of the study, ANFIS and GEP models were used in one-month ahead streamflow forecasting and the results were evaluated. Monthly run-off data of 21 years from two stations, the Safakhaneh Station on the Sarough-Chay Stream and the Senteh Station on the Kherkherh-Chay Stream in the Zarrineh-rud Basin of Iran were used in the study. The effect of periodicity on the model’s forecasting performance was also investigated. By application of periodicity coefficient in GEP model, determination coefficient in the case of the best input combination for Safakhaneh and Senteh increased 0.19 and 0.25, respectively. In the second part of the study, the performance of the ANFIS and GEP techniques was tested for streamflow estimation using data from the nearby river. The results indicated that the GEP and ANFIS models could be employed successfully in forecasting streamflow. In this case, for the best input combination, root mean square error (RMSE) for ANFIS and GEP obtained equal to 4.88 and 4.89 respectively. However, GEP is superior to ANFIS in giving explicit expressions for the problem.
A. Hezarjaribi; F. Nosrati Karizak; K. Abdollahnezhad
Abstract
Cation Exchange Capacity (CEC) is an important characteristic of soil in view point of nutrient and water holding capacity and contamination management. Measurement of CEC is difficult and time-consuming. Therefore, CEC estimation through other easily-measurable properties is desirable. The purpose ...
Read More
Cation Exchange Capacity (CEC) is an important characteristic of soil in view point of nutrient and water holding capacity and contamination management. Measurement of CEC is difficult and time-consuming. Therefore, CEC estimation through other easily-measurable properties is desirable. The purpose of this research was to investigate CEC estimating using easily accessible parameters with Artificial Neural Network. In this study, the easily accessible parameters were sand, silt and clay contents, bulk density, particle density, organic matter (%OM), calcium carbonate equivalent (%CCE), pH, geometric mean diameter (dg) and geometric standard deviation of particle size (σg) in 69 points from a 1×2 km sampling grid. The results showed that Artificial Neural Network is a precise method to predict CEC that it can predict 82% of CEC variation. The most important influential factor on CEC was soil texture. The sensitivity analysis of the model developed by using of Artificial Neural Network represented that clay%, silt%, sand%, geometric mean diameter and geometric standard deviation of particle size, OM% and total porosity were the most sensitive parameters, respectively. The model with clay%, silt%, sand%, geometric mean diameter and geometric standard deviation of particle size as inputs data was selected as the base model to predict CEC at studied area.
J. Behmanesh; M. Montaseri
Abstract
Potential evapotranspiration is one of the most important and effective factors for optimizing agricultural water consumption and water resources management. One of methods for prediction of evapotranspiration is to use the time series models. In this research, application of different time series models, ...
Read More
Potential evapotranspiration is one of the most important and effective factors for optimizing agricultural water consumption and water resources management. One of methods for prediction of evapotranspiration is to use the time series models. In this research, application of different time series models, such as AR and ARMA, in order to predicting monthly potential evapotranspiration in Urmia synoptic station were evaluated. In this process, monthly potential evapotranspiration since 1971 to 2010 was determined and the first 35 years and last 5 years were used for model calibration and validation respectively. After selecting the best model, the potential evapotranspiration were predicted for the next 5 years. The results showed that AR(11) time series model had the best results in comparing the other models and the trend of AR(11) time series model had least error. The values of R2 and RMSE in AR(11) model were 0.96 and 1.85 mm/month, respectively.
H. Naveh; K. Khalili; M. T. Alami; J. Behmanesh
Abstract
One of the important tools in modeling and forecasting of hydrological processes, is using and analysis of time series. The generated river flow series by using time series models have been used in many researches such as drought, flood periods, reservoir systems design and other purposes. The use of ...
Read More
One of the important tools in modeling and forecasting of hydrological processes, is using and analysis of time series. The generated river flow series by using time series models have been used in many researches such as drought, flood periods, reservoir systems design and other purposes. The use of nonlinear time series is very useful in river flow forecasting because of nonlinear river flow behavior in different spatial and time scales. The purpose of this study is to investigate the efficiency of bilinear nonlinear time series model in river flow forecasting. In this research monthly flow of Shahar-Chai and Barandouz-Chai rivers located in West Azarbaijan for duration of 31 and 39 years respectively were used. Despite of simplicity of bilinear nonlinear model, the results showed that this model had high efficiency in modeling and forecasting of two rivers and presented best results from ARMA model. The error of fitted model of Barandouz-Chai (1.605) was less than the model fitted for Shahar-Chai river (1.920). The reason may be due to longer data period for Barandouz-Chai river or it’s recharge from springs and ground waters.