Irrigation
A. Kazemi Choolanak; F. Modaresi; A. Mosaedi
Abstract
IntroductionPredicting river flow is one of the most crucial aspects in water resources management. Improving forecasting methods can lead to a reduction in damages caused by hydrological phenomena. Studies indicate that artificial neural network models provide better predictions for river flow ...
Read More
IntroductionPredicting river flow is one of the most crucial aspects in water resources management. Improving forecasting methods can lead to a reduction in damages caused by hydrological phenomena. Studies indicate that artificial neural network models provide better predictions for river flow compared to physical and conceptual models. However, since these models may not offer reliable performance in estimating unstable data, using preprocessing techniques is necessary to enhance the accuracy and performance of artificial neural networks in estimating hydrological time series with nonlinear relationships. One of these methods is wavelet transformation, which utilizes signal processing techniques. Materials and MethodsIn this study, to evaluate the efficiency of discrete and continuous wavelet types in the Wavelet-Artificial Neural Network (WANN) hybrid model for monthly flow prediction, a case study was conducted on the Kardeh Dam watershed in the northeast of Iran, serving as a water source for part of Mashhad city and irrigation downstream agricultural lands. Monthly streamflow estimates for the upstream sub-basin of the Kardeh Dam were obtained from the meteorological and hydrometric stations' monthly statistics over a 30-year period (1991-2020). The WANN model is a hybrid time series model where the output of the wavelet transform serves as a data preprocessing method entering an artificial neural network as the predictive model. The combination of wavelet analysis and artificial neural network implies using wavelet capabilities for feature extraction, followed by the neural network to learn patterns and predict data, potentially enhancing the models' performance by leveraging both methods. The 4-fold cross-validation method was employed for the artificial neural network model validation, where the model underwent validation and accuracy assessment four times, each time using 75% of the data for training and the remaining 25% for model validation. The final results were presented by averaging the validation and accuracy results obtained from each of the four model runs. To evaluate and compare the performance of the models used in this study, three evaluation indices, Nash-Sutcliffe Efficiency (NSE), Root Mean Square Error (RMSE), and Pearson correlation coefficient (R), were employed. Results and DiscussionThe analysis of meteorological and hydrometric data in this study revealed that monthly streamflow in two time steps, T-1 and T-2, were the most effective predictive variables. Each of the two runoff variables of the previous month (Qt-1) and the previous two months (Qt-2) were analyzed by each of the Haar and Fejer-Korovkin2 discrete wavelet transforms and the two continuous Symlet3 and Daubechies2 wavelets at three levels. The results of each level of decomposition was given as input to the ANN model. The presented results at each decomposition level indicated that hybrid models could accurately predict lower flows compared to the single ANN model, and the estimation of maximum values also significantly improved in the hybrid models. Among the wavelets used, Haar wavelets exhibited the weakest performance, and the less commonly employed Kf2 wavelet showed a moderate performance. Since the Haar and Fk2 wavelets, with their discrete structure, did not perform well in decomposing continuous monthly streamflow data, continuous wavelet models outperformed discrete wavelet models. The hybrid models, combining wavelet analysis and artificial neural networks, demonstrated up to an 11% improvement over the performance of the single neural network model. ConclusionStreamflow is a crucial element in the hydrological cycle, and predicting it is vital for purposes such as flood prediction and providing water for consumption. The objective of this research was to evaluate the performance of different types of discrete and continuous wavelet models at various decomposition levels in enhancing the efficiency of artificial neural network (ANN) models for streamflow prediction. Since climate and watershed characteristics can influence the nature of data fluctuations and, consequently, the results of the wavelet model decomposition, choosing an appropriate wavelet model is essential for obtaining the best results. Considering the existing variations in the results of different studies regarding the selection of the best wavelet type, it is suggested to use both continuous and discrete wavelet types in modeling to achieve the best predictions and select the optimal results. Given that a lower number of input variables in neural network models lead to higher accuracy in modeling results, it is recommended to perform decomposition at a two-level depth to reduce input components to the neural network model, thereby reducing the model execution time.
Soil science
Sh. Asghari; K. Heidari; M. Hasanpour Kashani; H. Shahab Arkhazloo
Abstract
Introduction
The study of soil mean weight diameter (MWD) of wet aggregates that is important for sustainable soil management, has recently received much attention. As the prediction of MWD is challenging, laborious, and time-consuming, there is a crucial need to develop a predictive estimation ...
Read More
Introduction
The study of soil mean weight diameter (MWD) of wet aggregates that is important for sustainable soil management, has recently received much attention. As the prediction of MWD is challenging, laborious, and time-consuming, there is a crucial need to develop a predictive estimation method to generate helpful information required for the soil health assessment to save time and cost involved in soil analysis. Therefore, it is useful to use different models such as multiple linear regression (MLR) and intelligent models including artificial neural network (ANN) and gene expression programming (GEP) to estimate MWD of wet aggregates through easily accessible and low-cost soil properties. The objectives of this study were (1) to creating MLR, ANN and GEP models for predicting MWD from the easily measurable soil variables in forest, range and cultivated lands of the Fandoghloo region of Ardabil province, (2) to compare the precision of the mentioned models in the prediction of MWD of wet aggregates using the coefficient of determination (R2), root mean square error (RMSE), mean error (ME) and Nash-Sutcliffe coefficient (NS) criteria.
Materials and Methods
Disturbed and undisturbed soil samples (n= 80) were nearly systematically taken from 0-10 cm depth with nearly 50 m distance in forest (n= 20), range (n= 23) and cultivated (n= 37) lands of the Fandoghloo region of Ardabil province, Iran (lat. 38° 24' 10" to 38° 24' 25" N, long. 48° 32' 45" to 48° 33' 5" E) in summer 2023. The contents of sand, silt, clay, CaCO3, pH, EC, bulk (BD) and particle (PD) density, organic carbon (OC), geometric mean diameter (GMD) of dry aggregates were determined in the laboratory using standard methods. Total porosity (n) was calculated using BD and PD data (n= 1-BD/PD). The mean geometric diameter (dg) and geometric standard deviation (σg) of soil particles were computed by sand, silt and clay percentages. The mean weight diameter (MWD) of wet aggregates was measured in the aggregates smaller than 4.75 mm by wet sieving equipment using sieves with 2, 1, 0.5, 0.25 and 0.106 mm pore diameter. All data were randomly divided into two series as 60 data for training and 20 data for testing of models. The SPSS 22 software with the stepwise method, MATLAB and Gene Xpro Tools 4.0 software were used to derive multiple linear regression (MLR), artificial neural network (ANN) and gene expression programming (GEP) models, respectively. A feed forward three-layer (9, 8, 6 and 6 neurons in the hidden layer) perceptron network and the tangent sigmoid transfer function were used for the ANN modeling. A set of optimal parameters were chosen before developing the best GEP model. The number of chromosomes and genes, head size and linking function were selected by the trial and error method, and they are 30, 3, 8, and +, respectively. The rates of genetic operators were chosen according to literature studies. The precision of MLR, ANN and GEP models in predicting MWD of wet aggregates were evaluated by the coefficient of determination (R2), root mean square error (RMSE), mean error (ME) and Nash-Sutcliffe coefficient (NS) statistics.
Results and Discussion
The values of sand (13.14 to 64.79 %), silt (21.11 to 74.96 %), clay (3 to 42.18 %), OC (1.01 to 7.17 %), PD (2.00 to 2.67 g cm-3), n (0.39 to 0.87 cm3 cm-3), GMD of dry aggregates (0.8 to 1.33 mm) and MWD of wet aggregates (0.35 to 2.65 mm) showed good variations in the soils of the studied region. The studied soils had clay loam (n= 11), sandy clay loam (n= 6), sandy loam (n= 12), loam (n= 13), silty clay loam (n= 14), silty clay (n= 1) and silt loam (n= 23) textural classes. There were found significant correlations between MWD with OC (r= 0.67**), sand (r= 0.70**), GMD (r= 0.30**) and PD (r= -0.46**). Also, significant and positive correlation was found between OC and sand (r= 0.59**). Due to the multicollinearity of sand with dg (r= 0.87**), we did not use the dg as an input variable to estimate MWD of wet aggregates. Generally, four MLR, ANN and GEP models were constructed to predict MWD of wet aggregates from measured readily available soil variables. The results of MLR, ANN and GEP models indicated that the most suitable variables to estimate MWD of wet aggregates were sand, OC and GMD of dry aggregates. The values of R2, RMSE, ME and NS criteria were obtained equal 0.52, 0.48 mm, 0.13 mm and 0.48, and 0.85, 0.30 mm, 0.03 mm and 0.78, 0.79, 0.35 mm, -0.10 mm, 0.95 for the best MLR, ANN and GEP models in the testing data set, respectively. Many researchers also reported that there is a positive and significant correlation between MWD of wet aggregates and OC.
Conclusion
The results showed that sand, OC and GMD of dry aggregates were the most important and readily available soil variables to predict the mean weight diameter (MWD) of wet aggregates in the Fandoghloo region of Ardabil province. According to the lowest values of RMSE and the highest values of R2 and NS, the precision of ANN models to predict MWD of wet aggregates was more than MLR and GEP models in this study. Because ANN is more flexible and effectively captures non-linear relationships, it performed better than the other models in predicting MWD.
M. Abiyat; M. Abiyat; M. Abiyat
Abstract
Introduction Agriculture is the essential sector for promoting food security. Crop area estimation (CAE) can meet the requirements of the crop monitoring plan. The organizing basis of the cultivation pattern is recognizing the types of crops and examining the condition of their crop area. Shush ...
Read More
Introduction Agriculture is the essential sector for promoting food security. Crop area estimation (CAE) can meet the requirements of the crop monitoring plan. The organizing basis of the cultivation pattern is recognizing the types of crops and examining the condition of their crop area. Shush county in Khuzestan Province has 300,000 hectares of the crop area. It is one of the agricultural hubs of Iran because it has a record annual production of more than two million tons of strategic crops such as wheat, sugar beet, and corn. CAE affects the amount of net production and shortage or surplus of produce for market steadiness. Traditional approaches for CAE are time-consuming and costly and are not widely enforceable. Remote sensing (RS) data provide good information for decision-makers by determining the crop type and the crop area. RS data has made it possible to avoid continuous reference to agricultural lands with less time and cost than another usual method and accurate CAE. Also, the use of multi-time images during the growing season of agricultural products allows the use of spectral curves when related to the crop calendar of each crop. This spectral curve is almost separate for each product and increases the ability to distinguish between products. Therefore, multi-temporal images support segregation based on multispectral images of products. The current study follows a speedy method with appropriate accuracy established on satellite image classification algorithms and spectral indices to identify and separate crops with RS data in Shush County.Materials and Methods Landsat-8 data with path/row coordinates 166/38 extracted from the USGS website were used to identify and separate the cultivated lands of the region. The reason for choosing Landsat images is the relatively suitable temporal and spatial resolution, availability, and the appropriate time distribution with the product growth period. The Landsat 8 carries 2-sensors, OLI (Operational Land Imager) and TIRS (Thermal Infrared Sensor). The OLI sensor with a spatial resolution of 30 meters has 8-bands in the visible spectrum, near-infrared (NIR), short-wavelength infrared (SWIR), and a panchromatic band with a spatial resolution of 15 meters. The TIRS sensor can record thermal infrared radiation with a spatial resolution of 100 meters with the help of 2-bands in atmospheric windows of 10.6 to 11.2 micrometers for band 10 and 11.5 to 12.5 micrometers for band 11. This research used bands 1-7 of the Landsat-8 OLI sensor with a spatial resolution of 30 meters after the initial corrections of satellite images. The spectral similarity between the region's dominant crops has made it impossible to select a single image to differentiate and extract the cultivation pattern. Wheat and barley have a high spectral similarity. The peak of the greenness of these products is in the first four months of the year, which has high NDVI values at this time. Therefore, choosing a good time to separate the crops was feasible by referring to the Khuzestan Organization Agriculture-Jihad (KOAJ) and receiving the regional crops calendar in 2018-19. Then, the low-level cloud cover images on April 24, June 27, and August 30, 2019, were selected for classification based on the crop calendar. Planting, harvesting, maximum greenness, and ripening information of the dominant crops in the area were pivotal in obtaining image dates. In dates selected related to the images were considered planting, harvesting, maximum greenery, and ripening information of the region's dominant crops.Results and Discussion According to the results, from total crop area in Shush county (163313.7 hectares) is allocated about 103513.2 hectares (63.4% of the county's crop area) to the ANN, about 102875.1 hectares (63.0% of the county's crop area) to the SVM, and about 102,277.3 hectares (62.6% of the county's crop area) to the NDVI, which in comparison with the KOAJ statistics, has an error of 0.11, 6.2 and 1.8%, respectively.This difference is the similarity of the reflective spectrum in some places, which affects the separability and recognition of phenomena and increases the error in estimating the area under cultivation of different crops. The highest and lowest errors in estimating the area under cultivation in the artificial neural network method were in barley and rice crops, respectively, in the support vector machine method were in wheat and rice crops, respectively, and in NDVI index were in wheat and barley crops, respectively. The difference between the cropped area obtained from classification methods and NDVI index with cropped area statistics of Agricultural-Jihad Organization may be due to the following: First, the cultivation history of different has caused problems such as reflections of diverse agricultural lands in one image. Second, the agricultural lands in this area are small. Most of them are under one hectare. Also, the crops in this area are diverse. Third, the smallest region that the image used in the present study can distinguish is about 900 square meters, which is a large number for the agricultural lands of the study area and causes errors.Conclusion The study results showed that the support vector machine method had the lowest error in CAE than the artificial neural network method, which indicates the higher accuracy of the support vector method in identifying and separating crops in the region. Comparing the area obtained from the NDVI index with the statistics of the Agricultural-Jihad Organization of Khuzestan province and evaluating the accuracy of this method indicated the higher efficiency of spectral indices in CAE for the region compared to classification methods. The NDVI index minimizes the error values of the results due to having a threshold and better identification of vegetation density. Therefore, based on the accuracy assessment results and comparing the cropped area with the KOAJ statistics, the utilization of the NDVI index provides the best CAE in the region.
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.
mahboobeh farzandi; Seyed Hossein Sanaeinejad; Bijan Ghahraman; Majid Sarmad
Abstract
Introduction: Temperature and precipitation are two of the main variables in meteorology and climatology. These are basic inputs in water resource management. The length of the statistical period plays a pivotal role in the accurate analysis of these variables. Observation data at Iran's first ...
Read More
Introduction: Temperature and precipitation are two of the main variables in meteorology and climatology. These are basic inputs in water resource management. The length of the statistical period plays a pivotal role in the accurate analysis of these variables. Observation data at Iran's first synoptic station from 1330 (1951) is available at the Iranian Meteorological Organization website The historical monthly precipitation and temperature of five stations in Iran is available since 1880 with missing data. These data measured by the Embassy of the United States and Britain from the Qajar period and recorded in World Weather records books. These synoptic stations include Mashhad, Isfahan, Tehran, Bushehr, and Jask. The monthly missing data were predominantly recorded during World War II (1941-1949). Unfortunately, these data have missing. Therefore, the accuracy of simulating these variables is very important. The current research aimed to predict the missing values of monthly temperature and precipitation in Mashhad station. The stations in the neighboring countries were selected due to the distance to Mashhad, relationship, and completeness of data since 1880, as the predictive variables. Monthly precipitation of Ashgabat from Tajikistan and Sarakhs, Kooshkah, Bayram Ali, Kerki and Repetek from Turkmenistan were selected as an independent variable in the making of Missing Rainfall in Mashhad. Also, the temperature of Ashgabat, Bayram Ali, Gudan, Sarakhs, and Tajan were selected to restore the monthly temperature of the Mashhad station. This research has fitted ten multiple regression models to monthly rainfall of Mashhad station and has fitted 6 multiple regression to the monthly temperature of Mashhad. then the parameters of these patterns are optimized by genetic and Ant Colony algorithm. Also, the Artificial Neural Network (MLP) model and Support vector regression have been selected and implemented in order to simulate monthly precipitation and temperature data of Mashhad.
Materials and Methods: In statistical modeling, regression analysis is a set of statistical processes for estimating the relationships among variables. It includes many techniques for modeling and analyzing several variables when the focus is on the relationship between a dependent variable and one or more independent variables (or 'predictors'). Genetic algorithm (GA) is a metaheuristic inspired by the process of natural selection that belongs to the larger class of evolutionary algorithms (EA). Genetic algorithms are commonly used to generate high-quality solutions to optimization and search problems by relying on bio-inspired operators such as mutation, crossover, and selection. Ant colony optimization algorithm (ACO) is a probabilistic technique for solving computational problems which can be reduced to finding good paths through graphs. This algorithm is a member of the ant colony algorithms family, in swarm intelligence methods, and it constitutes some metaheuristic optimizations. Artificial neural networks are one of the main tools used in machine learning. As the “neural” part of their name suggests, they are brain-inspired systems which are intended to replicate the way that we humans learn. Neural networks consist of input and output layers, as well as (in most cases) a hidden layer consisting of units that transform the input into something that the output layer can use. They are excellent tools for finding patterns which are far too complex or numerous for a human programmer to extract and teach the machine to recognize. In machine learning, support vector machines (SVMs, also support vector networks) are supervised learning models with associated learning algorithms that analyze data used for classification and regression analysis. Given a set of training examples, each marked as belonging to one or the other of two categories, an SVM training algorithm builds a model that assigns new examples to one category or the other, making it a non-probabilistic binary linear classifier (although methods such as Platt scaling exist to use SVM in a probabilistic classification setting).
Results and Discussion: At the first stage, several multiple regressions were fitted to monthly precipitation (with coefficients ranging from 0.63 to 0.81) and six patterns for monthly temperature (0.986-0.993). Afterward, GA and ACO were applied to improve the accuracy of the selected regression models by optimizing their parameters. At the next stage, ANN and SVR were used to estimate the monthly missing values separately. Finally, the results of the previous stages were compared using the root mean square error (RMSE), and the optimal models were applied to determine the missing values of monthly temperature and precipitation of Mashhad. The results showed that the Genetic Algorithm and Ant Colony increase the accuracy of the estimation of missing rainfall data significantly more than the previous methods. The lowest error criterion (RMSE) between regression patterns is 9.8 millimeters. By genetic algorithm, this criterion is reduced to 2.56 mm, and by ant colony algorithm to 2.559.
Conclusion: Comparison of the above methods in restoration temperature and precipitation shows that evolutionary methods (GA and ACO) are the best for estimating the missing monthly precipitation and machine learning methods (ANN and SVR) are the best to imputation missing data of monthly temperature.
Laleh Parviz
Abstract
Introduction: The globally growing demand for water has shown the need for its efficient and judicial utilization, and particularly in agriculture being single largest consumer of water. Crop evapotranspiration represents crop water demand and governed by weather and crop conditions and most of the current ...
Read More
Introduction: The globally growing demand for water has shown the need for its efficient and judicial utilization, and particularly in agriculture being single largest consumer of water. Crop evapotranspiration represents crop water demand and governed by weather and crop conditions and most of the current water demand models are non-spatial models, they use point data. Global scale satellite images can solve these problems. According to the high performance of satellite indices, it is necessary to estimate crop coefficient using combination of reflectance and thermal bands. The aim of this research was to estimate the effective crop coefficient of potato using vegetation indices and principle component analysis.
Materials and Methods: Principle component analysis (PCA) was used for effective crop coefficient estimation. Modeling of associations between vegetation indices and crop coefficient were conducted using artificial neural network. In the present study, NDVI, RI, EVI, SAVI, MSAVI, NVSWI, TVX, TVI, mNDVI and mTVI were the used as vegetation indices. PCA is designed to transform the original variables into new and uncorrelated variables (axes), namely the principal components, which are linear combinations of the original variables. The new axes lie along the directions of maximum variance. PCA provides an objective procedure of finding indices and information on the most meaningful parameters, which describes a whole data set affording data reduction with minimum loss of original information. Artificial neural networks are a computational model which is based on a large collection of simple neural units, loosely analogous to the observed behavior of a biological brain's axons. RMSE, MAE and MARE were the statistics used for investigating the performance of crop coefficient of vegetation indices with FAO crop coefficient.
Results and Discussion: Eleven MODIS vegetation indices are derived in the period of 2013 to 2016 for potato over the limited area between Tabriz and Bostanabad. The last year was considered as the validation period. According to the FAO-56 paper, the lengths of initial stage, crop development stage, mid-season stage, late season stage were considered to be 25, 30, 45, 30 days, respectively. The vegetation indices were derived using MODIS sensor with 2×2 pixels. The PCA showed that with increasing the number of components, the eigenvalues decreased. The analysis indicated that the three first components accounted for the 85.45 % of the total variance of data and the eigenvalues of them were greater than 1, the three first components were thus selected. NDVI, RI, TVI, MSAVI and NVSWI in the first component, mNDVI in the second component and LST in the third component had the highest coefficients. NDVI in the first component with high coefficient indicted the importance of index in the crop coefficient determination. The coefficients of SAVI and MSAVI were higher than NDVI. From the three investigations on the kind of principle component, the first investigation led to a 55.75 % decrease in RMSE relative to the second and third investigations. The first and second components together had less error rather than third component. The average of MAE for first, second and third investigations was, respectively, 0.17, 0.22 and 0.2. Therefore, component with exact values of particular vectors resulted in a reduced error. The sensitivity of artificial neural network led to an increase in the simulation accuracy (for example the RMSE decreased from epoch 100 to 50 was 48.27%). Crop coefficient estimation using vegetation indices of principle component analysis was underestimated about 1% in the validation period. Overestimation and underestimation were found in the initial and crop development stages, respectively.
Conclusions: The quantities of statistics showed the improvement of artificial neural network performance with combination of vegetation indices using principle component analysis. The vegetation indices with reflectance bands performed well. The combination of thermal and reflectance bands enhanced the vegetation indices efficiency. In addition to NDVI index for crop coefficient estimation, improvement of indices according to the study area condition increased the indices performance. The kind of mathematical equations of indices can increase the indices performance which using the same bands with different equations have different results. The selected component of principle component analysis has important role in increasing the simulation accuracy. The error reduction of simulated crop coefficients can increase the precision of irrigation consumption and agricultural planning which the principle component analysis has more important role.
Reza Hajiabadi; S. Farzin; Y. Hassanzadeh
Abstract
Introduction One reason for the complexity of hydrological phenomena prediction, especially time series is existence of features such as trend, noise and high-frequency oscillations. These complex features, especially noise, can be detected or removed by preprocessing. Appropriate preprocessing causes ...
Read More
Introduction One reason for the complexity of hydrological phenomena prediction, especially time series is existence of features such as trend, noise and high-frequency oscillations. These complex features, especially noise, can be detected or removed by preprocessing. Appropriate preprocessing causes estimation of these phenomena become easier. Preprocessing in the data driven models such as artificial neural network, gene expression programming, support vector machine, is more effective because the quality of data in these models is important. Present study, by considering diagnosing and data transformation as two different preprocessing, tries to improve the results of intelligent models. In this study two different intelligent models, Artificial Neural Network and Gene Expression Programming, are applied to estimation of daily suspended sediment load. Wavelet transforms and logarithmic transformation is used for diagnosing and data transformation, respectively. Finally, the impacts of preprocessing on the results of intelligent models are evaluated.
Materials and Methods In this study, Gene Expression Programming and Artificial Neural Network are used as intelligent models for suspended sediment load estimation, then the impacts of diagnosing and logarithmic transformations approaches as data preprocessor are evaluated and compared to the result improvement. Two different logarithmic transforms are considered in this research, LN and LOG. Wavelet transformation is used to time series denoising. In order to denoising by wavelet transforms, first, time series can be decomposed at one level (Approximation part and detail part) and second, high-frequency part (detail) will be removed as noise. According to the ability of gene expression programming and artificial neural network to analysis nonlinear systems; daily values of suspended sediment load of the Skunk River in USA, during a 5-year period, are investigated and then estimated.4 years of data are applied to models training and one year is estimated by each model. Accuracy of models is evaluated by three indexes. These three indexes are mean absolute error (MAE), root mean squared error (RMSE) and Nash-Sutcliffecoefficient (NS).
Results and Discussion In order to suspended sediment load estimation by intelligent models, different input combination for model training evaluated. Then the best combination of input for each intelligent model is determined and preprocessing is done only for the best combination. Two logarithmic transforms, LN and LOG, considered to data transformation. Daubechies wavelet family is used as wavelet transforms. Results indicate that diagnosing causes Nash Sutcliffe criteria in ANN and GEPincreases 0.15 and 0.14, respectively. Furthermore, RMSE value has been reduced from 199.24 to 141.17 (mg/lit) in ANN and from 234.84 to 193.89 (mg/lit) in GEP. The impact of the logarithmic transformation approach on the ANN result improvement is similar to diagnosing approach. While the logarithmic transformation approach has an adverse impact on GEP. Nash Sutcliffe criteria, after Ln and Log transformations as preprocessing in GEP model, has been reduced from 0.57 to 0.31 and 0.21, respectively, and RMSE value increases from 234.84 to 298.41 (mg/lit) and 318.72 (mg/lit) respectively. Results show that data denoising by wavelet transform is effective for improvement of two intelligent model accuracy, while data transformation by logarithmic transformation causes improvement only in artificial neural network. Results of the ANN model reveal that data transformation by LN transfer is better than LOG transfer, however both transfer function cause improvement in ANN results. Also denoising by different wavelet transforms (Daubechies family) indicates that in ANN models the wavelet function Db2 is more effective and causes more improvement while on GEP models the wavelet function Db1 (Harr) is better.
Conclusions: In the present study, two different intelligent models, Gene Expression Programming and Artificial Neural Network, have been considered to estimation of daily suspended sediment load in the Skunk river in the USA. Also, two different procedures, denoising and data transformation have been used as preprocessing to improve results of intelligent models. Wavelet transforms are used for diagnosing and logarithmic transformations are used for data transformation. The results of this research indicate that data denoising by wavelet transforms is effective for improvement of two intelligent model accuracy, while data transformation by logarithmic transformation causes improvement only in artificial neural network. Data transformation by logarithmic transforms not only does not improve results of GEP model, but also reduces GEP accuracy.
majid montaseri; sarvin zamanzad ghavidel
Abstract
Introduction: A total dissolved solid (TDS) is an important indicator for water quality assesment. Since the composition of mineral salts and discharge affects the TDS of water, it is important to understand the relationships of mineral salts composition with TDS.
Materials and Methods: In this study, ...
Read More
Introduction: A total dissolved solid (TDS) is an important indicator for water quality assesment. Since the composition of mineral salts and discharge affects the TDS of water, it is important to understand the relationships of mineral salts composition with TDS.
Materials and Methods: In this study, methods of artificial neural networks with five different training algorithm,Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG), Fletcher Conjugate Gradient (CGF), One Step Secant (OSS) and Gradient descent with adaptive learning rate backpropagation(GDA)algorithm and adaptive Neurofuzzy inference system based on Subtractive Clustering were used to model water quality properties of Zarrineh River Basin, to be developed in total dissolved solids prediction. ANN and ANFIS program code were written in MATLAB language. Here, the ANN with one hidden layer was used and the hidden nodes’ number was determined using trial and error. Different activation functions (logarithm sigmoid, tangent sigmoid and linear) were tried for the hidden and output nodes. Therefore, water quality data from seven hydrometer stationswere used during the statistical period of 18years (1993-2010).In this research, the study period was divided into two periods of dry and wet flow, and then in a preliminary statistical analysis, the main parameters affecting the estimation of the TDS are determined and isused for modeling. 75% of data are used for remaining and 25% of the data are used for evaluation of the model, randomly. In this paper, three statistical evaluation criteria, correlation coefficient (R), the root mean square error (RMSE) and mean absolute error (MAE) were used to assess models’ performances.
Results and Discussion: By applying correlation coefficients method between the parameters of water quality and discharge with total dissolved solid in two periods, wet and dry periods, the significant (at 95% level) variables entered into the model were Q, HCO3., Cl, So4, Ca, Na and Mg. The optimal ANN (LM) architecture used in this study consists of an input layer with seven inputs, one hidden and output layer with two and five neurons for dry and wet periods, respectively. Similar ANN(LM), ANFIS-SC model had the best performance. It is clear that the ANFIS with 0/72 and 0/58 radii value has the highest R and the lowest RMSE for dry and wet periods, respectively. Comparing the ANFIS-SC estimations with the measured data for the test stage demonstrates a high generalization capacity of the model, with relatively low error and high correlation. From the scatter plots it is obviously seen that the ANFIS-SC predictions are closer to the corresponding measured TDS than other models in two periods. As seen from the best straight line equations (assume the equation as y=ax) in the scatter plots that the coefficient for ANFIS-SC is closer to 1 than other models. In addition ANFIS-SC performancedwith the correlation coefficients in dry and wet periods, respectively 0.975 , 0.969 and with Root-mean-square errors, respectively 34.41 , 23.85 in order to predict dissolved solids (TDS) in the rivers of Zarrineh River Basin. The obtained results showed the efficiency of the applied models in simulating the nonlinear behavior of TDS variations in terms of performance indices. The results are also tested by using t test for verifying the robustness of the models at 99% significance level. Comparison results indicated that the poorest model in TDS simulation was ANN-GDAin dry and wet periods, especially in test period. The observed relationship between residuals and model computed TDS values shows complete independence and random distribution. It is further supported by the respective correlations for ANFIS-SC models (R2 = 0.0012 for dry period and R2 = 0.0214 for wet period) which are negligible small. Plots of the residuals versus model computed values can be more informative regarding model fitting to a data set. If the residuals appear to behave randomly it suggests that the model fits the data well. On the other hand, if non- random distribution is evident in the residuals, the model does not fit the data adequately. On the base of these results, we propose ANFIS-SC and ANN (LM) methods as effective tools for the computation of total dissolved solids in river water, respectively.
Conclusion: It can be concluded that the ANN with Levenberg-Marquardt training algorithm and ANFIS-SC models can be considered as promising tools for forecasting TDS values, based on water quality parameters. With attention to the aim of current research that is presenting the feasibility of artificial intelligence techniques for modeling TDS values, it is notable that the results presented in this paper are for research purpose and applying the abstained results for real-world needs some complicated steps and building artificial intelligences methods, based on complete data and parameters maybe affected the TDS values
R. Moazenzadeh
Abstract
Introduction: In two last decades, greenhouse cultivation of different plants has developed among Iranian farmers, approximately 45 percent of national greenhouse cultures consisting of cucumber, tomato and pepper. As huge amounts of agricultural water in Iran are extracted from groundwater resources ...
Read More
Introduction: In two last decades, greenhouse cultivation of different plants has developed among Iranian farmers, approximately 45 percent of national greenhouse cultures consisting of cucumber, tomato and pepper. As huge amounts of agricultural water in Iran are extracted from groundwater resources and a large number of Iranian plains are in critical conditions, and because irrigation is the major consumer of water (95 percent), it must be performed in a scientific manner. One approach to this is to obtain the knowledge of the consumptive use of major crops which is named evapotranspiration (ETc).
Materials and Methods: This research was carried out in a north-south greenhouse belonging to Plant Protection Research Institute, located on northern Tehran, Iran, for estimating greenhouse cucumber evapotranspiration. Trickle irrigation method was used, and meteorological data such as temperature, humidity and solar radiation were measured daily. Physical and chemical measurements were conducted and electric conductivity (EC) and pH values of 3.42 dsm-1 and 7.19, respectively, were recorded. Soil texture and bulk density were measured as to be sandy loam and 1.4 gr cm-3, respectively. In order to measure the actual evapotranspiration, cucumber seeds were also cultured in six similar microlysimeters and irrigation of each microlysimeter was based on FC moisture. If any drained water was available, it was measured. Finally, with measured meteorological characteristics in greenhouse which are suggested to have an effect on ET and were measurable, the best multiple linear regression and artificial neural network were established. The average data from three microlysimeters were used for calibration and that from three other microlysimeters were used for validation set.
Results and Discussion: In the former case, when we used one multiple linear regression with measurable meteorological variables inside the greenhouse to predict cucumber ET for the entire growth period, high and considerable amounts of error occurred, as the difference between measured and predicted values of ET is approximately 2.86 mm day-1 which is noticeable. Overestimation of the cucumber ET in the first and last stages which will result in decreasing water use efficiency and underestimation in blooming and yielding fruit stages, when cucumber is more susceptible to water stress, are the other disadvantages of using one equation for the entire growth period to describe and predict cucumber ET. In contrast, when we divided growth period into four steps, the MLR method’s performance in prediction of ET was improved and the difference mentioned above between measured and predicted values of ET (2.86 mm day-1) decreased to about 1.32 mm day-1. The results showed that measured and predicted values of ET ranged from (0.08 to 4.75) and (0.13 to 4.25) when the whole growth period is considered as one step, respectively. These mentioned values were obtained (0.08 to 1.5) and (0.13 to 1.75); (0.71 to 2.64) and (1.31 to 4.25); (2.18 to 4.75) and (1.69 to 4.13); (1.32 to 2.61) and (2.66 to 3.74) for each of growth period stages, respectively. Also the value of total ET for the entire growth period is measured 273.45 mm and predicted 275.7 and 275.59 mm, when the whole growth period is considered as one step or divided into four stages, respectively. Although dividing the growth period improved ET prediction, the results in the first and especially the third stage are still discussable. Therefore, as with MLR method, the capability of ANN technique was investigated in prediction of cucumber ET. Comparison of measured and predicted values of ET confirms that ANN has better performance than MLR, even when growth period is divided.
Conclusion: Determining cucumber evapotranspiration in the greenhouse was the main objective of this study. For this purpose we used Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) techniques. In MLR, first we used one equation for the entire growth period. The results showed that this single equation is not able to simulate actual ET of cucumber. To overcome this problem, we divided the growth period into four stages and derived a separate equation for each stage. The results showed that this procedure improves prediction of cucumber ET, especially in the second and last stages of growth period. Statistical indices such as RMSE, Ens, PBIAS and PSR, t-statistical results, measured versus predicted ET values, and predicted values of ET in the growth period indicate that ANN technique is not only reliable, but also easier than the MLR technique.
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.
shamsollah Ayoubi; Mohammad Reza Mosaddeghi
Abstract
Soil surface shear strength is an important parameter for prediction of soil erosion, but its direct measurement is difficult, time-consuming and costly in the watershed scale. This study was done to predict soil surface shear strength using artificial neural networks (ANNs) and multiple linear regression ...
Read More
Soil surface shear strength is an important parameter for prediction of soil erosion, but its direct measurement is difficult, time-consuming and costly in the watershed scale. This study was done to predict soil surface shear strength using artificial neural networks (ANNs) and multiple linear regression (MLR) and to rank the most important soil and environmental attributes affecting the shear strength. A direct shear box was designed and constructed to measure in situ soil surface shear strength. The device can determine two soil shear strength parameters i.e. cohesion (c) and angle of internal friction (φ). The study area (3500 km2) was located in Semirom region, Isfahan province. Soil surface shear strength was determined using the shear box at 100 locations. Soil samples were also collected from 0-5 cm layer of the same 100 locations at which the surface shear strength was measured using the shear box. Particle size distribution, fine clay content, organic matter content (OM), carbonate content, bulk density and gravel content were determined on the collected soil samples. Normalized difference vegetation index (NDVI), the type of land use and geology were also determined. The MLR and ANNs were used to model/predict soil surface shear strength (c and φ). In order to compare the modeling methods, coefficient of determination and root mean square errors were used as efficacy indices. The results showed that ANN models were more feasible in predicting soil shear strength parameters than MLR models due to capability of ANN models in deriving nonlinear and complex relations between the parameters. Results of sensitivity analysis for ANN models indicated that NDVI, bulk density and fine clay content are more effective parameters in predicting c in the studied region. Also it was found that sand content, bulk density and NDVI were more effective parameters and OM/clay ratio and organic matter content were less effective parameters in predicting φ in the region.
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.
A. Lakzian; M. Fazeli Sangani; Alireza Astaraei; A. Fotovat
Abstract
This study was conducted to evaluate using terrain attributes derived from digital elevation model (DEM) as ancillary data to predict soil organic carbon (SOC) by implementing different statistical and geostatistical techniques. A linear regression model (LR), Artificial Neural Network model (ANN), ordinary ...
Read More
This study was conducted to evaluate using terrain attributes derived from digital elevation model (DEM) as ancillary data to predict soil organic carbon (SOC) by implementing different statistical and geostatistical techniques. A linear regression model (LR), Artificial Neural Network model (ANN), ordinary kriging (OK), ordinary co-kriging (OCK), regression kriging (RK) and kriging with an external drift (KED) were performed to predict spatial distribution of SOC in an area of 2400 km2 in mashhad, iran. The SOC was measured for 200 soil samples of the study area and their corresponding Terrain attributes value was extracted from derived from 10-m resolution DEM. correlation between measured SOC and individual terrain attributes was determined, the number of 160 data were used for model development and 40 as validation data set. Resulting maps of different interpolation methods were compared to evaluate map quality using MAE and R2 criteria calculated from plotting measured versus estimated data. The results showed that there is a significant but not strong correlation between SOC and terrain attributes. The comparison of estimation techniques showed that the KED technique with wetness index as ancillary data has the best performance (MAE=0.18 %, R2=0.67) of all, but no significant difference with RK. There were modest differences between maps created with geostaistical technique but sensible difference with LR and ANN ones. The results of this study propose that although there is a significant correlation between SOC and terrain attributes therefore It can be use for enhancing the quality of map, but it is not able to express the spatial variability of SOC as it is necessary for detailed soil map. Because there is other factors controlling SOC spatial distribution
