جستجوی مقالات مرتبط با کلیدواژه « شبکه عصبی » در نشریات گروه « کشاورزی »

Reference evapotranspiration (ETo) is considered one of the important variables in hydrology and agricultural science and is a determining factor in water resources management. This study investigates a hybrid model of an artificial neural network with an artificial rabbit optimization algorithm (ANN-ARO) for daily modeling of ETo with limited meteorological parameters. It compares it with other hybrid methods, i.e. ANN with a particle optimization algorithm (ANN-PSO). ANN with genetic algorithm (ANN-GA) and five different data mining models. These models were evaluated using long-term daily climate data from 2000 to 2023 in two climates. The investigated stations included Birjand (with a desert climate) and Mashhad (with a cold semi-arid climate). The statistical comparison showed that considering all climatic parameters, the hybrid ANN-ARO model in Mashhad city with R2=0.9986 and MSE=0.0001 and in Birjand city with R2=0.9986 and MSE=0.0001 gave better estimates than other methods. In addition, the ANN_ARO optimization algorithm has the best estimation with "temperature" and "relative humidity" by considering the minimum meteorological parameter, and also by considering two and three input parameters, it performs better than other methods. In general, nature-inspired optimization algorithms are powerful tools to enhance the performance of ANN in ETo simulation. According to the results, the ANN-ARO model is highly recommended for estimating ETo in similar climate regions with limited climate data. This study proposes powerful models for accurate estimation of ETo with limited inputs in arid and semi-arid climates, which provide practical implications for the development of precision agriculture.

The aim of this study is to investigate the performance of various algorithms in enhancing the accuracy of land cover maps using Sentinel images.

The study area is a sheet (1:25000) encompassing an area of 15782.6 hectares. The land cover map was created using a range of algorithms - Mahalanobis distance, maximum likelihood, minimum distance, neural network, parallelepiped, support vector machine, spectral angle mapper, spectral information divergence, and binary encoding - applied to the optimal band composition derived from 12 bands (2, 3, 4, 5, 6, 7, 8, 8a, 11, 12, NDVI, SAVI). The training area was obtained from field information and satellite images. 70% of the samples were used for classification and 30% for evaluating the accuracy of the classified maps.

The results indicate that the support vector machine, neural network, and maximum likelihood classifications have the highest accuracy. The support vector machine classifier is slightly more accurate than the other two classifiers. To improve the classification, support vector machine kernels (linear, polynomial, radial basis function, and sigmoid), spectral angle mapper settings (6 modes), and parallelepiped (2 modes) were utilized. The results show that the support vector machine classifier, using the 6th degree polynomial function method, has the highest accuracy. Following this, the map was post-processed with the highest accuracy, resulting in an overall accuracy of 96.63 and a kappa coefficient of 0.9393.

An examination of 21 classification modes on Sentinel images in this study provides a comprehensive review of classification algorithms compared to previous studies.

Accurately and promptly monitoring the nutritional conditions of fruit orchards is crucial for providing optimal fertilizer recommendations, which in turn improves yield and enhances the quality of agricultural products. The current laboratory methods used to evaluate nutritional condition in fruit trees are expensive, challenging, time-consuming, and require an expert. In this study, image processing methods and neural network models was utilized to determine the stages of iron deficiency in peach trees. Therefore, a database containing 800 images of peach leaf samples was acquired. These images were then classified into four categories using the KNN clustering method no deficiency, low deficiency, moderate deficiency, and severe deficiency. The preprocessing, feature extraction, and modeling operations were performed in the MATLAB software, version 2017. Features such as mean and standard deviation were extracted from the RGB, HSV, and Lab color space components of each image. Subsequently, the principal component analysis (PCA) algorithm was applied to the feature vector. To determine the optimal structure of the network, criteria including precision, accuracy, recall, and the F1-score were evaluated. These criteria helped ascertain the number of optimal inputs and the corresponding number of neurons for each combination of input features (PCs). Results indicated that the neural network model, structured as 6-36-4, achieved an accuracy of 89.73 ± 0.54%, precision of 89.59 ± 0.57%, recall of 89.52 ± 0.51%, and an F1-score of 89.55 ± 0.54% in detecting levels of iron deficiency in peach tree leaves. The findings from the confusion matrix and the developed model reveal that this method can effectively and efficiently detect the severity of iron deficiency in peach tree leaves.

Precipitation is considered one of the most important components of hydrological cycle, and its effective and usable amount for plants is of great importance in the agricultural sector, especially rainfed cultivation. In this research, the effective precipitation (EP) in dry wheat fields of Khomein city was estimated by using RS and SEBAL on 28 available images from Landsat8 in the crop years 2014 to 2022. Penman-Monteith-Fao method was used to evaluate the accuracy of SEBAL. Then, a model of EP estimation was developed with ANN and meteorological data. For this purpose, the correlation between meteorological data and Growin Degree Days (GDD) with EP was investigated by Pearson's correlation method. the meteorological data of three stations from the closest synoptic stations to the study area were used and The meteorological data of the study area were interpolated using the Inverse Distance Weighting method (IDW). According to the results of the correlations, the average temperature parameter with a correlation of 0.92 and the GDD and the maximum relative humidity respectively with a correlation of 0.86 and -0.77 as effective variables in estimating EP. In the next step, the most effective parameters were used for modeling. the networks were trained under different scenarios, and the performance of the networks was evaluated using the RMSE and MBE error criteria. The results showed that by using the BR learning algorithm and having the variables of daily temperature and GDD, it is possible to predict the amount of EP for the target area with very good accuracy. The RMSE value of this model was 0.1899 mm and MBE was estimated as -0.0115 mm. By using the presented model, with simple meteorological variables, the actual evapotranspiration and finally the EP of the desired area can be determined with appropriate accuracy without the need to solve complex algorithms.

Snow monitoring and estimation of runoff from snow melting play an important role in controlling and managing watersheds and reservoirs and flood warning systems more efficiently. Given that the Koohrang area is found to be one of the snowy mountains in the country, and thanks to the high volume of runoff from precipitation, and snow melt, it plays a vital role in water supply for drinking, industry, and agriculture, neighboring provinces and even Iran as a whole so that it meets 10 % of total water demands in Iran. Accurate estimation of runoff from snowmelt entails spatial distribution of snow so that spatial variability of snow depth is measured via measuring snow depth in close resolution. On the other hand, the non-availability of gauge stations and extreme sampling conditions in snowy watersheds have caused researchers to think of simple and indirect strategies including regression techniques, interpolation methods, artificial intelligence, data mining, and also the use of satellite images, especially the use of radar interferometric method. Given the importance of snow depth variations and accurate estimation, although many methods have been used, there is an urgent need formore precise calculation and strategic position in this area requires procedures that are more accurate and more effective variables that are used in snow depth estimation. Study of artificial intelligence techniques and linear regression analysis and principal component analysis (PCA) along with geomorphometry parameters and inputs as well as satellite images were used to estimate the snow depth he and the results were compared. Therefore, in this study, unlike previous studies used much more variables to model snow depth, and also, the digital elevation model with the higher spatial resolution was used to model snow depth in a more accurate manner..

Methods and Materials:

Koohrang region is located in the west and Chaharmahal and Bakhtiari Province with an area of over 3700 km2. It is characterized by unique climatology, hydrology, and topography. Climatic characteristics of the region include an average annual temperature of 8.5 C, rainfall of 1430 mm, a frost period of 130 days, and a winter rainfall regime. In this research, using the hypercube technique, first, 100 points were selected for sampling in the Chalgerd area. In addition to these points, 195 other points were randomly collected from the study area. To obtain the data required for this research in field work, sampling was done over three days by the Monte-Rose model sampler. After the collection of snow samples, auxiliary data required for zoning, which includes data related to satellite images and variables derived from the digital elevation model, was extracted in the Saga software environment. The artificial neural network (ANN) was chosen as a new computing system and method to estimate snow depth using morphometric and climatic information related to snow depth. After extraction of the auxiliary variables in the study, between 32 input variables and snow depth, multiple linear regression analysis was conducted to test this model is 295 points. In order to fit the multiple regression equations, snow depth data as the dependent variable and physical variables as independent variables were considered. After obtaining an equation relating to the model was tested on regression test data (20% of data) to determine the accuracy of the model to predict the snow depth. In this study, in order to reduce the number of input data to the ANN and linear regression models, the PCA method was used, and finally, the number of components was chosen to be eight. For model evaluation, the predicted snow depth was evaluated using a linear regression model and ANN followed by calculating RMSE and R2.

By trial and error, we found that a multi-layer neural network with a sigmoid activation function and a hidden layer of snow 1-6-32 for the optimal structure for the network as well as the number of repetitions and the coefficient of torque and 0.7 and 1000 was found. To evaluate and compare the performance of ANN, test data (20%) were used. ANN output values were compared with the corresponding observational values and details on the correlation coefficient were extracted. So as can be seen in the results, ANN and regression accounted for snow depth variation of 62 and 46% respectively and this regression model was significant at a probability level of 5%. The results of the PCA are to reduce the number of entries after the model of 32 to 8, the values in the model ANN and linear regression coefficient was reduced and root mean square error (RMSE) increases, and the 55 and 45 % variations in snow depth have been able to properly modeled. The less R2 and RMSE, the more accurate model is. Thus, according to the error criteria value, the ANN model outperforms other ones. According to the results obtained of all variables used in ANN, the most important variables affecting the spatial variability of snow depth in the study area in order of importance, include profile longitudinal curvature, general curvature, gradient, transverse profile curvature, watershed gradient, slope middle position, wind, normalized elevation, geographical directions, and snow normalized difference index. It is worth noting that additional variables with negligible contributions were neglected. Given that prevalent winds blow in west and southwest directions and most of the highlands are nestled in these directions, much more snow accumulation can be found in this direction than those north, east and southward directions.

In the present research, to estimate the spatial distribution of the snow, the four models of ANNs, linear regression, PCA, and neural network were considered. After reviewing the methods according to the statistical criteria, the lowest error rate was attributed to ANN (RMSE, 19.57), followed by PCA using ANN (RMSE, 20.86), then linear regression (RMSE, 21.09), and the highest error rate on PCA using linear regression (RMSE, 21.59). Of all variables used in ANN, the most important variables affecting the spatial variability of snow depth in the study area in order of importance, include profile longitudinal curvature, general curvature, gradient, transverse profile curvature, watershed gradient, slope middle position, wind, normalized elevation, geographical directions, and snow normalized difference index. Therefore, digital elevation models with different resolutions in modeling can be used. However, here, variables such as vegetation, geology, solar radiation were not used and therefore it is recommended to use these variables in similar studies and different time resolutions. However, in future research, the most effective variables mentioned here can be promising for accurate zonation of snow depth in snowy watersheds.

In line with the study of land use and land cover, remote sensing technology has been welcomed by many researchers as a source of spatial information production and suitable tools, which shows the accuracy and validity of these maps. The purpose of this research is to evaluate and compare the accuracy of preparing land use maps using two methods of remote sensing and one method of visual interpretation of Google Earth images in the Kasilian representative watershed. In this research, after taking educational samples using Google Earth software and implementing them on the Landsat 9 image of 2021, classification of images was done in ENVI software, and the land use map was prepared based on training samples, Neural Network and SVM methods. In the method of visual interpretation, all land uses in Google Earth images were manually digitized and a land use map was obtained. Then, the accuracy of the map was checked for all three methods and the results showed that the map obtained from visual interpretation of Google Earth images with overall accuracy and Kappa coefficient of 100% was in agreement with the ground reality compared to Neural Network and SVM methods with overall accuracies of 87.6% and 88.2% and Kappa coefficients of 76% and 77.8%, respectively. However, due to the time-consuming visual interpretation method, especially for large watersheds, and the acceptable accuracy of Neural Network and SVM methods, it is suggested to use advanced methods to prepare land use maps, especially in large watersheds.

The cycle of soil erosion (including removal, transport and deposition) that controls the sedimentation of watersheds, includes a set of complex and highly nonlinear processes. On the other hand, the factors influencing sedimentation in watersheds are very diverse, and according to the specific conditions of climate, soil, vegetation, geology, topography, etc., in each basin, the weight and role of each of the mentioned factors in sediment production is very different. Accurately determining and measuring these factors and making mathematical relationships between them are often difficult, expensive, time-consuming and error-prone, and this is the case with the use of models based on computational intelligence and the use of a limited number of basin dynamic variables, it is possible to simulate the behavior of the watershed in sediment production. Regardless of the type of intelligent models, in most of the conducted research (especially in internal research), the simulation of suspended sediment is mainly based on the discharge variable and the role of variables such as precipitation (especially precipitation obtained from satellite images), which are effective in the sedimentation of basins, have received less attention. In addition to precipitation, the skewness of sediment measurement data is also one of the issues that lack of recognition and attention will reduce the efficiency of estimator models. In the present study, the role of variable daily rainfall (taken from CHIRPS satellite) in the simulation of suspended sediment of Qarachai River has been investigated.

Multi-layer perceptron artificial neural network was used in order to simulate the daily suspended sediment concentration of Qarachai River (at the Ramian hydrometer station in Golestan province). In this regard, the variables of discharge and previous discarge (in instantaneous and daily scales) as well as the average daily and previous rainfall of the basin (taken from CHIRPS satellite) for a statistical period of 37 years (1980-2017) as variables model input was used. In order to increase the generalization power of the models, self-organized mapping neural network (for data clustering) and gamma test was used to find the best combination of input variables. In order to improve the efficiency of network training, a variety of activation and loss functions as well as the overfitting prevention algorithm were used. In order to investigate the effect of using activation and loss functions in suspended sediment estimation, different scenarios were considered, which led to the construction of 9 models. After that, using validation indicators, the effectiveness of the models in simulating suspended sediment was investigated and compared, and then the best model was selected.

The results obtained from the present research showed that among the different models, the neural network model with Huber's activation function and ReLU loss function, having the average absolute value of the error equal to 368 mg/l, the root mean square error equal to 597 mg per liter, the Nash-Sutcliffe coefficient of 0.87 and the percent bias -2.2% were selected as the best model. The results also showed that the use of the rainfall variable (as one of the important factors in causing erosion and sediment transfer in the basin) has improved the efficiency of the models, therefore, considering the ease of using CHIRPS satellite rainfall data, it is suggested in order to simulate the suspended sediment of rivers, this data is also used along with other predictive variables.

In the simulation of suspended sediment, discharge variable is often used as the only predicting variable of suspended sediment, while in basins with rainy, or rainy-snow regimes, the role of precipitation in the production of surface runoff and soil erosion is very important and plays an important role in the production and transport of sediment in the basin. In this regard, although the use of rainfall data obtained from ground rain gauge stations has played an effective role in increasing the efficiency of data-based models in estimating suspended sediment, however, the preparation of hundreds of spatial distribution layers of daily rainfall from the data point data of ground stations, the use of this variable in the simulation of the suspended sediment of the basin has been faced with many problems (such as the lack or inappropriateness of the spatial distribution of rain gauge stations, statistical deficiencies, the use of inappropriate interpolation methods and time-consuming calculations). Therefore, in practice, the variable of river flow is often used as a predictor of sediment, and precipitation is used less often. One of the solutions to the problem mentioned in the present study is the use of CHIRPS satellite data, which was investigated for the first time in this study. These data, available since 1981, can easily be used to simulate suspended sediment or other applications related to watersheds. Another important point that needs to be taken into account in the simulation of suspended sediment is the presence of high skewness in sediment measurement data (both suspended sediment and flow rate), which lack of attention in the process of training (or recalibration) and testing the models leads to It will lead to the construction of weak models in terms of efficiency and the existence of uncertainty in the accuracy of their results. In this regard, it is necessary to use logarithmic transformations or suitable functions of activation and loss in the training process, which in this research, two functions, ReLU and Huber, were proposed respectively. Another important point is to pay attention to the generalization power of data-based models, which is largely dependent on the data used in their calibration or training process. These data should be selected in such a way that while they are representative of the data in the entire statistical period, they are similar and have the same distribution with other data sets (such as cross-validation or test sets). According to the results obtained from the present research and in order to increase the efficiency of artificial neural network models in estimating the suspended sediment of watershed hydrometric stations, it is suggested to use the experiences obtained in this research in other sediment measuring stations of the country.

Drought is one of the most important natural disasters with devastating and harmful effects in various economic, social, and environmental fields. Due to the repetitive behavior of this phenomenon, if the appropriate solutions are not implemented, its destructive effects can remain in the region for years after its occurrence. Most natural disasters, such as floods, earthquakes, hurricanes, and landslides in the short term, can cause severe financial and human damage to society, but droughts are slow-moving and creepy in nature, and their devastating effects appear gradually and over a longer period of time. Therefore, by modeling drought, it is possible to provide plans for drought preparation and reduce the damage caused by it. In this study, computational intelligence algorithms of Multi-Layer Perceptron neural network, Generalized Regression Neural Network, Support Vector Regression with support kernel, and Support Vector regression with the proposed kernel (Support Vector) Regression New kernel has been used to model the drought using the Standardized Precipitation Index. The modeling results, in most cases, showed better performance of the proposed SVR_N model than other models. The values of RMSE and R2 were 0.093 and 0.991, respectively, and the GRNN, MLP, and SVR models performed better in modeling after SVR_N, respectively. Modeling of drought phenomenon in modeling is supported by vector regression method.

 In order to simulate the yield and water productivity of cucumber plant (Cucumis sativus L.), an experiment was conducted in the form of a completely randomized block design with three irrigation levels of 100, 85 and 75% of the water requirement in two growing seasons during 2017 and 2018 and using perceptron neural networks (MLP) and support vector machine (SVM) methods were used and finally, to select the appropriate and optimal model, the indices of explanatory coefficient, mean squared error and normalized mean squared error were used. The amount of irrigation water, number of leaves on the plant, temperature, evaporation rate and relative humidity were selected as input data and 60%, 20% and 20% of the total data were allocated for training, validation and testing of the model, respectively. The results showed that the MLP neural network with the inputs of irrigation water and number of leaves was more accurate in simulating fruit yield and water productivity in cucumber plants with an explanation coefficient of 0.92 and 0.86, respectively. The results of the sensitivity analysis indicated that the irrigation water input parameters are the most important effective parameters on the water consumption efficiency model and cucumber fruit yield with sensitivity coefficients of 0.9 and 0.86, respectively.

The processes of soil erosion and sediment transport along rivers are the main causes of some socio-economic and environmental problems, such as a reduction in water quality, storage capacity of dams, destruction of aquatic habitats, failure of hydroelectric power plants, and soil degradation. Therefore, understanding the sedimentation status of watersheds is crucial for the effective management of soil and water resources. However, due to the lack of technical and human resources, continuous recording of sediment data is not possible in most sediment measuring stations, and sediment data are recorded only for a few days. In such a situation, a model that can estimate the amount of sediment load using auxiliary variables such as stream discharge and rainfall becomes crucial. Today, it is believed that techniques based on artificial intelligence have a much greater ability to uncover hidden relationships between variables than classical methods and are thus very useful and effective in modeling natural processes.

In this study, various machine learning techniques, including Artificial Neural Network (ANN), Adaptive Fuzzy-Neural Inference System (ANFIS), and Random Forest (RF), were used for sediment load modeling and sediment forecast for days without measurements. To achieve the research objectives, long-term meteorological and hydrometric data ranging from 2000 to 2020 were collected from related organizations and pre-processed before entering the model. The input variables for the models included 24-hour rainfall, flow rate, normalized difference vegetation index, maximum and minimum temperature, and daily suspended sediment as the dependent variable. Prior to modeling, the entire dataset was divided into two parts, training and testing, in a 70:30 ratio. Relationship modeling was performed using the training data, and model validation was conducted using the test dataset. The efficiency of the models was evaluated using two indicators, the coefficient of explanation (R2) and the root mean square error (RMSE). Additionally, morphometric parameters such as form factor (FF), drainage density (DF) coefficient, and relief ratio (RR) were utilized in modeling.

The hydrological analysis of the basin revealed that the highest annual amount of rainfall and erosivity index were recorded at the Sheyvand station in the east of the basin, while the lowest values were observed at the Ramhormoz station. The highest average monthly flow rate of 5.8 cubic meters per second was obtained at the Manjeniq station in April, and at the Mashin station, the highest average monthly flow rate of 8.8 cubic meters per second was recorded in December and January. Morphometrically, the studied basin belonged to the class of elongated basins, sloping basins in terms of relief, and the medium class in terms of drainage density. Analysis of the time series of NDVI index showed that the highest vegetation cover occurred in March, while the lowest values were recorded in September and October. The annual trend of the vegetation index indicated an overall improvement in vegetation cover in the region from 2000 to 2020, with the NDVI value increasing from 0.15 to 0.22. Among the different machine learning techniques studied, the Artificial Neural Network (ANN) model had the highest coefficient of explanation (R2=0.87) and the lowest RMSE for both sediment measuring stations in the region, making it the best model. The optimal inputs for the neural network model at Mashin station were daily average flow adjusted by the basin shape factor, daily rainfall, last day's rainfall, daily minimum temperature and daily maximum temperature. For the Manjeniq station, the optimal inputs were daily average flow, daily rainfall, last day's rainfall, cumulative rainfall for the past two days, and cumulative rainfall for the past three days. The NDVI index was removed from the model due to its low significance. The Random Forest (RF) model ranked second, and the Adaptive Fuzzy-Neural Inference System (ANFIS) model ranked third, with weak performance, especially for the Mashin station, where out-of-range errors occurred. Temporal analysis of sediment values showed that the highest sediment production occurred in December and January for Mashin station and in April for Manjeniq station. The highest production of sediment occurred in 2006 and 2002, and the trend of changes from 2011 to 2018 showed a decline, attributed to consecutive droughts and lack of rainfall. The annual average sediment production calculated using the values estimated with the neural network model was 88017 tons, equivalent to 1 ton per hectare per year.

Overall, this research demonstrated that machine learning methods, especially the neural network model, are highly effective for modeling and predicting sediment on a daily scale. These methods can compensate for the lack of sediment measuring facilities and equipment in most existing hydrometric stations in the country and eliminate the need for continuous sediment data and other water quality parameters. 

 The protection of natural resources, especially land, and their use, has long been considered. It can be said that because land use has undergone many changes over time, these changes have direct and many effects on the ecosystem and the environment and consequently have various consequences, including these consequences that can be used to change land use. The area was affected by the rapid expansion of urbanization and its effects on land-use patterns in the surrounding environment and, finally, land fragmentation in these areas. Accordingly, in many cases, converting land use from its natural state to artificial land use has irreversible consequences. To reduce the consequences, this can be adapted to the land use structure. Land appropriateness refers to matching the capacities of a plot of land and its land use, and the disproportionate allocation of land use and disregard for its changes has many consequences such as socio-economic segregation, environmental depletion, and loss of resources. Decisions in land and resource management should always be guided in a way that does not conflict with the interests of society and the natural environment. In this regard, one of the effective ways to control and minimize the damage and consequences of land use is to adapt its structure so that, based on the characteristics of land resources and their capabilities, the land can be spatially distributed and arranged more rationally. This study aims to identify and zone the appropriateness of land use structure with the existing capabilities in Hamedan and to evaluate the efficiency of the multilayer perceptron neural network method in the field of land use structure optimization in this city.

 In this study, to adapt the land use structure in the city of Hamedan, based on the research background and according to the effective criteria in the field of land use structure, various indicators were selected, including 12 land use indicators, slope, average temperature, and average rainfall. Average humidity, average wind speed, geology, soil type, distance from the river, distance from wells, distance from main roads, and vegetation type. Then, using the field visit, the points with user suitability were registered as educational points. After preparing the layers of the mentioned indicators, these layers were standardized in the software environment of the GIS system. In the next step, the multilayer perceptron neural network uses the after-release algorithm by importing layers affecting the optimization of the land use structure as input and using the middle layer of distance. From appropriate points in terms of land use structure, this network was implemented with the structure of 1-10-12 to adapt the land use structure in Hamedan. From 35% of the total image pixels, the distance from the agricultural proportions as training points falls into three categories the first part (70%) for network training, the second part (15%) for stopping calculations when the error is increasing, and the third part (15%) was used for network verification. Finally, the final land suitability map was drawn. The resulting layer had a value between 0 and 1 which was divided into five land suitability classes. In the present study, after identifying the factors affecting the land use structure and adapting its structure, and preparing each of them, the mentioned layers were standardized. Then, using the field visit, the points with appropriate use were recorded as educational points. Thus, the land use structure was adjusted by the multilayer perceptron neural network model with 58 replications. The results of the neural network validation and the resulting output layer indicate the high accuracy of the network in fitting the land use structure so that the square root mean values of error (RMSE), and absolute error (MAE). Correlation coefficient (R2) in the implementation process of the network is equal to 0.19, 0.21, and 0.89, respectively, indicating the network's high accuracy in implementing the optimizing process. Completely inappropriately divided, and the results showed that most of the areas covered some somewhat suitable and perfectly suitable lands with 32.62 and 28.13% of the total area, respectively.

 In the present study, after identifying the factors affecting the land use structure and adapting its structure, and preparing each of them, the mentioned layers were standardized. Then, using the field visit, the points with appropriate use were recorded as educational points. Thus, the land use structure was adjusted by the model of a multilayer perceptron neural network with 58 replications. The results of the neural network validation and the resulting output layer indicate the high accuracy of the network in fitting the land use structure so that the square root mean values of error (RMSE), and absolute error (MAE). The correlation coefficient (R2) in the implementation process of the network is equal to 0.19, 0.21, and 0.89, respectively, which indicates the network's high accuracy in the implementation of the optimizing process. Completely inappropriately divided, and the results showed that most of the areas covered some somewhat suitable and perfectly suitable lands with 32.62 and 28.13% of the total area, respectively.

 The results of optimizing land use structure in Hamedan show that most of the area is not suitable for agricultural activities in terms of effective factors. In this area, most urban land uses completely barren and uncultivable lands, lands. There are mountainous, rocky, and low-quality pastures, mainly in the western and southwestern areas of Hamedan. Also, in this area, lands that have been relatively suitable in terms of a proportion are quite suitable in terms of 12 factors in the best conditions for agricultural and horticultural activities and are the best place for developing agricultural activities. Thus, to change the land use conditions towards a more appropriate trend while paying attention to integrated urban-rural planning for Hamedan and its surrounding settlements. It is recommended to pay attention to land use planning rural-urban plans and projects because the rapid expansion of Hamedan and its suburban spaces has created numerous challenges in terms of land suitability. In such a way that about 23.1% of the lands are ready to be transformed into unsuitable and completely unsuitable conditions. In addition, 32.62% of land use is subject to change to semi-suitable conditions. Based on what has been said, controlling, supervising, and directing the constructions and preventing the over-horizontal expansion of the city of Hamedan and its surrounding spaces by urban and rural stakeholders (local management) is proposed to rangeland and agricultural lands. The findings of the study also indicated that the highest area of land in this area is related to somewhat suitable and perfectly suitable land and the lowest area belongs to unsuitable and somewhat unsuitable land. Therefore, it can be said that the city of Hamedan is currently in a semi-suitable situation in terms of land suitability, which can have a more favorable trend in the future with proper planning and policies.

A drought crisis is a dry period of climate that can occur anywhere globally and with any climate. Although this crisis starts slowly, it can have a serious impact on health, agricultural products, the economy, energy, and the environment for a long time to come. Drought severely threatens human livelihood and health and increases the risk of various diseases. Therefore, modeling and predicting drought is one of the most important and serious issues in the scientific community. In the past, mathematical and statistical models such as simple regression, Auto-regression (AR), moving average (MA), and ARIMA were used to model the drought. In recent years, machine learning methods and computational intelligence to model and predict drought have been of great interest to scientists. Computational intelligence algorithms that have been previously considered by scientists to model drought include multilayer perceptron neural network, RBF neural network, support vector machine, fuzzy, and ANFIS methods. In this research, the purpose of modeling and predicting drought is by using three neural network algorithms, including multilayer perceptron, RBF neural network, and generalized regression neural. The drought index used in this research is the standardized precipitation index (SPI). In this research, the wavelet technique in combination with artificial neural network algorithms for modeling and predicting drought in 10 synoptic stations in Iran (Abadan, Babolsar, Bandar Abbas, Kerman, Mashhad, Rasht, Saqez, Tehran, Tabriz, and Zahedan) have been used in different climates and with suitable spatial distribution throughout Iran.

This study, initially using monthly precipitation data between 1961 and 2017, SPI drought index in time scales of 3, 6, 12, 18, 24, and 48 months through programming in soft environment MATLAB software implemented. The results of this step were validated using the available scientific software MDM and Drinc. Then, prediction models were designed using the Markov chain. In this study, a total of six computational intelligence models, including three single models of multilayer perceptron neural network (MLP), radial basis function neural network (RBF), and generalized regression neural network (GRNN), and three hybrids wavelet models with these three models (WMLP-WRBF-WGRNN) have been used to model and predict the SPI index in 10 stations of this research. In implementing all these six models, the MATLAB software programming environment has been used. In this study, four types of discrete wavelets were used, including Daubechies, Symlets, Coiflets, and Biorthogonal. Due to the better performance of the Dobbies wavelet, this type of wavelet was used as a final option in the research. In the Daubechies wavelet used between levels 1 to 45, level 3 showed the best performance among different SPI time scales; therefore, the Daubechies level 3 wavelet was used in all hybrid models of this study. After training all six algorithms used, the evaluation criteria of coefficient of determination (R2) and root mean square error (RMSE) was used to measure the difference between actual and estimated values.

The results of this study showed that computational intelligence methods have high accuracy in modeling and predicting the SPI drought index. In the first stage, the results showed that the individual MLP, RBF, and GRNN models, if properly trained, have close results in modeling and predicting the SPI drought index. In the next step, it was observed that the wavelet technique would improve the modeling results. In using the wavelet technique in combination with three single models MLP, RBF, and GRNN, the choice of wavelet type is also more effective in modeling, so in this research, the first of the four types of discrete wavelets Daubechies, Symlet, Qoiflet, and Biorthogonal in combination with Three single models of this research were used and the results of these four types of wavelets showed the relative superiority of the Daubechies wavelet over the other three wavelets. In using the Daubechies wavelet, since this wavelet has 45 times and the choice of order was also effective in modeling, it was observed by testing the wavelet 45 times that the 3rd wavelet, in general, has higher accuracy in all time scales of SPI index, 3, 6, 12, 18, 24 and 48 months and also in all three algorithms MLP, RBF, and GRNN. Therefore, in this research, the third-order Daubechies wavelet was used in all three algorithms of this research, as well as in all time scales. The results showed that combining the wavelet technique with all three models MLP, RBF, and GRNN will improve the results. The research graphs showed that for the quarterly time scale, the values obtained from the single model prediction in MLP and RBF modeling have a somewhat one-month phase difference compared to the hybrid model, while in the GRNN model, this prediction difference is negligible. The modeling results for both single and hybrid modeling modes indicate that there is no phase difference between the single and hybrid modeling methods in time scales of 6, 12, 18, 24, and 48. For the 12- and 24-month time scales, the single GRNN model had more fluctuations and errors in SPI monthly modeling and forecasting, while the hybrid model in these two-time scales had much better behavior in monthly modeling and forecasting. Distribution diagrams of data related to observational SPI of Abadan station showed that the modeling results for single and hybrid modes in 3 and 6-month time scales are less accurate than other time scales and fit line separation, and its uncertainty is higher than others. However, in all neural network models and in all time scales, the hybrid method has shown more accuracy. The numerical results of the study indicate that in all SPIs and stations under study, the differential values of R2 are positive, which indicates higher values of R2 in the hybrid model than in single neural network modeling, which indicates an improvement in hybrid modeling compared to individual models. Also, the differential values of RMSE are negative in all studied models and stations, which indicates that the amount of RMSE in predicting hybrid models is lower than individual neural network models. In the research graphs, it can be seen that the amount of differences in RMSE and R2 indicates a greater difference in time scales 3 and 6 than the time scales 12, 18, 24, and 48, which somehow goes back to the nature of the data of these time scales. The most significant improvement in R2 and RMSE is from the 3-month low to the 48-month high, respectively.

 From the findings of this study, it can be concluded that artificial neural network algorithms are efficient methods for modeling and predicting the SPI drought index. The use of wavelets in all three models of artificial neural networks will also improve the results. It can also be concluded that for better modeling of the SPI drought index, it is necessary to select the optimal wavelet type and order. From the results of this study, it can be concluded that the wavelet technique has a greater impact on the lower time scales, i.e., 3 and 6 months, than the higher scales, i.e., 24 and 48 months.

In this study, we investigated the effects of forest operation on runoff and sediment using small-scale plots. The runoff and sediment samples were collected from 36 sample plots with dimensions of one by two meters in different areas of the operation. We used the Multi-Layer Perceptron (MLP) for modeling, with 65% of the data for training, 10% for validation, and 25% for testing. We evaluated the accuracy of the model using the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE), and compared our results with optimized models obtained through trial and error. We collected information and produced runoff and sediment maps using GIS. Our results showed that the most important factors affecting runoff production were soil bulk density, rainfall intensity, slope, rainfall values, percentage of grass cover, and canopy cover percentage. For sediment, the most important factors were rainfall intensity, soil bulk density, slope percentage, and surface cover percentage. The MSE and R values for runoff modeling were 0.009 and 0.9 in the training stage and 0.01 and 0.82 in the test stage, respectively. For sediment modeling, the MSE and R values were 0.01 and 0.86 in the training stage and 4.3 and 0.8 in the test stage, respectively. Our results showed that neural networks have high capability in modeling runoff and sediment in forest lands. We also conducted an overlap analysis to measure the accuracy, precision, and efficiency of the results and methods presented in our study. Therefore, the proposed model can be used to combine ANN and GIS in the simulation and modeling of runoff and sediment in forest areas."

The Present article examines factors that have effect on saffron warehouse receipt and on saffron futures in Iran commodity exchange. This study tries to identify the import of saffron future price and the two-way communication between these two financial instruments (saffron warehouse receipt and saffron futures) to saffron market.

In this regard, this study seeks to answer the existence of the relationship between linear and non-linear causality between these two financial instruments. The data were obtained daily in the period from June 2018 to July 2019 using price fluctuations in saffron warehouse receipt and saffron futures. Descriptive – analytical research methods and library data collection methods, regression models and the concept of neural networks with the help of Eviews software and R Economic Statistical Software were used. The price fluctuations of saffron warehouse receipt have been extracted using Arch family models.

Results indicate that there is a two linear causality relationship between warehouse receipt’s price fluctuation and future’s price fluctuation. To investigate the existence of non-linear causality between the two under studied, variables VAR model residual was used. The BDS test result show the existence of a non-linear relationship between the mentioned variables. The results of the non-linear granger causality test based on neural network show that futures price are the cause for price fluctuations in saffron warehouse receipt.

It can be stated that price discovery is formed in saffron future market and saffron warehouse receipt market follows the futures market.

Precipitation is one of the most important climatic phenomena affecting the globe. In each round of rainfall, only a part of the rainfall is used by the plant, and the rest is removed from the reach of the plant through different ways such as runoff and passing through the root zone. For this purpose, the concept of effective rainfall is used to express the part of the precipitation that directly responds to the plant's water needs. Estimating effective rainfall is one of the essential components in water resources management, irrigation planning decisions, and a guiding factor for crop production estimation. To make the best possible use of rainfall for the agricultural sector in rainfed lands, estimating the effective rainfall is vital. Since the only source of water supply for rainfed crops is rainfall and the yield of rainfed crops depends on the amount of water absorbed by the plant, almost all of the effective rainfall is spent on evapotranspiration. Therefore, the purpose of this research is to estimate the amount of effective precipitation through the estimation of the evapotranspiration rate of rainfed crops and also to develop a model of effective precipitation estimation based on an artificial neural network.

Considering the importance of estimating the effective rainfall and since rainfall is the only source of water supply for rainfed crops and the yield of rainfed crops is dependent on the amount of water absorbed by the plant, almost all of the effective rainfall is spent on evapotranspiration. Therefore, to more accurately estimate the effective rainfall, by having the yield of rainfed crops for a region and using the relationship between evapotranspiration and crop yield, it is possible to obtain the actual evapotranspiration ration and, as a result, the effective rainfall amount. The study area of ​​this research is Kermanshah Province, one of the western Provinces of Iran, where extensive rainfed crops are cultivated every year. The meteorological parameters of 10 meteorological stations in Kermanshah Province were received and calculated a result of the weather condition of Kermanshah Province. Then, the potential evapotranspiration was calculated using meteorological parameters and CROPWAT software. In addition, the amount of cultivated area (ha) and the amount of production (t) of rainfed wheat in Kermanshah Province were extracted from the agricultural statistical yearbooks, and the yield of rainfed wheat for 14 crop years (crop years 2005 to 2019) was calculated. Then, with the crop factor and potential evapotranspiration rate in hand, using the Doorenbos and Kassam equation, the actual rate of evaporation and transpiration during the crop growth period for the aforementioned 14 agricultural years was estimated. Then the correlation between effective precipitation and meteorological parameters (such as maximum temperature, minimum temperature, humidity, wind speed, sunshine hours, growing degree days, and precipitation) was investigated and the most effective parameters were used to develop a model using feedforward neural network (FFNN). 5 networks were developed under different scenarios (with different inputs and outputs of effective precipitation) and the error of the networks was evaluated with the evaluation criteria of root mean square error (RMSE), mean bias error (MBE) and index of agreement (D). Finally, the best network with the least error was introduced to predict effective rainfall.

The total rainfall during the growing period of the dry wheat crop in crop years varied between 204.59 and 748.79 mm and the yield of the crop varied between 0.3 and 1.63 t ha-1. The results showed that the highest amount of yield in crop years is not related to the highest amount of rainfall and this result increases the importance of estimating the effective rainfall. The results show that the amount of effective precipitation estimated using Doorenbos and Kassam's equation during the studied period (14 years) and during the growth of the dry wheat crop varied between 119.85 and 279.90 mm. Then, in order to accurately estimate, an effective rainfall estimation model was created in Kermanshah Province with the help of a neural network. In this model, the effect of each of the meteorological parameters on the effective precipitation estimated by the inverse solution method was investigated with the Pearson correlation method, and the most effective parameters were used for modeling in several scenarios. Among all the meteorological parameters such as temperature, humidity, sunshine hours, wind speed, growing degree days (GDD), and precipitation, the precipitation parameter with a correlation of 0.99 was recognized as the most effective parameter in estimating effective precipitation. Meteorological parameters were prioritized based on correlations and used for modeling by a neural network. Then, networks were trained under different scenarios (various inputs individually and together), among which the network with rainfall input had the best performance in estimating effective rainfall. R^2 (Coefficient of Determination) of effective rainfall prediction with the help of this model was estimated to be 0.99 and its RMSE (root mean square error) and MBE (mean bias error) value was 4.61 and -1.4 mm and index of agreement (D) was estimated 0.997.

In order to use water optimally in agriculture and drainage projects, it is necessary to know and estimate effective rainfall. Several experimental methods have been presented to estimate effective precipitation. However, considering that these experimental methods were developed for areas with special characteristics and their generalization to all areas is not error-free, in this research effective precipitation was estimated by the inverse solution method, and a suitable model was used. Meteorological information and information from crop yearbooks and CROPWAT software were used to calculate effective precipitation by the inverse solution method. In order to present a model based on artificial intelligence, the correlation of meteorological variables with effective precipitation was investigated. Finally, a model based on a neural network was proposed in Kermanshah Province to estimate effective rainfall. The results of this research showed that neural networks, which are based on mathematical and natural theories, are more successful in predicting effective rainfall based on the amount of rainfall directly.

In free overfall spillways, waterfalls over the crown of the spillway almost vertically and impacts the downstream bed of the dams. Due to the high velocity and energy of the flow which impacts the erodible downstream bed, it may cause scouring close to the foundation of the dam and consequently threaten the stability of the dam.

In this study, artificial intelligence methods were used to estimate the scour depth of slope control structures with sharp-crested weir due to the complexity of the phenomenon. Three models including neural network, adaptive fuzzy neural system, and support vector machine (SVM) were used as artificial intelligence or black-box model to solve the problem..

The results showed that artificial intelligence methods are more efficient than conventional experimental methods in estimating the depth of downstream scours of slope control structures with sharp-crested weir. Using more parameters in the input of artificial intelligence models does not increase the accuracy of these models. It is because of increasing errors as a result of using more parameters in these models. In estimating the downstream scour depth of slope control structures with the sharp-crested weir in both calibration and validation stages, an adaptive fuzzy neural system model is up to 20% more reliable than the artificial neural network model and up to 8.5% than the support vector machine model.

The preparation of geological maps based on field data and the application of aerial photographs have always been an error because of the structural diversity of the earth and the difficulty of accessing certain regions. But in recent decades, the use of satellite imagery has but in recent decades, the use of satellite imagery has gone a long way to increasing the accuracy and timeliness of geological mapping. The purpose of the current study is to investigate the applicability of Landsat 8 satellite images and object-oriented pixel classification methods in mapping the geological formations of some part of the Shirkuh Mountain range in Yazd province. This area is part of the scattered mountain range of Central Iran with a dry climate and minimal vegetation. Initially, enhanced operations were performed to identify geological information’s using MNF, PCA and FCC processing. Then, the images were classified using object-oriented algorithms (BAYES, SVM, KNN, Decision Tree and Random Forest), neural network (ARTMAP, RBF, MLP and SOM), and base pixels (Maximum Likelihood, Minimum Distance, Mahalanobis and SAM). Next, the error rate of each method was calculated using Boolean logic and kappa coefficient. The results showed that the maximum probability classification with kappa coefficient of 75% in the base pixel category, Fuzzy ARTMAP classification in neural network method with kappa coefficient of 72% and Bayesian classification in object-oriented method with kappa coefficient of 82% have the best results among other methods. These results show that the methods mentioned in the identification and separation of geological formations are effective. The SAM of pixel-based methods, SOM of neural network methods and RF of object-oriented methods with 49%, 64% and 61%, respectively, showed the lowest accuracy in each category.

Precipitation is one of the most significant climatic parameters; its distribution and values in different areas is the result of complex linear and nonlinear relationships between atmospheric elements-climatic processes and the spatial structure of the earth's surface environment. Classification of data and placing them in small and homogeneous zones can be effective in improving the understanding of these complex relationships and their results. In the present study, zoning and analyzing the distribution of rainfall in Iran concerning environmental factors was performed using the annual precipitation data of 3423 synoptic, climatological, and gauge stations in the country during the period from 1961 to 2015 and the altitude, slope, aspect, and station density data. After standardization and preparation of the data matrix, the optimal number of clusters was determined and the data set was entered into the neural-fuzzy network model (ANFIS-FCM). The results showed that the values of R2  and MAE  indices were 0.76 and 0.23, respectively which indicate the appropriate accuracy of the model. It was also found that in the four output zones of the model, environmental factors have a high impact on the spatial distribution of precipitation. In the first and third zones, the combination of high altitude and slope factors along with geographical proximity to precipitation systems has caused the average annual rainfall in these zones to be 318 and 181 mm, respectively. The mean annual rainfall has decreased to about 100 mm by the weakening of the role of environmental factors in the second and fourth clusters.

Understanding the Stage–Discharge relationship is of great importance in the management and planning of water resources, as well as the design of hydraulic structures, the organization of rivers, and the planning of flood warning systems. With the advancement of science and increasing the speed of computing, new methods called intelligent systems have been introduced, the use of which can be a better option for modeling. In this research, Fuzzy-GMDH, RBF and ANFIS combined intelligent methods have been used, respectively. The Fuzzy-GMDH method, which is a combination of two techniques of fuzzy logic (Fuzzy) and Group Method of Data Handling (GMDH) for flow-prediction. To study the proposed model, real and normalized data of Mand River located in Bushehr province were used and the results were compared with two methods of RBF and ANFIS neural networks. First, important parameters were determined using sensitivity analysis and then the mentioned methods were evaluated and compared with statistical indicators such as Nash coefficient (NASH). The results showed that the raw data in the Fuzzy-GMDH method with a value of NASH = 0.8822, offers higher accuracy than normal data (NASH = 0.8888). On the other hand, the Fuzzy-GMDH model has a better performance in predicting discharge daily than the other two methods with flow coefficient values of 0.8555 and 0.8776, respectively.