نشریه دانش آب و خاک
سال سی و سوم شماره 4 (زمستان 1402)

Evaporation is one of the most important factors in the hydrological cycle and is one of the determinants of energy equations at the ground level and water balance, which is estimated in various fields such as meteorology, hydrology, agriculture, and water resources management. Evaporation is also one of the main causes of water loss and stress on water resources. Therefore, knowing its amount as one of the hydrological variables is very important in agricultural research and soil and water conservation and modeling. Evaporation is a physical process that has a direct and close relation with atmospheric factors, the most important of which are temperature, wind speed, relative humidity and solar radiation. Researchers have been able to analyze evaporation using mathematical and empirical methods and their combination, as well as using intelligent neural methods. Due to the importance of evaporation in the water cycle and its effect on the quantity and quality of surface water resources, the study and accurate knowledge of this phenomenon is one of the important issues in the study of water resources. Using pan evaporation is one of the most common methods of estimating evaporation. But in most areas, the number of evaporating stations is not enough and they do not have suitable spatial distribution. Therefore, indirect methods such as hybrid relations, intelligent neural systems, data mining methods and remote sensing techniques have been considered by researchers.

In the present study, the evaporation of free water zones in the Urmia Lake basin has been estimated. For this purpose, the efficiency of combined empirical methods including deBruin, Tichomirov, Penman and Meyer as well as intelligent neural methods including artificial neural networks (ANN), random forests (RF) and gradient boosted trees (GBT) were compared and evaluated using statistical indices of R, NRMSE, MAPE and also Taylor diagram. Moreover, in order to increase the accuracy and efficiency of the combined methods, these relations were calibrated for the Urmia Lake basin. In order to evaluate the different combinations of meteorological variables to estimate the evaporation of free water zones in intelligent neural systems, 14 scenarios were considered with the aim of increasing the accuracy of evaporation estimation. In these scenarios, various combinations of meteorological parameters were defined that were used as variables of the combined empirical relations to estimate evaporation of free water zones. Also, pan evaporation data were used to estimate the rate of evaporation of free water zones by applying the pan coefficient and the obtained results were used as a basis for evaluating combined methods and intelligent neural systems.

The results showed that among the studied combined methods at six considered stations, the deBruin method is more accurate than other methods. Only in Tekab station, the Meyer method with NMRSE value of 30.00% and MAPE of 19.99% had higher accuracy. After calibrating the relations, the deBruin method also had the highest accuracy in all stations compared to other relations. Among the intelligent neural methods in 4 of 7 studied stations, the ANN method was introduced as the best and most accurate intelligent method for estimating evaporation of free water levels. In Maragheh, Mahabad and Sarab stations, RF method had the highest accuracy, while in all of the stations, the GBT method had the weakest performance.

Despite the overall improvement in the results of the evaporation estimation and the reduction of the error values of the calibrated empirical combined relations, the NMRSE values indicated different efficiencies of the combined relations in estimating the evaporation of free water zones. So, the calibrated combined relations were not accurate at any of the stations. Moreover, evaluating the results of intelligent neural methods indicated the high accuracy of them compared to combined relations in estimating evaporation of free zones of water. Also, the obtained results showed that the temperature and radiation parameters in the model obtained from the best scenario of intelligent methods have been used in all stations, which indicated the importance of these two parameters in evaporation modeling. Also, the results showed that although the calibration of the relations generally improved the accuracy of the combined relations; however, according to the statistical analysis, the combined relations did not have the suitable accuracy in estimating evaporation. Therefore, the use of intelligent neural systems in estimating evaporation of free zones of water was recommended. Among all of the studied methods, the ANN method had the highest accuracy in estimating the pan evaporation. Thus, this method was introduced as an accurate model in 4 stations with NRMSE values less than 10%.

Artificial intelligence models as powerful methods in modeling nonlinear complex problems, have a significant ability and this has been proven in numerous articles. Artificial intelligence has been used in various issues, including engineering, medicine, etc. The success of this method in comparison with analytical and numerical methods, their easiness, speed and accuracy caused to open their place among researchers as much as possible. Today, Considering that one of the challenges of human life is the issues related to water resources management, so in this study, an attempt has been made to investigate the performance of artificial intelligence and regression models in the cases of water resources. Various researches have been done in the case of modeling and parametric analysis of water resources. However, in this study, artificial intelligence (Learning Machine) models were used to simulate the qualitative and quantitative parameters of water. The models used in this study are: Self-Adapting Extreme Learning Machine (SAELM), Least Square Support Vector Machine (LSSVR), Adaptive Neuro Fuzzy Inference System (ANFIS) and Multiple Linear Regression (MLR) model which was used to predict changes in hydrogeological parameters. Today, due to the growing global population, one of the most important challenges is access to safe drinking water. In our country, Iran, due to its location in the semi-arid region and low rainfall, this danger is felt more than ever. One of the serious issues is the salinity leakage into groundwater resources. In this study, an attempt has been made to simulate the leakage of salinity dynamic flow into the freshwater resources of the coastal aquifer, using artificial intelligence and statistical models. At the end, the simulation results and the accuracy of the models are given. The study area in this work, is Mighan Wetland and Mighan aquifer in Markazi province. Annual rainfall occurs in small amounts in this area. According to the statistical results provided by synoptic and rain gauge stations in the region, the maximum and minimum rainfall values range from 461 mm in the northeast to 208 mm in the center of Arak plain. The hydraulic outlet of the aquifer to the Mighan plain is located in the center of the plain. The water entering the Mighan plain and leaves the system due to evaporation from the water table. Observatory wells were used to sampling this lake due to its saline water. The wells were located in an area called Vismeh near the lake.

In this study, qualitative and quantitative parameters: water salinity, total dissolved solids (TDS), chlorine ion (cl), sampling time (t), electrical conductivity (EC), Salinity and groundwater level (GWL) were simulated. In this work, Adaptive Neuro Fuzzy Inference System (ANFIS), Least square support vector machine (LSSVM), Self Adaptive Extreme learning machine (SAELM) and Multiple linear regression (MLR) models were used for simulation. In this study, data from 173 months of sampling were used. 70% of the sample size was used for training and 30% for testing models.

Simulation was performed using artificial intelligence models and regression model. The simulation results showed higher accuracy of artificial intelligence models. After simulation and obtaining the results, then the uncertainty analysis was performed by Wilson Score method without continuity correction. In this method, the prediction error (ei), the mean prediction error (Mean) and the standard deviation of the error is (Se). If the mean error value of a model in predicting the target variable is positive, it means that the performance of the model is Over Estimated. Also, if the average value of the model error is negative, the performance of the model is Under Estimated. Moreover, the results of Uncertainty Analysis with a significance of 5% were obtained. and finally we briefly write the subsequent performance Over Estimated (OS) and Under Estimated (US).

The results showed that different models were successful in predicting water parameters. In order to comprehensively evaluate the accuracy of the models in the simulation, the performance of the models was measured by five approaches. The proposed approaches were: 1) Evaluation of prediction by accuracy chart, 2) Performance evaluation by mathematical indices, 3) Performance evaluation, by Uncertainty Analysis by Wilson Score method without continuity correction, 4) Accuracy evaluation by error distribution charts and 5) Performance evaluation by discrepancy rate (DR) charts. Finally, all the results are given at the end of each section, respectively.Approach 1- According to the prediction accuracy charts, 16 charts were drawn and the most accurate models of which are depicted in Figures 4 to 7. After modeling, the results showed that the most accurate models in simulating groundwater parameters were SAELM model in GWL simulation. According to the results, SAELM model in GWL and EC simulation, LSSVM in TDS simulation and MLR in Salinity simulation were the superior midel, Respectively.Approach 2- According to the performance measurement indices, finally the results showed that SAELM model was the best model in simulating parameters (EC) and (GWL). The LSSVM model was also the most accurate model in modeling (TDS). MLR model was the best model in (Salinity) parameter simulation.Approach 3- Uncertainty analysis was performed based on Wilson score method. The performance of the models in the simulation showed that the performance of the SAELM model was determined as Under estimated and other superior models in simulation had Over estimated performance.Approach 4- Based on the error distribution diagrams, the best accuracy was assigned to SAELM and MLR models.Approach 5- Based on the discrepancy ratio, SAELM and MLR models were estimated to be the most accurate models in the simulation.

Reference evapotranspiration (ET0) is an important parameter in the interactions among soil, vegetation, atmosphere, surface energy and water. Direct measurement of evapotranspiration values is costly and time consuming. On the other hand, modeling this complex process in which many variables interact with each other is not feasible without considering multiple assumptions. In this regard, the FAO Penman-Monteith method is used in a wide range of climatic and environmental conditions. One of the weaknesses of FAO Penman-Monteith method is its dependence on various meteorological parameters. Therefore, it is necessary to implement methods with lower meteorological variables that can estimate ET0 with suitable accuracy. Thus, in the present study, an attempt was made to estimate ET0 with acceptable accuracy using machine learning models.

In the present study, daily meteorological parameters in the time period of 2000-2020 including maximum and minimum air temperature (Tmax, Tmin), mean temperature (T), wind speed (U2), average relative humidity (RH), maximum and minimum relative humidity (RHmax, RHmin) and sunshine hours (n) were obtained on a daily basis in three stations of East Azerbaijan province (Tabriz, Sarab, and Maragheh). Moreover, six scenarios were defined as input combinations. Then, using random forest (RF) method in two cases: Single random forest and using the genetic algorithm (GA) to optimize its effective parameters with considering the FAO Penman-Monteith model as a basis, the machine learning models were calibrated and validated for estimating ET0 values at studied stations. Furthermore, the performance of empirical equations in three groups based on temperature (Hargreaves, Blaney-Criddle and Romanenko), radiation (Irmak) and mass transfer (Meyer) were also investigated. It should be noted that 75% of the data were considered for calibration and 25% for the validation of machine learning methods. Finally, using the statistical criteria of correlation coefficient (CC), scattered index (SI) and Willmott’s Index of agreement (WI), a suitable machine learning method was introduced to estimate the reference evapotranspiration. Also, the most suitable combination of meteorological parameters for ET0 estimation was suggested.

The obtained results showed that in all studied stations, scenario 6 has the best performance, either in the case of single random forest (RF) or in the case of random forest optimized by genetic algorithm (GA-RF). Meteorological parameters of this scenario include minimum and maximum air temperature, minimum and maximum relative humidity, sunshine hours and wind speed. By optimizing the RF-6 parameters with the genetic algorithm at Tabriz station, the statistical criteria were improved (CC from 0.990 to 0.991, SI from 0.103 to 0.098). At Sarab station, the CC was increased from 0.980 to 0.982, the SI was decreased from 0.140 to 0.132 and the WI was increased from 0.989 to 0.990. At Maragheh station, CC was increased from 0.990 to 0.991, SI was decreased from 0.103 to 0.098 and WI remained unchanged at 0.995. In general, the decreasing trend of the scattered index for RF method from scenarios 1 to 6 can be understood by increasing the input parameters of the random forest method. Among the three groups of empirical methods based on air temperature, radiation and mass transfer for estimating ET0, the best performance was seen for the Blaney-Criddle method based on air temperature. In all studied stations, the GA-RF model showed better performance than the empirical methods. Also, GA-RF-5 with similar meteorological parameters with Blaney-Criddle method provided accurate ET0 estimations.

Determining the amount of daily evapotranspiration and consequently accurate estimation of water requirement of plants provide the basis for proper designing of irrigation systems by reducing installation costs and providing a suitable program for the use of water resources in the agriculture sector. So, in the present study, meteorological data from Tabriz, Sarab and Maragheh stations were used to evaluate the ability of machine learning methods including RF and GA-RF to estimate the values of reference evapotranspiration. The results showed the high accuracies of RF-6 and GA-RF-6 for all studied stations and Belany-criddel among the empirical models. In a more detailed look, the genetic algorithm had positive effects on increasing the model accuracies by reducing scattered index of GA-RF scenarios 1, 4, 5 and 6 in Tabriz and Maragheh stations as well as scenarios 1, 5 and 6 at Sarab station. Finally, it can be concluded that both RF and GA-RF models provided the most accurate estimates of daily reference evapotranspiration in the East Azerbaijan province.

Due to water resources shortage, better agricultural water using is one of the most important challenges facing the agricultural water sector. Today, the use of pressurized irrigation systems such as tape irrigation system is one of the best ways to improve agricultural water use. Due to increasing use of tape irrigation systems in row crops and the importance of understanding how to distribute moisture and salts in these irrigation methods, the purpose of this study is to use HYDRUS -2D software for simulation. The geometry of the flow and movement of water and solutes in the soil was tape irrigation method. For this purpose, while modeling the flow geometry by two-dimensional HYDRUS -2D software using observational data obtained from field experiments, hydraulic parameters and soil solute transfer were optimized by reverse solution method.

The experiments were performed on corn plants in the Research Farm of the Department of Water Science and Engineering, Imam Khomeini International University, located in Qazvin. The experiment started in August 2020 and ended in mid-November after 105 days of corn growth period. Corn was cultivated in plots with an area of ​​9 square meters with dimensions of 3.3 meter. The distance between planting rows was 75 cm and the distance between corn seeds on the ridges was 30 cm. The irrigation tape used in the experiment was of the plate type tape and the discharge of each plate at the operating pressure of the experiment was measured as 1.3 liters per hour. The distance between the plates on the irrigation strip was 25 cm. Profile probe PR2 was used to measure soil moisture to determine the time and duration of irrigation. To do this, in the middle of each plot and to a depth of one meter, the tubes of the device were placed by using the auger. Due to the high price of the device and for economical use, high pressure polyvinyl pipes with an internal diameter of 26 mm, were used which had already been calibrated. To save and reduce the volume of operations, assuming the soil is homogeneous, harvests were made on one side of the ridge. The HYDRUS -2D software package uses the numerical solution of the Richards equation to analyze the motion of water in a porous medium in the saturated and unsaturated states. The HYDRUS -2D uses various models to estimate soil hydraulic parameters. In the mentioned model, the initial guess values ​​of soil hydraulic parameters are estimated using a neural network paired in a model called Rosetta and soil information such as texture and percentage of its components and some moisture points in the soil characteristic curve.

The results showed that although HYDRUS -2D model has a high ability to simulate the movement of water in porous media, however, this issue is directly related to the accuracy of the flow geometry and the limitations of the HYDRUS -2D model regarding the definition of irrigation systems should be considered. In addition, to evaluate the accuracy of data estimates by the model, it is not enough to just check the appropriateness of statistical indicators. The estimation of the model from the soil moisture characteristic curve as well as the water balance given to the model should be controlled. In the conditions of this research, the best result was obtained when the length of nodes with variable flow boundary condition was equal to 3.14 cm. For optimizing soil hydraulic parameters, NRMSE statistical indices of 9.3%, RMSE of 0.025 (cm3 cm-3) and MSE of 0.00066 (cm3 cm-3) show excellent model simulation. In addition, the water balance given to the model by the software was calculated to be equal to 285 liters, which was close to the actual amount of water given to the ground, i.e. 253 liters. The values ​​of the above indices for optimizing the parameters of solute transfer in soil were 22.2%, 0.17 (mg cm-3) and 0.028 (mg cm-3), respectively.

For evaluating the accuracy of the results presented by the model, it is not enough to just place the statistical indicators in the appropriate range and judge the results based on it, but also to control the initial conditions, soil moisture limits and also compare the volume of water. The data given by the model with the actual volume of water given are among the items that should be checked. Based on the results of this study, the accuracy of the water balance presented by the model is directly related to the length of nodes with variable flow conditions. Therefore, it seems necessary to study and determine the optimal length of nodes with variable flow boundary conditions before performing any simulation operation.

The alfalfa plant with the scientific name Medicago sativa L is considered the most important fodder plant in the world and it is a very high quality fodder suitable for all kinds of livestock (Kirimi, 2002). Alfalfa fodder plant is known as the queen of fodder plants in terms of nutritional value and palatability due to the variety of species compared to other fodder plants (Toran et al., 2017). In Iran, the area under alfalfa cultivation is 340,767 hectares and its production amount is 3,551,850 tons, and in Ardabil province, the area under alfalfa cultivation is 9,065 hectares and the annual production amount of alfalfa is 63,105 tons (Ministry of Jihad Agriculture, 2020). Examining weather data and their effect on plants is one of the most important factors in increasing productivity. Therefore, each area has potential and limitations regarding crop cultivation that is compatible with a specific climate, which studies the feasibility of suitable areas for cultivation. The main goal of this research is to locate alfalfa fodder cultivation in Ardabil province using water and meteorological criteria during alfalfa growth period. The difference between the present research and other studies in this field is that it studies the efficiency of four methods during the alfalfa fodder growth period.

Ardabil province is located in the northwest of Iran, and its location is in the latitude of 37 degrees and 45 minutes to 39 degrees and 42 minutes of north latitude and the geographical longitude of 47 degrees and 3 minutes to 48 degrees and 55 minutes of east longitude. In this research, from the data of annual precipitation, average annual temperature, minimum annual temperature and maximum annual temperature, six synoptic stations during the statistical period (1990 to 2020) and the height and slope of the land, as well as from the software; ARC GIS, Export Choice and Super Decision have been used. In order to weight and locate alfalfa crops, the methods of Analytical Hierarchy Process (AHP), Analytical Network Model (ANP), Fuzzy Hierarchical Process (FAHP) and Weighted Method (WLC) have been used.

In this research, alfalfa fodder cultivation location in Ardabil province was evaluated and investigated using AHP, FAHP, ANP and WLC methods. In the AHP method, the results with ExportChoice software analysis showed that annual precipitation with a weight of 0.377, average temperature with a weight of 0.258, and maximum temperature with a weight of 0.112 were respectively recognized as the most important criteria during the alfalfa growth period. The results of the FAHP method study showed that precipitation with a weight of 0.367, average temperature with a weight of 0.259, and minimum temperature with a weight of 0.105 are respectively effective in the stages of alfalfa fodder cultivation. In the ANP method with the analysis of Super Dicision software, the results showed that temperature criteria (average, minimum and maximum) with a weight of 0.404, annual precipitation with a weight of 0.289 and topography (height and slope) with a weight of 0.056 are the most important effective parameters, respectively. During the growth period, fodder is alfalfa. By combining the studied criteria during the growth period of alfalfa fodder with the WLC method in the GIS environment, the location of alfalfa cultivation in Ardabil province was done.

The final results of the data analysis with the studied methods showed that rainfall, temperature and topography criteria respectively play an important role during the alfalfa growth period and also by combining the data; A location map of alfalfa fodder cultivation in Ardabil province was prepared. About 22% is very suitable, 21% is suitable, 23% is slightly suitable and 24% is unsuitable for alfalfa cultivation and The results of network analysis (ANP) showed that; Pars Abad region with a score of 238/., Sablan and Meshkin Shahr area with a score of 226/. domain with a score of 228/. compared to other studied stations, they have priority for alfalfa cultivation. Therefore, it is suggested; A- Studies that are carried out with multi-criteria methods on agricultural products, their weighting should be done based on the study of the optimal climatic needs of that crop by the researcher, not through a questionnaire. B- Ardabil province is suitable for the cultivation of alfalfa fodder in terms of climatic conditions and place. It is recommended to grow alfalfa fodder instead of non-strategic crops that require a lot of water.

Most of the water consumed in Iran is allocated to the agricultural sector. The world's population will reach about 9 billion by 2050. The population of our country will exceed 86 million in 1404, in which population growth is faster than many other countries. For the exponential and rapid growth of population of the world and Iran, a great challenge will be created in food production with limited water and land resources. Due to population growth and urbanization, water resources in the world are becoming more and more limited. Therefore, paying attention to the amount of water consumed by plants and agricultural cultivation pattern, to maximize the yield of farms, is one of particular importance. Determining the capacity of canals or water pipes depends on the irrigation hydromodule and this parameter must be carefully extracted for each area. On the one hand, if the irrigation hydromodule of an area is estimated to be less than the actual value, water requirement of the plants, will not be met and the agriculture will suffer a lot from this issue. On the other hand, if the irrigation hydromodule of an area is estimated to be higher than the actual value, farmers will not save water and therefore the efficiency of irrigation systems will decrease. Therefore, it is required that for each area, the cultivation pattern and irrigation hydromodule should be carefully estimated and the combined hydromodule should be extracted and be the basis for designing irrigation projects.

In this research, according to meteorological data, the rate of evapotranspiration and finally the irrigation hydromodule for some stations in the country is determined. Climatic data of Ardabil, Ahvaz, Qazvin, Kerman and Mashhad stations were collected and the evapotranspiration values of grass, as reference plant, were extracted using Cropwat8 software. The climatic data period in different stations was chosen so that the beginning of the period, as far as possible from the establishment of each station (in the absence of incomplete or missing data) and the end of the period ending in 2015. The length of the period in different stations varies depending on the year of establishment and it was tried to consider the maximum length of the period for each station. The cultivation pattern of the desired areas was extracted from the sources. The changes trend in climatic parameters, rainfall and evapotranspiration of the reference plant of each region were determined. Hydromodules, probability of occurrence, return period and Weibull conversion were extracted for each hydromodule (one per year). Firstly, obtained irrigation hydromodules from the Cropwat8 software for all the years were sorted in ascending order and each one was given a number (m). Then the probability percentage (P%) was calculated for each of the hydromodules. The return period (RP) was calculated for the various probabilities. Finally, using the Weibull conversion coefficient, irrigation hydromodules with different return periods were extracted for each region.

The results showed that the average evapotranspiration of the grass, as reference plant, for Ardabil, Ahvaz, Qazvin, Kerman and Mashhad stations were calculated 2.87, 5.75, 3.79, 5.4 and 2.49 mm d-1, respectively. The average irrigation hydromodules for the five mentioned stations were 0.66, 0.99, 0.75, 1.1 and 0.71 lit s-1 ha-1, respectively. Using the linear variation function, in return periods of 2 to 200 years, the irrigation hydromodule values in Ardabil, Ahvaz, Qazvin, Kerman and Mashhad stations varies from 0.673 to 0.768, 1.023 to 1.22, 0.76 to 0.861, 1.095 to 1.248 and 0.7 to 0.759 lit s-1 ha-1, respectively. Using the exponential variation function, in the return periods of 2 to 200 years, the irrigation hydromodule values in Ardabil, Ahvaz, Qazvin, Kerman and Mashhad stations varies from 0.665 to 0.775, 1 to 1.249, 0.754 to 0.867, 1.086 to 1.255 and 0.695 to 0.761 lit s-1 ha-1, respectively. Taking the linear change function, by changing the return period from 2 to 200 years and reducing the probability of occurrence, the amount of irrigation hydromodule in Ardabil, Ahvaz, Qazvin, Kerman and Mashhad stations were increased 0.148, 0.303, 0.156, 0.237 and 0.092 lit s-1 ha-1, respectively that is equivalent to 19.27, 24.84, 18.11, 19 and 12.12 percent, respectively. Also, considering the exponential change function, the amount of irrigation hydromodule in the mentioned stations were increased 0.173, 0.391, 0.177, 0.267 and 0.55 lit s-1 ha-1, respectively that is equivalent to 22.32, 39.1, 23.47, 21.27 and 13.98 percent of the average. In short return periods (including 2, 5 and in some stations 10 years), the linear function estimates the amount of irrigation hydromodule more than the exponential function. At higher return periods (including 25, 50, 100, and 200 years), the exponential function estimates the amount of irrigation hydromodule more than the linear function. In the intermediate return periods (including 10 and 25) the results of the linear and exponential functions are very close to each other.

The lowest amount of hydromodule was obtained in Ardabil station for a return period of 2 years and the highest amount was obtained for Ahvaz station for a return period of 200 years. Taking the linear changes function and considering that with increase in return period (even up to 200 years), the irrigation hydromodule does not change much (about 20% of the average), it is suggested that the construction of water storage, transmission and distribution buildings should be designed and implemented with low probability of occurrence (high return period).

One of the first steps for optimal management of water consumption in the agricultural sector is to estimate water needs by determining evapotranspiration. There are several direct and indirect methods for estimating evapotranspiration; each one has advantages and disadvantages. Due to the importance of measuring evapotranspiration in most hydrological studies and estimating the water requirement of plants and due to the limitation of the possibility of direct measurement, there is a serious need for experimental methods to estimate evapotranspiration. In the present study, reference evapotranspiration was initially estimated at selected stations in the east of Lake Urmia. Then, experimental methods of calculating the pan coefficient were used to calculate the reference evapotranspiration using evaporation pan data considering the FAO standard method.

The aim of this study was to evaluate the accuracy of pan coefficient estimation methods to calculate daily evapotranspiration in the east of Lake Urmia basin. There are several direct and indirect methods for estimating evapotranspiration; each one has advantages and disadvantages. The evaporation pan method has been used to estimate evapotranspiration values. For this purpose, data from Tabriz, Sarab, Maragheh, Bostanabad and Herris synoptic stations located in the east of Urmia Lake basin were used. The meteorological data utilized in the current study are minimum, average and maximum temperature, sunny hours, minimum, average and maximum relative humidity, wind speed, and evaporation from the pan. It is worth mentioning that due to the limitation of recording evaporation pan data, the present study was carried out using data for 6 months of the year (May to October) in which continuous data are available. The values of the pan coefficient were estimated using six experimental methods including Konica, Allen and Parvit, Snyder, modified Snyder, Orang and Mohammad et al. To determine the best method for estimating the pan coefficient, the evapotranspiration values obtained from the application of each method were compared with the evapotranspiration values obtained from the standard FAO-Penman-Monteith method. Furthermore, statistical meters of R, RMSE, MAE and box and violin plot diagrams were used to evaluate the obtained results.

In this study, six experimental models were used to estimate the pan coefficient. Based on the obtained results, the highest range of average monthly changes of the pan coefficient is related to the Orang method. Also, considering the average monthly values obtained for the pan coefficient, the Orang method estimates the reference evapotranspiration to a considerable amount. The results showed that in Bostanabad and Harris modified Snyder method, in Sarab and Maragheh method of Mohammad et al. and in Tabriz Allen and Parvit method are the best methods for estimating pan coefficient. Also, in general, in all stations, the Orang method has the highest error in estimating pan coefficient. In order to use experimental models for estimating the pan coefficient to calculate evapotranspiration, it is necessary to determine the appropriate model for each region based on the climatic conditions.

Due to the importance of estimating reference evapotranspiration in most hydrological studies as well as estimating the water requirement of plants, several direct and indirect methods have been developed. In the present study, six models of estimating the pan coefficient were evaluated in order to calculate the daily reference evapotranspiration using evaporation pan data. The obtained results showed that in general, the models for estimating the coefficient of the pan with acceptable accuracy can be used to calculate evapotranspiration. Meanwhile, due to the effect of climatic factors in these models, it is necessary to evaluate the efficiency of each model in different climatic conditions and determine the appropriate model for each region. For example, the results of the present study showed that the Orang method for the study area (east of Lake Urmia) does not provide suitable results and if this model is used for the east of Lake Urmia, it is necessary to calibrate the model. Also, based on the obtained results, the accuracy of other methods is close to each other. In Bostanabad and Herris, the modified Snyder method, in Sarab and Maragheh, the method of Mohammad et al., and in Tabriz, the method of Allen and Parvit, are the best methods in estimating daily reference evapotranspiration.

Urmia Lake is the largest saltwater in the Middle East, which has been located in the northwest of Iran. Nowadays, various factors have exposed it to dryness and wind erosion, the result of which is the increase in soil salinity, the thinning of solute crystals, and the occurrence of dust storms. Identifying the nature of these dusts specially the mineralogy of them is important in providing solutions to deal with the crisis. Investigating the characteristics and mineralogy of dusts in the region are useful in predicting and controlling ways to reduce their damages, and dust mineralogy is a practical method to determine their origin. In other words, the deposition of dust in different areas can affect the nearby ecosystems by making changes in the texture, composition of elements and even the acidity of the soils of the affected areas. The source of dust is very important in the mineralogy of sedimentary particles and depends on various factors such as geology and soil characteristics as well as climatic conditions. Also, the height of atmosphere which the dusts are there can be useful in studying the affect of mineralogy in this height.

For this purpose, three flat sites without vegetation and prone to fine dust production were selected from the eastern shore of Urmia Lake, and each site was divided into 3 layers based on the height from sea level, but the first layer was omitted from the studying areas because of the high soil moisture due to low distance to lake, which results in decreasing dust production by this layer, and eventually 2 random samples (0-5 cm) were picked up from each layer. This research work carried out based on 12 selected soil samples from 3 sites and their layers. The soil samples from 0 to 5 cm depth as a surface soil of layers were transferred to trays with dimensions of 3 x 40 x 30 cm in the wind tunnel of agriculture faculty of Tabriz University, with 370cm length, 50cm width and 70cm height, and wind erosion was simulated by applying the maximum wind speed of 45 meters per second to it was done for 15 minutes at each height. Then, the dust particles released at 2 heights of the wind tunnel (10 and 30 cm from the floor of the device) and the control soil sample were subjected to XRD analysis and the obtained diffractions were interpreted using High Score software. Finally, statistical analysis was performed using a nested design to find the effect of factors such as the location, layer and height of the wind tunnel on the content of minerals in windblown dust.

The obtained results showed that the dominant minerals in the most dust samples, were quartz, calcite, halite and gypsum with the highest average percent of quartz, because of the widespread occurrences of this mineral in the earth crust. The statistical analysis results revealed the significant effect of layer on quartz at the p<0.01 level, but the effect of site on calcite was significant at the p<0.05 level. But the maximum amount of quartz appeared in layer 2 of site 2, while its minimum amount has observed in layer 2 of site 1. The maximum and minimum amount of calcite was found in site 2 and 3 respectively, but predominance of quartz in the dust samples can be attributed to the wind blow within a short distance. This differences can be related to the nature of the parent materials of sites from which soils were derived. The presence of calcite as the main mineral in samples is due to study area temperature and precipitation increase and decrease respectively, which cause lake dryness, while gypsum and halite are produced in result of chemical equilibrium process and distribute in salty soils. Gypsum also can be produced during the reaction of calcite and sulfates of sea salts. The dryness of the lake also results in rising the gypsum minerals from dried floor of lake. Also, the presence of halite is affected by Urmia Lake salts that remain after water evaporation in dried land as a main mineral in soil and dust samples of affected lands.Key Words: XRD analyze, Wind erosion, Mineralogy, Wind tunnel, Urmia Lake.

Global warming is one of the challenges that has attracted more and more public opinion in recent years, and if wrong behavior continues, including excessive use of fossil fuels, it can become a serious threat to human life. One of the effects of global warming is climate change. The phenomenon of global warming and the resulting climate change, with changes in temperature and precipitation, have significant effects on various systems such as water resources, agriculture, and the environment. In such a way that it can be considered as a big threat to water systems all over the world. These threats are different for different regions of the world. The industrialization of societies and increasing greenhouse gases have caused climate change and seriously threaten human life. Change in rainfall is one of the important effects of climate change. Changes in precipitation have affected surface runoff and underground water sources, and in such conditions, water resources management becomes more difficult and complicated. The most reliable tool for investigating the effects of climate change on different systems is the use of climate variables simulated by coupled atmosphere-ocean general circulation models. These models can simulate climate parameters (temperature, precipitation, etc.) for future periods. But the main weakness of these models is their low spatial resolution and the simplifications they consider for climate processes. Microscale exponentials are used to cover the weakness of spatial resolution. The aim of this research is to evaluate the climate change on temperature and precipitation and its effect on the runoff entering the Nahand dam reservoir.

In this research, the daily temperature and precipitation data of Nahand basin during the period (1360-1384) were used as the base period to evaluate climate changes using the CanESM2 climate model and RCPs emission scenarios in future periods. And SDSM statistical model was used for the microscopic scale.By applying the output of the CanESM2 general circulation model, using the SDSM model under RCP 2.6, RCP 4.5 and RCP 8.5 emission scenarios, and with the help of the IHACRES conceptual integrated model, the impact of climate change on the runoff entering Nahand Dam was evaluated.Nahand Dam is one of the drinking water sources of Tabriz. Therefore, determining the incoming runoff to the tank can help to manage the system optimally. Also, to simulate the runoff entering the reservoir in future periods, the conceptual integrated model of IHACRES was used to simulate rainfall-runoff. The main goal of IHACRES model is to determine the hydrological behavior of the basin using a small number of parameters.

Based on the results of the temperature assessment in both the near future (2021-2060) and the far future (2061-2100) and under all emission scenarios, it is increasing and the temperature increase in the far future is more than the near future. The lowest and highest temperature increase is respectively related to the RCP 2.6 scenario in the near future period of 0.17°C and the RCP 8.5 scenario in the far future period to the extent of 1.01°C compared to the base period (1981-2005). By examining the trend of changes in the average precipitation in the coming periods, it can be seen that the precipitation, contrary to the temperature, is decreasing in all scenarios, so that the lowest and the highest decrease, respectively, related to the RCP 2.6 scenario in the future period is close to 7.23 mm and The RCP 4.5 scenario will be 25.77 mm in the far future period compared to the base period. Runoff will decrease in future periods under all scenarios. The lowest and highest decrease in the order of the near future (2021-2060) under the RCP 2.6 scenario is 0.08 m3s-1 (8.51%) and the far future (2061-2100) under the RCP 4.5 scenario is 0.08 m3s-1 It is 0.18 (19.15%).

In this study, the effects of climate change on the runoff entering the Nahand dam were investigated using general atmospheric circulation models (GCM) and the fifth report (AR5) of the International Panel on Climate Change (IPCC) with the CanESM2 climate model under RCPs emission scenarios. The results of the climate change study on the entrance to Nahand Dam show that the runoff will decrease under the influence of this phenomenon, so that under the RCP 4.5 scenario, the runoff will decrease by 19.15% in the far future period.

A spur dike is one of the structures that play a fundamental role in reducing the shear force on the river bank. The confrontation between this structure and the water flow causes strong eddies in both horizontal and vertical directions around the spur dike, which is the main cause of the scouring phenomenon around the spur dike structure and a result of its failure. Determining the depth of flooding is important because it is an indicator of the amount of flow destruction potential around the structure and is also an important parameter in the design of the foundation dimensions of the structures along the flow path. The findings of steady flow tests, in which the quantity of flow rate is equal to the peak flow rate of the flood hydrograph, are used to establish the maximum scour depth in the design of spur dikes (with a specified return period). The flow characteristics, and therefore the factors causing the scour, change with time in flood waves, and the scour depth after the hydrograph is less than the comparable peak flow rate’s equilibrium scour depth (link et al. 2017). The results demonstrated that because the non-steady flow and flow conditions vary in nature during floods, the temporal variations of scouring dimensions around structures under unsteady flow would be fundamentally different from those under steady flow. However, because no study has been performed on scouring around the spur dike under unsteady flow, there is no definite and recorded information in this field, and the magnitude of flood currents in nature makes the need for research in this sector even more pressing. Enhancing our understanding of scouring conditions and their temporal variations over time in the hydrograph will help us build better hydraulic structures. Experiments were carried out at the Hydraulic Laboratory of the Shahid Chamran University of Ahvaz (Iran) in a flume 10 m long, 0.74 m wide, and 0.60 m deep. In the present study, a single unsubmerged spur dike was considered for three percent permeability of 0% (i.e., impermeable spur dike), 33%, and 66%. Moreover, three spur dike alignment angles  equal to 60° (repelling alignment), 90° (deflecting alignment), and 120° (attractive alignment) were considered.  is the angle between the spur dike and the upstream wall. Totally, 27 experiments were performed in the flow rate range of 15 to 50 LS-1. The experiments were designed to examine the impact of widely accepted geometric parameters of the spur dike (as an important and general structure used in river engineering projects to preserve river walls or other important structures such as bridges), such as its permeability (closed and open spur dike) and placement angle relative to the wall in time changes, as well as the maximum scouring depth around the spur dike in unsteady flow conditions. Furthermore, the influence of the shape of the hydrograph as a variable on the scouring process was explored. The comparison of scour depth variations between various scouring angles shows that the scour depth changes at different angles are nearly identical, and the distinction between scour depth changes in the test angles is small, indicating that the angle has little impact on scour depth changes. The spur dike permeability parameter plays an essential role in the maximum scour depth surrounding the spur dike and its value drops dramatically as permeability rises. Scouring in this area is caused by horseshoe vortex and rising in the spur dike nose. The movement of water through the open spur dike rods minimizes or reduces the intensity of vortices that occur behind the spur dike and near the nose. The process of scouring depth changes caused by all skewed and normal hydrographs has many differences. Since hydrographs skewed to the left (hydrograph with a ratio of peak time to hydrograph continuation time of 0.33) the time of the ascending branch is shorter and the discharge reaches its maximum value quickly, so the slope of the graph of the scour depth changes over time. It is very intense at first and then become insignificant. In hydrographs with a skew to the right (hydrograph with a ratio of peak time to hydrograph continuation time of 0.66), scour depth changes occur in more time. By comparing the scour depth changes between different angles of the impervious spur dike, it shows that the scour depth changes are the highest at 90 degrees and the lowest at 120 degrees. While in spur dike with the permeability of 33% and 66%, the most changes in scouring depth occur at an angle of 60 degrees. The highest percentage of changes in the maximum scour depth compared to the scour depth in the peak hydrograph is related to the hydrograph with the ratio of the peak time to the duration time of the hydrograph 0.5 (normal distribution). The temporal development of scour depth in all three angles of 90, 60, and 120 degrees and all three hydrographs with the ratio of peak time to hydrograph continuation time is 0.33, 0.5, and 0.66, which is such that with the increase in the permeability of the scour, the scour depth It decreases significantly. So, On average, in the spur dike with permeability of 33% and 66%, respectively, compared to the impermeable spur dike, 48% and 88% reduction in scour depth is observed. The process of scouring depth changes caused by all skewed and normal hydrographs has many differences.

Wheat plays a dominant role in global food security as it contributes almost 20% of the total dietary calories and proteins worldwide. Economic measures can promote the development of Conservation Agriculture (CA), and due to their correlation with socioeconomic sectors, CA measures can affect the whole socioeconomic system. Many studies have been conducted on the benefits of CA, but considering that economic factors are one of the important factors for accepting the principles of CA, however, many economic analyzes have not been conducted on the impact of CA on costs, especially in Iran. Knowledge of the profitability of agricultural management methods can be a suitable basis for making favorable decisions to move toward CA. Considering that financial profitability in the Initial phase of CA (IP-CA) may be controversial, this study is aimed at estimating the cost of wheat production in two systems CT and IP-CA of Golestan province.

7 study sites Bandar Gaz, Kordkoy, Gorgan. Bandar Torkman, Agh Qala, Azad Shahr and, Galiksh, which have the largest area under cultivation and exploiting CA and CT (Conventional Tillage) were selected in Golestan province north of Iran. In this study, the treatments included CA and CT, and it was possible to compare the treatments at the same time in 7 sites and 84 farmers who managed two CA and CT lands together and CA had been implemented in them for 3-6 years were selected and sites were in the initial phase of CA. Agricultural inputs, including the consumption of seeds, water, Poisons, chemical fertilizers, labor, and agricultural machines, were considered as production costs. In this study, the profitability of each CA and CT system was investigated using cost and income information. Then, using the Translog Cost Function, the effect of CA technology on input demand and production costs was investigated.

The use of CA in the production of wheat has reduced the consumption of agricultural inputs other than poison; so, the largest decrease of 45.48% belongs to the labor force and the smallest decrease of 15.62% belongs to the seed. Greater production cost under CT respectively was due to higher labor force, use of agricultural machinery, and water cost. The amount of poison consumption was higher in CA than CT, except in Kordkoy sites. Generally, the cost of poisons under CT was the lowest than in CA. The highest weed control cost under CA could be associated with higher weed seed bank near the soil surface, and maximized germination potential of fresh weed seed due to residual burying. The use of CA has led to a reduction in the use of chemical fertilizers; So, the biggest decrease of 33.33% is assigned to Agh Qala site. Conservation agriculture has led to a decrease in the workforce in all cities. The average production of wheat crops in Golestan province in 2021 in CA was 8.45% higher compared to CT. The gross profit in CA and CT systems is calculated as approximately 122 and 94 million Rials per hectare respectively, which in CA is approximately 28 million Rials (30.50%) more than in CT. The average production cost of each kilogram of wheat in one hectare is 54,641 Rials under CT and 43,289 Rials under CA and in fact, the cost of producing one kilogram of wheat in CA decreased by almost 20%.

In this study, CA, on the one hand, as a result of reducing production costs, led to a reduction in production costs, and on the other hand, due to the higher production of wheat, it increased income per hectare. In this study resulted that IP-CA has been able to manage the use of agricultural institutions in a better way, which leads to a reduction in production costs and an increase in production IP-CA, in addition to saving wheat production costs, has indirect social benefits for farmers. Reducing the need for labor creates new economic opportunities for farmers, and saving time creates new businesses and generates non-agricultural income. If the economic benefits of CA, along with its numerous benefits such as reducing carbon dioxide, more water efficiency and, most importantly preserving the soil of this valuable trust, are all included in the calculations, it shows the very high value of CA for the economic and social future and environment.

Evaporation is one of the main components of hydrological cycle and one of the effective climatic variables in arid areas such as Iran. Accurate estimate of evaporation rate plays an important role in sustainable development and optimal management of water resources. Evaporation is one of the essential processes, because it depends on meteorological variables such as solar radiation, air temperature, wind speed, relative humidity and atmospheric pressure, which are related to the topography and the climate of the region. Class A pan-evaporation is one of the standard and direct tools for measuring evaporation, which is used all over the world due to its ease of application in determining evaporation. However, in most stations accurate evaporation recording is not practical due to instrument limitations and maintenance problems. On the other hand, the temporal and spatial distribution of evaporation stations compared to meteorological stations is limited, so according to the problems mentioned, the use of meteorological variables in estimating the rate of evaporation from the pan will be useful. In different regions, the impact of different climatic factors on changes evaporation from the pan has not be fully understood, so the relatively accurate estimation and prediction of this phenomenon is an effective step in the relevant fields. In recent years, for estimating the amount of evaporation from the pan, a variety of intelligent systems and software calculations such as data mining methods have been developed.

In this study, meteorological data of Tabriz station in the period of 2003 to 2018 have been used to estimate the evaporation values from the class A pan. For this purpose, a simple correlation between meteorological variables and evaporation from class A pan was created and based on the result of this correlation, in the studied station the minimum temperature and relative humidity were inversely and the maximum and average temperature were directly affected by evaporation. Thus, ten combined scenarios were defined and modeling was performed using Support vector regression (SVR), Gaussian process regression (GPR), M5tree, Random forest (RF) and Linear regression (LR) methods. It should be noted that in this study, 70% of the data were selected for training and 30% for testing. Finally, the performance of each method in estimating evaporation values was evaluated using root mean squared error (RMSE), mean absolute error (MAE), Nash- Sutcliffe coefficient (NS) and Akaike information criterion (AIC).

The results showed that GPR10 method with RMSE = 1.90 mm/day, MAE = 1.48, NS = 0.81 and SVR10 method with RMSE = 1.92 mm/day, MAE = 1.51, NS = 0.8 had reasonable performance in estimating the values of daily evaporation from class A pan. The GPR method showed its higher capability to estimate daily evaporation values in all definition scenarios with the least error and the most accuracy. The SVR model with appropriate results was in the second place. The results of statistical parameters for random forest model were even weaker than the results of linear regression. In general, scenario number 10 with all meteorological variables and scenario number 1 with only the input minimum temperature variable had the best and weakest results among all defined scenarios, respectively. Scenarios 6 to 10 have more accuracy and less error and modeling structures with the least number of variables has the least accuracy. Also, wind speed and solar radiation variables were introduced as the most effective factors in estimating the evaporation rate from class A pan.

Evaporation is one of the important processes that cause the losses of half of precipitation in arid and semi- arid regions. Accordingly, knowledge of the amount of evaporation and its modeling as one of the most important hydrological variables in agricultural research and factors related to water and soil of great importance. So, accurate estimation of this phenomenon is essential. In this study, meteorological data from Tabriz station were utilized to assessment capability of machine learning methods. Evaporation values were estimated using five data mining methods including SVR, GPR, M5, RF and LR. Conclusively, the results of evaluation criteria indicated that GPR and SVR models using all variable of meteorological data performed more accurate than others. Finally, both of them are recommended to estimate the amount of evaporation from class A pan.

Citrus is an important fruit crop in Iran. One of the main reasons for decreasing yield of these plants, in addition to moisture stress, is their unbalanced nutrition, so nutrient balance is an important factor in increasing quantity and quality of crop production. In proper plant nutrition, each nutrient must not only be sufficiently available to the plant but also create a state of equilibrium, and observance of the ratio between the nutrients is of particular importance. Diagnosis and recommendation integrated system (DRIS), and deviation from optimum percentage (DOP) can be used as efficient methods to interpret the results of plant analysis and the nutritional diagnosis in crops and fruit trees. In the north of Khuzestan, due to the dense cultivation of trees and soil depletion of the plant's nutrients, it requires widespread use of fertilizers containing macro and micronutrients. The objective of this study was to determine the optimum level of the nutrients and evaluate the nutritional status of Lisbon lemon (Citrus lemon) and Perl tangerine (Citrus tangerina) in Dezful area using DRIS and DOP methods. 30 Lisbon lemon and 30 Perl tangerine gardens were randomly selected from citrus gardens in Dezful region in the south of Iran. Leaf samples as composite were collected from non-fruiting branches in late September 2015, and N, P, K, Ca, Mg, Fe, Mn, Zn, Cu, and B concentrations were determined. DRIS norms were achieved from the gardens with high-yielding. Then, DRIS and DOP indices for nutrients in the gardens with low-yielding, considering average yield, were calculated to evaluate nutrients balances and order of nutrient requirements. Sufficiency ranges of macro and micronutrients were derived by the DRIS method. The mean concentrations of nutrients in the high-yielding population were used as reference values to calculate DOP indices. Finally, nutritional balance index (NBI) was calculated for all nutrients. The results showed that the optimum level of the nutrients in Lisbon lemon leaves were 2.97, 0.11, 1.85, 3.88 and 0.17% for N, P, K, Ca, Mg, and 200.5, 24.9, 23.9, 68.8, 32.9 mg kg-1 for Fe, Zn, Mn, Cu, and B, respectively. Also, the optimum level of these nutrients in Perl tangerine leaves were 2.97, 0.09, 1.57, 3.44, and 0.34% for N, P, K, Ca, Mg, and 167.2, 32.7, 26.1, 28.0, 48.4 mg kg-1 for Fe, Zn, Mn, Cu, and B, respectively. DRIS-derived sufficiency ranges in Lisbon lemon (Citrus lemon) were 1.7-4.2, 0.08-0.14, 1.2-2.5, 3.2-4.5, 0.13- 0.2% for N, P, K, Ca, Mg, and 126.5-274.6, 20.7-29.2, 25.1-112.5, 16.4-31.5, 9.8-56.1 mg/kg for Fe, Mn, Zn, Cu, B, respectively, and also in Perl tangerine (Citrus tangerina) were 1.7-4.2, 0.07-0.12, 1.1-2.1, 2.6-4.2, 4.2-5.0, and 0.6-0.9% for N, P, K, Ca, Mg, and 117.1-217.5, 18.1-47.4, 5.2-50.1, 19.6-32.5, and 22.1-74.7.1 mg/kg for Fe, Mn, Zn, Cu, B, respectively. A comparison of the DRIS method with the DOP showed that Iron for Lisbon lemon and Boron for Perl tangerine gardens had the most negative index values. According to the DRIS index, priorities on the macro and micronutrients were determined for Lisbon lemon as Fe > N > B > K >Mn> Ca > Mg = P > Cu > Zn and for Perl tangerine as B > Fe > K > Cu > N > Ca > Mg >Mn> Zn > P. Based on DOP index, priorities on the macro and micronutrients were determined for Lisbon lemon as Fe > K > B > Cu > Mn > Ca > N > P > Mg > Zn and Perl tangerine as B > Zn > Fe > N > Mn > P > K > Mg > Ca > Cu. However, priorities on the nutrients were different in DRIS and DOP methods for both gardens except for the first priority. The efficiency of DRIS and DOP methods of this study compared to previous research on the priority of certain nutrients can be related to plant nutrition management, plant type, and climatic conditions of the study area. In general, nitrogen and potassium were the most deficient for both gardens, and among the micronutrients Iron and boron had the highest deficiency for both gardens. Overall, nitrogen, potassium, iron, boron, and priority nutrients should be given special attention to their nutrition.

Water resources management, especially irrigation practices, is heavily reliant on reference evapotranspiration (ET0). ET0 is the rate of evaporation and transpiration from a standard reference surface with a presumed surface resistance of 70 s.m-1, the height of 0.12 m and an albedo of 0.23. Penman-Monteith FAO-56 (P-M FAO-56) approach is the most commonly used method for calculating ET0. In spite of the fact that FAO-PM is achievable, its implementation remains inconvenient because it requires a large amount of meteorological data, which is derived from standard meteorological observation stations. In the absence of complete climate data, it is highly desirable to have a model with fewer input climatic dates. Therefore, remote sensing methods have been used and improved over time to estimate ET0 at various spatial scales. Alternatively, it has been observed that the research community has become increasingly interested in obtaining data from metaheuristic algorithms that are based on artificial intelligence (AI).

In this research, it has been attempted to estimate the amount of daily reference evapotranspiration (ET0) using two data-driven models, using a combination of inputs from meteorological station data and satellite imagery data from MODIS sensor, by considering different inputs from these sources. The models include the random forest (RF) and hybridized RF with genetic algorithm optimization (GA-RF). Moreover, the correlation of input variables with ET0 is evaluated and the possibility of training a simple and accurate machine learning model in the conditions of lack or absence of meteorological data using satellite image data is investigated. So, this study aimed to determine ET0 in the time period of 2003-2021 using land surface temperature (LST) data and leaf area index (LAI) acquired from MODIS sensor and Tabriz meteorological station data including maximum and minimum air temperatures (Tmax, Tmin), average temperatures (T), wind speeds (U2), average relative humidity (RH), maximum and minimum relative humidity (RHmax, RHmin), and sunny hours (n). For the study area, daily LST were extracted from the Terra (MOD11A1) and Aqua (MYD11A1) satellites. Moreover, the LST of Terra and Aqua satellites were combined, since the LST values had missing data due to the presence of clouds. Furthermore, MODIS MCD15A3H version 6.1 using four-day data from Terra and Aqua satellites was used to determine the leaf area index (LAI). The standard P-M FAO-56 method for calculating daily reference evapotranspiration was considered as the base method. The set of input parameters was considered based on the cross-correlation of the parameters with reference evapotranspiration obtained from the FAO-Penman-Monteith equation.

The results of two data-driven models including standalone random forest (RF) and hybridized RF model with genetic algorithm (GA) to estimate ET0 values were compared with calculated ET0 by P-M FAO-56 equation. The results indicated that all of the studied input variables are highly correlated with the target variable. Based on the P-M FAO-56 method, the average air temperature with the highest value (R2=0.903) and the wind speed with the lowest value (R2=0.282) has a high and low correlation with reference evapotranspiration. Also, by comparing LAI and LST MODIS parameters, LST has the highest correlation coefficient with ET0 with R2=0.865. A total of twelve scenarios for estimating ET0 are evaluated, each with a different set of input parameters. Based on the correlation between the parameters and ET0, the first ten scenarios are categorized. Additionally, the eleventh scenario is based only on satellite images, and the twelfth scenario is based solely on weather station data. Based on the results, the GA-RF-10 (R2=0.976, RMSE=0.200, MAPE=11.373, and MBE=0.028), which includes all input parameters, outperforms the other models. There was a greater degree of accuracy with the RF-10 (R2=0.949, RMSE=0.293, MAPE=16.442, and MBE=0.017) when compared with the other random forest models. Based on the comparison of scenario 11 (satellite image data) and scenario 12 (meteorological station data), it appears that scenario 12 is more accurate for both RF (R2=0.922, RMSE=0.357, MAPE=20.712, and MBE=0.009) and GA-RF (R2=0.944, RMSE=0.306, MAPE=17.037, and MBE=0.013) models. Despite the fact that only satellite image parameters did not provide accurate estimation of ET0 compared to independent meteorological parameters, the inclusion of these parameters in the ET0 estimation resulted in more acceptable results, demonstrating the importance of satellite image parameters. Thus, satellite data may be useful and recommended for estimating ET0, particularly in areas without meteorological stations.

Over-harvesting of water resources along with climate change led to the aggravation of the water shortage crisis. Therefore, correct management and planning for sustainable use of water resources are of high importance. In this situation, one of the most effective solutions is to increase agricultural water productivity. The main goal in improving agricultural water productivity is to save water consumption along with increasing the yield of agricultural products. There is 128,000 hectares of tomato cultivated land, standing for 1.1% of the total cultivated area in Iran. Irrigation management is one of the most effective and recommended ways to control water consumption in tomato farms. Nevertheless, it is necessary to study the mentioned solution on large-scale such as province with considering different climate, farm area, irrigation system and irrigation management in the field. In this research, irrigation management was the proposed solution to improve the water productivity. Initially, the current status of irrigation management in 12 tomato farms was investigated. Then, the effect of the irrigation management, specifically the corrected irrigation schedule, were evaluated owing to enhance the water productivity.

12 tomato farms were firstly selected in the agricultural lands of Zanjan province. Most of the experimental farms were equipped with drip tape irrigation systems. In the second phase, two farms were selected and the proposed irrigation schedule were implemented in order to improving the water productivity. Each farm was divided into two parts; one with real conditions (farmers' management) and another with controlled conditions. In the controlled treatments, irrigation management was implemented through optimization of irrigation time. In each farm, basic information such as area, physical and chemical properties of soil and water quality were determined. Irrigation information (such as inflow discharge and irrigation schedule) was measured and determined at least three times during the cropping season. Soil moisture were measured before and after irrigation in order to calculate the water application efficiency. The amount of harvested product and production costs were obtained at the end of the cropping season through measurements and interviews with farmers. In this research, the indicators including the volume of consumed water, the water use efficiency, and the physical and economic efficiency of water have been calculated to analyze the water productivity.

The minimum and maximum of consumed water in tomato farms was measured as 6142 and 17580 m3/ha, respectively (with an average of 10669 m3/ha). The average of consumed water in farms with surface irrigation systems equals to 16600 and in farms equipped with drip tape irrigation systems is about 9483 m3/ha. While the actual water requirement in the studied area is between 6120 and 6950 m3/ha. The amount of application efficiency was calculated in the range of 34.8 to 90% (66% on average). The average of this index in surface and drip tape irrigation systems were determined 39.9 and 71.4%, correspondingly. The minimum and maximum values of tomato yield were measured 40 and 140 ton/ha (with average of 77.2 ton/ha). The results of the second phase of the research showed that the application of proper irrigation management leads to a significant reduction in water consumption. Implementation of this strategy in farms 201 and 202 led to a 39% decrease and a 8% increase, respectively of water consumption during the cropping season. Irrigation schedule in some farms is relatively fixed and they have less flexibility compared to changes in net water requirement. The water use efficiency (CPD) was calculated as an important criterion in order to investigate physical productivity. The value of CPD was obtained in the range of 2.3 to 22.8 (on average 8.7). As the consumed water increases to a certain amount (approximately 10000 m3/ha), the value of the CPD shows an upward trend, However, with the increase from the mentioned value, the value of the CPD drops. Implementation of modified irrigation management has led to a significant increase in CPD index. On average, the value of the CPD in the controlled plots has increased by 29.5% compared to the real conditions.

In some farms, the irrigation schedule was not in accordance with the net irrigation requirement and excessive irrigation was done by farmers. It was especially evident in the first half of the crop growth period, and with the reduction of groundwater level, the depth of irrigation water became closer to the actual requirement. In fact, the limitation of water resources was recognized as the main factor controlling water consumption in most farms. However, it is possible to considerably reduce the consumed water and improve the productivity by applying proper irrigation management (specifically correcting the irrigation time). Using the results of the present research through the preparation of understandable instructions for farmers can lead to the prevention of excessive irrigation and the control of water consumption in farms.