سعید صمدیان فرد

The amount of underground water discharge by identified wells and aqueducts in Tabriz plain is 134 MCM per year. According to the hydrograph drawn for Tabriz plain, the groundwater level has dropped by 1.394 meters for 16 statistical years (2006-2021) and 0.088 meters in the wet year (2020-2021). The results of the water balance calculation of the region showed that the plain is in a state of imbalance and the reservoir deficit was estimated at 22.74 MCM. The results of this study showed that one of the important factors of water shortage is to turn to crops with a high water requirement. So, the sustainable perception of the seven scenarios on the dominant crop pattern applied in the region which four scenarios (1) providing 80% of the water requirement of the products instead of providing full water requirement, (2) providing full water requirement while reducing the 20% cultivated area, (3) providing 90% of the water requirement of the products simultaneously with 10% reduction in their cropping area, (4) onion production due to high water requirement removal from the cropping pattern and reduction of 10% of the alfalfa cultivar and 10% Chickpea and vegetable cultivars were accepted, which are roughly proportionate to the sustainable harvesting value. The results showed that the most important solution for optimal water use is management of water use and in agricultural sector, changing the pattern of cultivation  is a good way to reform the water use pattern.

Water scarcity and the need for optimal water utilization in arid and semi-arid regions, including Iran, have encouraged water authorities and farmers to adapt modern irrigation systems likedrip irrigation, to make optimal use of water resources. The most important advantage of drip irrigation over other irrigation methods is its ability to control the amount of water applied to each plant. New irrigation methods focus on plant irrigation and not on land irrigation. In arid and semi-arid regions, a drip irrigation system is used to use water optimally and prevent wastage and evaporation. Factors such as soil texture, type of cultivated plant, amount of available water, distance of drippers and laterals, the wetted surface, and the dimensions of the moisture bulb under the soil surface are involved in the design of the drip irrigation system. Due to the variety of soil textures in the earth, the movement of water under the soil surface is different in all kinds of textures, therefore, knowing exactly how water moves in the soil and how the moisture bulb is distributed under the soil surface is of particular importance. The purpose of this study is to investigate the movement of moisture bulbs, check their dimensions under the soil surface in different soil textures and flow rates, and evaluate the capability of the Moment analysis method to simulate this process under various conditions.

To simulate the moisture bulb in different soil textures, detailed information on the physical properties of the soil, including the percentage of particles that make up the soil texture, bulk and real density, porosity, and saturated hydraulic conductivity, is required. In this research, the simulation of the moisture front in different soil texture was conducted using Rosetta software, which defines 12 types of soil textures. In these tests, the source of soil power was considered as surface and point. The total feeding volume of each type of soil texture is 24 L, and this volume was used with different flow rates of two, four, six, and eight L s-1. To numerically simulate the progress of the moisture front, Hydrus software was used. Then the analytical simulation of the moisture front was done using the equations of the Moment analysis method. In this study, an ellipse was drawn to represent the moisture bulb simulated by Hydrus software at different times for the applied flow rates. Coefficient k was used to draw the ellipse, and its appropriate value was determined by minimizing the difference between the model and Hydrus results.

To calculate the moments, the first step is to obtain the values of M00 According to the applied flow rates of two, four, six, and eight L s-1 and the amount of volume intended to feed all types of soil texture, i.e., 24 L, the duration of irrigation is 12, 6, 4, and 3 hr, respectively. The comparison of moisture distribution over all periods and soil textures showed acceptable results, and the distributed subsurface moisture values were similar. In the study of clay texture, with time from the start of irrigation, the difference in the total amount of distributed moisture increased, and the reason for this result is the decrease in the permeability of the clay due to the filling of fine pores. The results indicated that σx2 values changed with the increase in irrigation duration. The highest variance was found in sandy clay with a flow rate of 8 L s-1 (1503.3 cm2), while the lowest variance was observed in clay texture with a flow rate of 4 L s-1 (368.6 cm2). By increasing the amount of applied discharge, σz2 increases and the slope of this increase is different in each soil texture, according to the characteristics of that texture. Also, the effect of irrigation duration on the value of σz2 is evident. In other words, the longer the duration of irrigation, the more the amount of variance changes.

In this research, the accuracy of the Moment analysis method in predicting moisture distribution from drip irrigation was evaluated using results from Hydrus and Moment analysis. The Hydrus results demonstrated that the moisture bulb expanded over time in both the horizontal and vertical directions. The results also indicated higher flow rates increased the horizontal expansion of the moisture bulb, while the duration of irrigation affected both horizontal and depth expansions. Using the moment analysis method, the center of mass of water distribution in the soil and the changes in the moisture front along the x and z axes were determined. By examining and comparing the dimensions of the moisture front resulting from Hydrus and ovals, it was observed that there is a suitable compatibility between the two methods. Therefore, the Moment analysis method can be relied upon to estimate the dimensions of the moisture bulb in drip irrigation. It also provides an efficient and accurate approach to reducing the time and cost of field experiments.

Water shortage and the need for its optimal use in arid and semi-arid regions, including Iran, has led water officials and farmers to use modern irrigation systems, such as drip irrigation with the aim of making optimal use of water resources. Drip irrigation has been welcomed in most parts of the world due to its high efficiency and the possibility of irrigation in different environmental conditions. The most important reason for the superiority of drip irrigation over other irrigation methods is the controllable amount of water for each plant. Drip irrigation is a method in which water is poured out of the net at low pressure through an orifice or device called an emitter and dripped into the bottom of the plant. This irrigation system, like other methods, requires accurate knowledge of the parameters affecting it to achieve the desired efficiency. One of the most important parameters for the irrigation system is the distribution of moisture in the soil and in fact the shape of the moist bulb. Therefore, knowledge of how to distribute water in the soil is essential for the proper design and management of subsurface drip irrigation systems. Since testing is very difficult and time consuming to detect the shape of moisture distribution in the soil, the use of numerical and analytical simulation can be an effective and efficient way to design these systems.

In order to determine the progress of the moisture front in drip irrigation, first the soil texture type and physical properties of the soil were determined. It should be noted that the emitter flow rate was measured and adjusted in volume at the beginning of the test to minimize the difference between the emitter flows along the three side tubes. Evaluation experiments were performed with three outflows of 2, 4 and 6 liters per hour. With the start of the system, the progress of the moisture front at different times was measured by digging a trench using a scale. Numerical simulation of moisture front progress was performed using HYDRUS model based on Richard equation and analytical simulation was performed using Moment Analysis. HYDRUS software was used to numerically simulate the progress of the moisture front. The simulation range was considered to be 100 cm by 100 cm on the two-dimensional plane. In these simulations, 3956 nodes are used to represent the entire simulation range and also, relevant equations were used to calculate the two-dimensional spatial Moment of the wetting pattern.

The simulations show that the initial volumetric moisture content is 0.11 and the saturation volumetric moisture content is 0.380 and the water dispersion rate increases over time on the x and z axes. With increasing flow, the maximum dispersion is in the x-axis, which occurs in flow of 6 liters per hour. The result for flow of 6 liters per hour based on the data used is slightly higher than the desired value. The reason why the value of M00 in the flow rate of 6 liters per hour is higher than expected, is that in the simulation flow rate of 6 liters per hour change in the size of the inlet diameter and the amount of flux changes the amount of water entering the soil and moistens a large volume of soil. Due to the different amount of moisture applied to the area at different times, the value of z_c,σ_x^2,σ_z^2 is different and has caused a change in the size of the oval in different flows. The increase in the size of the ovals indicates the high dispersion of water in that area. The results showed that the Moment analysis was able to express the position of the center of mass of water distributed in the soil with correlation coefficient of 0.986 in linear mode and 0.982 in logarithmic mode. By comparing the values of diameter and depth obtained from the HYDRUS and the drawn ovals, it can be concluded that both methods provide close results. The accuracy of the Moment analysis method in simulating different types of moisture patterns resulting from drip irrigation under different flows with the use of different volumes of water is similar to the HYDRUS model and therefore it is possible to use this feature to predict the pattern of moisture from a certain flow using a specific volume of water.

In this study, the accuracy of Moment analysis in simulating various moisture patterns resulting from drip irrigation under different flows with the use of different volumes of water was investigated and the possibility of using this feature to predict the pattern of moisture from a given flow using a specific volume of water checked. In order to investigate the Moment of the amount of water distributed in the soil by subsurface drip irrigation, simulation was performed by two-dimensional HYDRUS software for three discharges of 2, 4 and 6 liters per hour with an inlet water volume of 12 liters. Then, using the results of simulation of moisture distribution range by a programming language including MATLAB software, and by calculating the Moments, it was determined that the Moments are able to express the position of the center of mass of water distributed in the soil and how it is distributed relative to x and z axes. The increase in the size of the ovals indicates that more water is distributed in that area. Comparing the diameters and depths of the moisture front between the simulated HYDRUS model and the Moment analysis model, it was found that the Moment analysis is an efficient way to study the distribution of water moisture by drip irrigation and this method can be used as an alternative input to estimate parameters.

The increase in population has intensified the process of land use in different parts of the world. The purpose of the present research was to investigate the changes in the use of irrigated and rainfed cultivation with an emphasis on the water needs of plants in the Sarab Plain located in East Azarbaijan Province, Iran. Based on this, in order to discover the changes created in the study area, the images of TM, ETM and OLI sensors of Landsat satellite in 1996, 2005 and 2021 were processed and classified after geometric and atmospheric corrections. Using the overall accuracy test and Kappa statistic, the accuracy of production maps was determined. The classification results showed that the Support vector machine method has a higher accuracy than the neural network method with an average total accuracy of 93.37% and an average kappa of 91.33%. During the years of 1996-2021, the area of irrigated cultivation increased by 24.2% and the area of rainfed cultivation decreased by 2.7%. Moreover, the volume of water required for the five major products of the region was calculated using Cropwat software and it was found that the volume of water consumption has increased in the period of 1996-2021.

In order to effectively manage soil and water resources, it is imperative to investigate wet aggregate stability (WAS) as a fundamental indicator for assessing soil structure and quality. In this study, machine learning techniques, specifically random forest (RF) and random forest optimized with genetic algorithm (GA-RF), were employed. The analysis focused on determining the texture, organic matter content, and lime characteristics of 55 soil samples collected from the Arsbaran forests. Utilizing various input combinations based on correlations with WAS, modeling was performed across seven distinct scenarios. Furthermore, three performance metrics including correlation coefficient (CC), normalized root mean square error (NRMSE), and Wilmot coefficient (WI) were utilized to evaluate the effectiveness of the models. The findings indicated that the RF5 model exhibited superior performance among the random forest models, achieving NRMSE = 0.038, CC = 0.736, and WI = 0.789. Similarly, the GA-RF5 model, optimized through a genetic algorithm approach, demonstrated exceptional performance with NRMSE = 0.031, CC = 0.800, and WI = 0.842 when considering input percentages of sand, silt, and clay. Moreover, results from RF1 (NRMSE = 0.047, CC = 0.589, WI = 0.721) and GA-RF1 (NRMSE = 0.036, CC = 0.662, WI = 0.797) emphasized that clay content exhibited the strongest correlation with stability. Additionally, the incorporation of calcium carbonate equivalent in scenario 7 significantly enhanced model performance and positively influenced the prediction of wet aggregate stability. In summary, the hybrid model combining random forest with a genetic algorithm is recommended for precise and reliable determination of wet aggregate stability in studies focusing on soil properties.

Soil temperature is one of the important factors in agriculture and hydrology, and its accurate measurement is very important to ensure the optimal growth and development of the plants. Soil temperature is a factor that affects many processes such as seed germination, soil moisture level, aeration, nitrification and availability of plant nutrients. Because the soil temperature data is measured in some synoptic stations, most of the data have limitations or are incomplete. However, choosing the best method to estimate soil temperature with other available meteorological data is an efficient approach in many fields. Soil temperature depends on several factors including color, slope, vegetation, density, humidity and amount of sunlight. Currently, some physical models are available that are intrinsically related to the state of soil heat flow and energy balance in underlying soils to estimate soil temperature. The importance of soil temperature in agricultural sciences and hydrology, on the one hand, and the existence of many difficulties in recording this vital parameter, have led researchers to seek a relationship between soil temperature and other parameters in order to be able to estimate soil temperature with optimal accuracy.

In this research, daily soil temperature values were collected during the time period of 1990-2022 in Ramsar, Arak and Shiraz stations. On the other hand, the parameters of minimum temperature (Tmin), maximum temperature (Tmax), average temperature (Tm), maximum relative humidity (Umax), minimum relative humidity (Umin), average relative humidity (Um), average wind speed (FFM) and Sunshine hours (SSHN) was considered as the input parameters and soil temperature (T-soil) as the target parameter. It is worth mentioning that the way of choosing different input compounds to estimate the value of soil temperature in the studied models is based on having a higher correlation with soil temperature based on the thermal map. Moreover, the ability of data-driven models of Gaussian process regression (GPR), support vector regression (SVR), M5P algorithm, linear regression (LR), and multilayer perceptron (MLP) neural network in estimating soil temperature was evaluated using different statistical parameters of correlation coefficient (R), root mean square error (RMSE), Nash Sutcliffe coefficient (NS), average absolute value of percentage error (MAPE) and Wilmot agreement index (WI).

The evaluation of five GPR, SVR, M5P, LR and MLP models for three stations of Arak, Ramsar and Shiraz shows that the 8th M5P scenario and the 8th LR scenario with lower root mean square error respectively (0.899 and 0.889) for Ramsar station, (0.958 and 0.949) for Arak station and (0.966 and 0.953) for Shiraz station have better performance than other studied models. Also, the evaluation of the impact of the input parameters in creating the scenario for the models shows that the parameters of relative humidity and air temperature had more important role than other input parameters. So that by adding parameters of relative humidity and air temperature, the accuracy of the model has increased. Therefore, these parameters are among the most key and important parameters of soil temperature.

The analysis and evaluation of soil characteristics has an important impact in the fields of hydrology, agriculture and climate. On the other hand, soil temperature has a direct relationship with the amount of moisture available to the plant, so that an increase in soil temperature can increase the transpiration rate of plants, and as a result, soil moisture decreases. Soil temperature is also an essential factor in agriculture because it determines whether plants can grow, and controls soil chemistry and biology and atmosphere-land gas exchange. Therefore, predicting soil temperature is very important for successful crop management and yield optimization. So, In this research, five data-driven methods of GPR, SVR, M5P, LR and MLP were used to predict soil temperature in Arak, Ramsar and Shiraz stations during the time period of 1990-2022. The obtained results were compared using statistical parameters and it was concluded that the 8th M5P scenario and the 8th LR scenario have shown the best performance in three stations with the lowest error compared to all scenarios. Therefore, the application of the mentioned models to predict the soil temperature has proper accuracy and is recommended for management and evaluation in terms of environmental and civil aspects.

Indiscriminate use of water resources and the occurrence of drought in recent years have caused many problems in the country's water resources. The increasing shortage of water resources and high irrigation costs require developing new irrigation methods for optimal water consumption, which can minimize the amount of water used to produce yields. Evapotranspiration is one of the most important parameters needed to estimate the water balance in any ecosystem. Evapotranspiration is an essential parameter in the hydrological cycle process in natural ecosystems, which links the water and energy balance of the earth's surface with the atmosphere. Reference evapotranspiration (ET0) plays an important role in the availability of water resources and stimulating the hydrological effect of climate change. Accurate estimation of ET0 is necessary for forecasting climate changes, predicting and monitoring droughts, assessing the lack of availability of water resources, assessing crop water needs, and planning irrigation. FAO's Penman-Monteith method is known as a standard reference method for estimating ET0. However, this model and, in general, water balance-based assessment methods require accurate and long-term meteorological data, which are not always and everywhere available. Therefore, alternative methods for predicting ET0 at different temporal and spatial scales should be developed, which are easily applied and require fewer input data without compromising the estimation accuracy. Also, due to the high rate of evapotranspiration in the coastal and central stations of the country, so far, few studies have predicted the ET0 parameter. Therefore, this study was carried out to predict daily reference evapotranspiration in Isfahan and Astara stations. The current study is forecasting daily reference evapotranspiration in two stations of Astara and Isfahan using Gaussian Process Regression (GPR), Support Vector Regression (SVR), M5P tree model, and M5Rules linear regression. For this purpose, the daily meteorological data of the stations including average temperature, minimum temperature, maximum temperature, average relative humidity, minimum relative humidity, maximum relative humidity, wind speed, and sunshine hours during the period of 1990-2021 as inputs to the models was used. Also, to evaluate the effectiveness of the models, the evaluation criteria of determination coefficient (R2), root mean square error (RMSE), Nash-Sutcliffe coefficient (NS), and Wilmott's index of agreement (WI) were used. The evaluation of the results of different scenarios of the GPR model in Astara station showed that the fifth scenario was recognized as the best scenario of this model due to having a lower error value (RMSE=1.52 mm day-1). For the M5Rules model, the fifth scenario has performed better than the other scenarios of the M5Rules model due to having fewer inputs and similar errors compared to the sixth to eighth scenarios (RMSE=1.42 mm day-1). In the M5P model, the fifth scenario has a higher accuracy than the other scenarios due to having a lower error value (RMSE=1.42 mm day-1). For the SVR model, the sixth scenario with the least error (RMSE=1.58 mm day-1) was selected as the best scenario compared to other scenarios of the SVR model. For the Isfahan station, for the GPR model, the fifth scenario has performed better than the other scenarios due to having fewer inputs. The comparison of M5Rules model scenarios also showed that the eighth scenario with RMSE=1.85 (mm day-1), had higher accuracy than other scenarios. The seventh scenario of the M5P model has performed better than other scenarios due to its RMSE=1.86 (mm day-1). Finally, the evaluation of SVR model scenarios showed that the eighth scenario with RMSE=1.88 (mm day-1) had a better performance than other scenarios. The comparison of the models used to predict daily reference evapotranspiration in Astara station showed that the fifth scenario of M5P and M5Rules models having evaluation criteria of R2=0.76, RMSE=1.42 (mm day-1), NS=0.7 and WI=0.89 had the highest accuracy compared to other models and showed the best performance. Also, the evaluation of the results of the models in Isfahan station showed that the eighth scenario of the M5Rules model, having the evaluation criteria of R2=0.8, RMSE=1.85 (mm day-1), NS=0.8 and WI=0.94 had the best performance compared to other models and the M5Rules model was selected as the best model. Also, the seventh scenario of the M5P model had almost the same performance as the eighth scenario of the M5Rules model and showed a good performance. Therefore, M5P and M5Rules models successfully predicted reference evapotranspiration. One of the limitations of the present study is the lack of access to dew point temperature and solar radiation data. Therefore, the use of these parameters is suggested for further studies.

The constant need to increase agricultural production, along with more and more frequent drought events in the country, requires a more accurate assessment of irrigation needs and thus a more accurate estimate of actual evapotranspiration. Prediction of water consumption over agricultural areas is important for agricultural water resources planning, management, and regulation. It leads to the establishment of a sustainable water balance, mitigates the impacts of water scarcity, as well as prevents the overusing and wasting of precious water resources. As evapotranspiration is a major consumptive use of irrigation water and rainwater on agricultural lands, improvements of water use efficiency and sustainable water management in agriculture must be based on the accurate estimation of ET. Irrigated agriculture is expected to produce more crops with less water consumption in the future. Therefore, accurate forecasting of water demand along with sustainable management and more efficient methods to meet the growing demand under scarce water resources is necessary. The models used to predict evapotranspiration should be used in different regions with different climates to evaluate their performance. Therefore, in this research, tree models and Hargreaves were used in Yazd and West Azerbaijan provinces, which have different climates, in order to evaluate the performance of the models used.

In recent years, water management issues have been addressed using models derived from artificial intelligence research. In recent years, water management issues have been addressed using models obtained from multiple types of research. The use of combined models has made significant progress in recent years. combined models are able to perform processing in a short period of time and at the same time with high accuracy. Using these models, the main challenging aspects are represented by the selection of the best possible algorithm, the selection of suitable representative variables and the availability of suitable data sets. Therefore, in this study, the ability of tree models (M5P and RF) with Hargreaves model (Hs) in estimating daily evapotranspiration in Urmia and Yazd stations during the period of 2000-2021. The noteworthy point is that in the combined tree-Hargreaves model, the used tree models were used as input to the Hargreaves model. The combined model has been used for the first time in this research and the use of this model can predict daily evapotranspiration as well as possible.

The results of the model are performed using 5 evaluation criteria of Coefficient of determination, Root mean square error, Nash-Sutcliffe coefficient, and Wilmot’s index of agreement. In all the used models, the best scenario was the model whose input included parameters of minimum temperature, maximum temperature, relative humidity, wind speed, and sunshine hours. Comparison and evaluation of standalone tree models showed that in the Urmia station two models RF-5 and M5P-5 had less error (0.4 and 0.38-mm day-1, respectively) than other standalone models. Similarly, in the Yazd station, RF-5 and M5P-5 models have higher accuracy (0.36 and 0.35 mm day-1(, respectively) than other standalone models. For combined models, the obtained results showed that the fifth scenario of the M5P-Hs model provided the best performance in Urmia and Yazd stations with the lowest error (0.33 and 0.24 mm day-1) respectively. It was also concluded that the fifth scenario of the RF-Hs model in Urmia and Yazd stations had a lower error (0.36 and 0.26 mm day-1) than other models, respectively. Finally, tree models have increased the accuracy of the Hargreaves model in this research.

Finally, the RF, M5P, RF-Hs and M5P-Hs models were able to predict daily evapotranspiration values in the shortest time and with the highest accuracy. However, the results showed that the lower the model inputs, the weaker the model prediction. The results of this research showed that the combination of tree models with Hargreaves model is able to predict daily evapotranspiration values with high accuracy compared to individual models. The results of this research showed that the wind speed parameter is one of the most important meteorological parameters needed in estimating daily evapotranspiration, so adding this parameter results in the highest accuracy in all models. Also, due to the important role of wind speed in predicting daily evapotranspiration values and the unavailability of the maximum wind speed parameter in this research, it is recommended to use the maximum wind speed parameter as one of the model inputs for further studies.

Evaporation is one of the most complex and important processes in studying hydrological and meteorological factors and plays a major role in determining the energy balance equations on the earth's surface. So, knowing the exact amount of evaporation volume is important for monitoring and correct management of water resources, irrigation planning, determining the irrigation needs, estimating evaporation from the reservoir of dams and modeling hydrological projects, especially in arid and semi-arid regions. On the other hand, modeling such a complex process in which many parameters interact with each other is so difficult that it is not possible to simplify this issue without multiple assumptions. Therefore, accurate estimation of evaporation has always been of great importance. Many experimental methods have been presented in estimating evaporation, but since these methods require a lot of input data or it is not possible to measure the variables in all areas, many of these methods have lost their effectiveness. Therefore, it is necessary to use methods which need fewer number of meteorological variables and estimate the evaporation with high accuracy. Therefore, the aim of the current research is to evaluate and present the most accurate model of evaporation estimation using three data-driven models in six synoptic stations in arid, semi-arid and humid climates of Iran, so that the proposed model, in addition to having sufficient accuracy, requires fewer input parameters to estimate evaporation even when there is no sufficient data.

In this regard, the ability of three machine-learning methods of gradient boosted tree (GBT), generalized linear model (GLM) and artificial neural network-multi layer perceptron (MLP) in estimating the amount of pan evaporation in dry (Yazd and Bafq stations), semi-arid (Birjand and Siah-Bisheh stations) and humid climates (Sari and Ferdous stations) were investigated. Daily parameters of some fundamental and effective meteorological variables on evaporation during the time period of 2001-2020 were collected. In order to investigate the possibility of using different combinations of meteorological parameters to estimate the evaporation as accurately as possible, six different combinations of meteorological parameters (average temperature, relative humidity, and wind speed and sunshine hours) were considered. Also, to evaluate the accuracy of the mentioned models, four assessment criteria were used including root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R) and scatter index (SI). Furthermore, diagrams of time series of the best models and the distribution diagram of observed and predicted pan evaporation by the models were presented and the most suitable combination of meteorological parameters that had suitable accuracy for estimating pan evaporation was suggested.

The results showed that in Birjand, Yazd, Ferdos, and Siah-Bisheh stations, MLP-VI with RMSE of 1.97, 1.95, 1.97, 2.91, respectively, performed more accurate than other studied models. Moreover, In Sari station MLP-IV and in Bafq station, MLP-V, with RMSE of 1.41 and 1.92, respectively, provided the most precise estimates of evaporation values. Finally, it can be comprehended that in all three studied stations, MLP provided the most accurate estimations of the amount of pan evaporation and it is suggested as a method with high degree of accuracy. Furthermore, GBT presented the weakest performance in comparison with other studied models. The mentioned trend about the high accuracy of the mentioned models for all studied stations can also be concluded from presented Figures. So, it can be inferred that the accurate models mentioned in each station had the least distribution around the bisector line and had the most accuracy and the least error. In other words, it is possible to estimate the evaporation values in all stations with the meteorological data of temperature, relative humidity, sunshine hours and wind speed with acceptable accuracy.

Evaporation is one of the main components of water balance in agriculture and is one of the effective and influential factors for suitable irrigation planning. Therefore, accurate estimation of this parameter has a significant role on reducing excessive water consumption. So, in this study, three data-driven models of MLP, GBT and GLM were implemented in six stations including Yazd, Birjand, Sari, Bafq, Siah-Bisheh and Ferdous. The obtained results indicated that the sixth scenario using all utilized meteorological parameters in Yazd, Birjand, Siah-Bisheh, and Ferdous stations, forth scenario in Sari and fifth scenario in Bafq station with the lowest error provided the most accurate estimates of the evaporation and may be recommended for proper estimation of pan evaporation values.

Due to population growth and Iran's location in arid and semi-arid regions of the world, the need for water and food has increased and as a result, the pressure on water and soil resources will be more than before. On the other hand, the risk of drying up Lake Urmia, which causes environmental problems in the region, requires macro-water planning for the region and the use of optimal cultivation pattern to deal with water scarcity. Therefore, optimal use of water preserves water resources and increases the quality of products. Today more than ever, increasing the production of strategic crops such as wheat requires the proper use of water resources. The main source of food for the Iranian people is wheat and related products, and any action that increases the yield of wheat due to limited soil resources, especially water resources, is important and necessary at the same time. In recent years, significant advances have been made in modeling product growth and development using mechanical models. Plant growth models are increasingly used in the analysis of agricultural systems and simulate the plant's response to growth factors using mathematical equations. The AquaCrop model is one of the dynamic and user-friendly models developed by the FAO. The AquaCrop model receives information about farm, plant, soil, irrigation and climate, and ultimately predicts important parameters such as crop. Wheat yield simulation allows efficient management and better planning under various environmental inputs such as soil and water. To achieve higher accuracy and less model error, field parameters must be properly calibrated by the model to achieve proper performance. Also, calibration of the model, if not done correctly, causes a high error prediction by the model, which leads to incorrect management, water loss, plant drought and other cases. Therefore, using a model that has accurate and close prediction to the AquaCrop model and requires fewer input parameters is essential, which saves time, reduces costs and eliminates calibration errors. However, this model requires relatively large input parameters and is a time-consuming model in the presence of multiple scenarios.3

In recent years, smart models have been able to show high accuracy and become reliable models. Therefore, in the present study, to solve this problem and develop a model with less input data, using the ANN, SVR and SVR-FFA intelligent models and creating 440 scenarios in 2 farms, the performance of the AquaCrop model was compared.99WestW2 farm is located in Miandoab city and has a yield of 6.588 (ton ha-1) and WestW10 farm is located in Mahabad city and has a yield of 5.05 (ton ha-1).

The results of the model are performed using 5 evaluation criteria of Correlation coefficient, Root mean square error, Nash-Sutcliffe coefficient, Wilmot’s index of agreement and, Mean absolute percentage error. The results of this study showed that for both 99WestW2 and WestW10 farms, the SVR-FFA3 model could have the lowest error rate, so that for the yield index, the RMSE value for the mentioned farms was 0.033 and 0.069 (ton ha-1), respectively. The use of three models SVR, SVR-FFA, and ANN and their comparison with the AquaCrop model to predict wheat yield has been done for the first time in this study. The SVR model was able to show the highest accuracy after the SVR-FFA model. For 99WestW2 farm, it can reduce the error rate to 0.043 (ton ha-1) and for WestW10 farm to 0.077 (ton ha-1) and show good performance. The ANN model, after the SVR model, was able to show acceptable accuracy. The ANN model for 99WestW2 farm was able to reduce the error rate to 0.123 (ton ha-1) and for WestW10 farm to 0.094 (ton ha-1). Finally, the ANN model had a relatively higher error than the SVR-FFA and SVR models, respectively, and showed a relatively lower performance than the two models.

Finally, the intelligent SVR-FFA, SVR and ANN models, despite having the least number of inputs, were able to predict yield values in the shortest time and with the highest accuracy. However, the results showed that the lower the model inputs, the weaker the model prediction. For further studies, it is suggested that the ANN model be combined using the firefly algorithm (MLP-FFA) to increase the accuracy of the ANN model and make more accurate predictions of wheat yield.

Climate change and its consequence impacts on the different phenomena of earth are serious mankind concerns during recent years. Climate change and global warming have very significant negative impacts on different resources including water and ice resources, forests, pastures, agricultural fields, industry and finally human life. Air temperature and precipitation variations are primary effects of climate change on the atmospheric elements. Hence, the assessment of the atmospheric element for an instance temperature has critical importance. Temperature rise caused by climate change have serious negative impacts on agricultural activities through increasing the evaporation and the possibility of droughts. Because climatological elements have nonlinear behavior and they are not function of a certain statistic distribution therefore a tendency for using non-parametric approaches especially Mann-Kendall is growing. The complicated nature of physical processes and lack of adequate knowledge in the climate models have caused creating statistical models and their development for defining these processes. The application of these models for reconstruction of past values and predicting of future values has been called time series. The aim of current research is analyzing the variation trend of mean maximum monthly temperature using Mann-Kendall test, mean maximum monthly temperature with time series method, determining proper pattern and prediction of temperature variations at the Northwest of Iran in the following years.

In this research the trend of mean maximum temperature variations in 12 selected stations in Northwest of Iran in a 24 years period was investigated. At first, the trend of variation data series for was tested using Mann-Kendall approach. Then, mean maximum monthly temperature was predicted using time series model. Minitab 17 software was applied in order time series model development and prediction purposes. Total number of data for each set was 285 where 80% of them were considered for calibration and 20% for model validation. The performance of models was investigated based on Model Efficiency Coefficient (CE) and Correlation Coefficient (R) indices. The CE varies between ∞- to 1 and the closer values to 1 indicates more accurate model performance. Finally, temperature predictions were done for following 8 years based on developed models.

The obtained results of application of Mann-Kendall test for determining mean maximum temperature trend in 12 studied stations in the Northwest of Iran clarified an increasing behavior for all stations. Increasing trends in Ahar and Sarab station were significant at the level of 95% and in the Tabriz, Marageh, Miyaneh, Ardabil, Khalkhal, Urmia, Khoy and Mahabad stations the significance level was 99%. Regarding to the basic assumptions in time series modeling, before starting model creating, the normal and static situation of data series was tested. The obtained results of these tests also showed a linear increasing trend in the investigated stations. Consequently, seasonal and non-seasonal differential process on initial series in the studied stations was conducted to model recognize through ACF and PACF differential series graphs. The temperature variations along different seasons of year in all stations proved more increasing for all stations in the winter in comparison with other seasons.
Considering 12th differential level due to seasonal characteristic of data, ACF and PACF graphs of differential series were plotted and a correlation was observed between data in first lag. To create series model, seasonal model of SARIMA(p,d,q)(P,D,Q)ω was applied. After calibration and validation of final models for studied stations, these models were applied to for predicting 8 following years (2018-2026) and were compared with basic period (1994-2017). According to the predictions, mean maximum temperature in all station shows an increasing in comparison to the basic period. The highest increasing amount is for Jolfa station with 4.39˚C and the lowest value was determined for Parsabad station with 0.69 ˚C. The variations of temperature was assessed in seasonal scale for 8 upcoming years. The comparisons of temperature variation for all stations in the different seasons showed increasing behaviors in all stations in winter in comparisons with other seasons.

Mean maximum temperature in 12 studied stations was modeled by time series. High values for R and CE in these stations proved high accuracy of this method for predicting of air temperature. After model development and selection of the most proper model for studied stations, the prediction of temperature was performed for 8 following years for each station. The temperature variations in this duration were investigated seasonally and the results showed that the maximum temperature increasing for all stations will occur in the winter. Temperature increasing in winter months may cause negative impacts like change in precipitation pattern from snow to rain, early melting of region snow reservoirs, incomplete vernalization of the seeds and early start of growing season with a risk of frost hazard for crops.

In the hydrologic cycle, evaporation is the primary step that causes water loss. Evaporation takes into account various parts of the water balance under completely different climates, and its correct prediction is very important for water resources management. The importance of evaporation and its impact on surface water balance is highlighted through its relation to climate change and global warming. The latest outputs of meteorological models suggest that global warming has caused an increase in evaporation from the land surface and surface water bodies, which is anticipated to have a serious impact over time on water resources management and the global population. In arid and semi-arid regions, accurate prediction of evaporation is very important for decision-makers due to water scarcity. Estimating daily evaporation with the highest accuracy and in the fastest possible time is essential to determine the water needs of different products, design irrigation programs, and manage water resources in different areas, especially when there is insufficient meteorological information. Evaporation has complex and non-linear behavior. Also, the evaporation parameter is not measured in some meteorological stations. Furthermore, meteorological stations are not correctly distributed in many developing countries including Iran. Since coastal areas have more evaporation than others, in many cases the amount of evaporation is higher than the global average. Despite the high importance of evaporation in coastal areas, very few studies have predicted this parameter in Iran. Moreover, accurate prediction of water loss in these areas leads to a better understanding of the hydrological cycle and is essential for optimal water management and agriculture. Thus, the purpose of this research is to predict daily evaporation values in four coastal stations of Abadan, Ramsar, Bandar Abbas, and Bandar Anzali.

The main meteorological parameters including average relative humidity, minimum relative humidity, maximum relative humidity average temperature, minimum temperature, maximum temperature, sunshine hours, and wind speed, under separate scenarios, as input for support of vector regression (SVR) and SVR with firefly algorithm (SVR-FFA) for estimating evaporation values were used on a daily scale. Statistical parameters in the time period of 1990-2021 were utilized as input to the mentioned models. In order to evaluate the performance of the implemented models, various statistical parameters were used, including correlation coefficient (R), root mean squared error (RMSE), Nash-Sutcliffe coefficient (NS), and Willmott's Index of Agreement (WI). To better estimate the daily evaporation values, eight different scenarios were used as the combinations of input parameters.

Based on the obtained results for all studied stations, the SVR-FFA-8 showed the least error with RMSE = 2.843 (mm day-1) for Abadan station, RMSE = 1.13 (mm day-1) for Ramsar station, RMSE = 1.985 (mm day-1) for Bandar Abbas station and RMSE = 1.225 (mm day-1) for Bandar Anzali station. For the indices of correlation coefficient, Nash-Sutcliffe coefficient, and Wilmott’s index of agreement, the SVR-FFA-8 model also indicated in the highest values between observed and predicted amounts. Also, the indices of correlation coefficient, Nash-Sutcliffe coefficient, and Wilmott’s index of agreement illustrated the highest accuracy in Abadan station for all combinations compared to other stations, which shows the high correlation of observed and predicted values in this station. After SVR-FFA-8, SVR-FFA-7 model in Abadan and Bandar Anzali stations and the SVR-FFA-6 in Ramsar and Bandar Abbas stations showed acceptable performance. Thus, the RMSE for Abadan and Bandar Anzali stations is 2.995 (mm day-1) and 1.272 (mm day-1), respectively, and for Ramsar and Bandar Abbas, 1.176 (mm day-1) and was obtained 1.993 (mm day-1). Comparing the results of SVR combinations also revealed that for Abadan, Ramsar, and Bandar Anzali stations, SVR-8 and for Bandar Abbas station, SVR-6 showed the highest accuracy among all SVR combinations in all four studied stations. Also, Ramsar station presented the lowest RMSE compared to other stations. After the SVR-8 model for Abadan, Ramsar, and Bandar Anzali stations, the SVR-7 and SVR-6 models for the Bandar Abbas station showed a weaker performance due to having less input parameters. The comparison between the input parameters also concluded that the sunny hours is the most important parameter in predicting the daily evaporation values in all four stations, thus increasing the accuracy of the models.

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.

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.

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.

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.

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%.

Accurate estimation of reference evapotranspiration (ET0) is essential in water management in the agricultural sector, especially for arid and semi-arid climates. ET0 plays a vital role in the water and energy cycle and is an essential link between ecological and hydrological processes. Therefore, accurately estimating ET0 is a major issue for understanding the water cycle in continuous soil-plant-atmosphere systems. The traditional ET0 estimation methods are mainly based on physical principles, such as Priestley-Taylor, Hargreaves, and Samani, which have many limitations in accurate ET0 estimation in cases of minimum meteorological parameters (such as radiation solar, wind speed, and air temperature). Numerous studies have focused on ET0 estimation using terrestrial data. However, in the case of a lack of meteorological stations, the conventional methods of estimating ET0 using ground data will be inefficient, so remote sensing (RS) provides the possibility to fill such a gap, in such conditions, satellite images are the most effectivefor evaluating ET0 in large areas. Because satellite images have a suitable spatial and temporal resolution, the time series of satellite images can be used to estimate ET0. The successful estimation of ET0 from satellite images paved the way for its prediction using artificial intelligence models. The primary satellite imagery sources can be obtained from Landsat, Moderate Resolution Imaging Spectroradiometer (MODIS), and Global Land Surface Satellite (GLASS). Remote sensing data provides the possibility of recording more information through satellite images. Remote sensing methods can be used to extract vegetation information and different types of radiation, which help estimate ET0.

In the current research, two different agro-climatic locations including Ahvaz and Tabriz stations were selected. According to De Martonne classification method, Ahvaz was classified as dry climate and Tabriz as semi-arid climate. In this research, random forest (RF) and multi-layer perceptron (MLP) algorithms have been used to estimate monthly ET0 in Ahvaz and Tabriz stations. The input parameters were selected from Landsat 8 and MODIS satellite images in the time period of 2014 to 2021. The utilized parameters were the monthly average, Landsat Land Surface Temperature (LSTLand), MODIS Land Surface Temperature (LSTMOD), Landsat Satellite Normalized Difference Vegetation Index (NDVILand) and MODIS Normalized Difference Vegetation Index (NDVIMOD). To evaluate the accuracy of the input parameters and models, the estimated monthly ET0 was evaluated with the monthly ET0 of the FAO-Penman-Monteth equation.

The input parameters for implemented models were Landsat land surface temperature (LSTLand), MODIS land surface temperature (LSTMOD), Landsat Satellite Normalized Difference Vegetation Index (NDVILand), and MODIS Normalized Difference Vegetation Index (NDVIMOD). Six possible scenarios were defined to estimate monthly ET0. The first two scenarios were considered as a single parameter (scenarios 1 and 2) and other scenarios were evaluated with two input parameters. Scenarios 3 and 4 were evaluated based on the parameters of the Landsat satellite and MODIS sensor, respectively. In scenarios 5 and 6, monthly ET0 was estimated with Landsat and MODIS NDVI and Landsat and MODIS LST, respectively, to determine the effect of NDVI and LST values on ET0 estimation. According to the obtained results, for the MLP and RF models in Ahvaz station, the value of R2 ranges from 0.440 to 0.972 and 0.271 to 0.983, respectively. In Ahvaz station, the lowest and highest RMSE is 0.279 mm.month-1 (RF-5 model) and 1.396 mm.month-1 (RF-4 model), respectively. Additionally, in this station, the highest and lowest values of NS are 0.962 (RF-5 model) and 0.042 (RF-4 model), respectively. According to the obtained results, in estimating the monthly ET0, the best performance is related to MLP-6 (R2=0.972, RMSE=0.348, and NS=0.940) and RF-4 (R2=0.983, RMSE=0.279, and NS=0.962). The highest and lowest values of R2 in Tabriz station were 0.988 and 0.186, respectively. Moreover, MLP-4 and RF-5 models in this station have the lowest and highest RMSE, respectively. The results showed that in Tabriz station, the best performances were related to MLP-4 (R2=0.988, RMSE=0.299, and NS=0.935) and RF-4 (R2=0.979, RMSE=0.302, and NS=0.933). In addition, in this station, the RF-5 model has the weakest performance among all models with R2=0.186, RMSE=1.169, and NS=0.012.

The results showed that 1) the accuracy of monthly ET0 estimation in Ahvaz (arid climate) and Tabriz stations (semi-arid climate) with scenario 4 including LSTMOD and NDVIMOD was better than other investigated scenarios; 2) in estimating monthly ET0 using a single input parameter including LSTLand (scenario 1) and LSTMOD (scenario 2), in both Ahvaz and Tabriz stations, scenario 2 had better performance with both MLP and RF models; 3) estimation of monthly ET0 in Ahvaz and Tabriz stations has performed best with RF-4 and MLP-4 models, respectively, with LSTMOD and NDVIMOD input parameters (scenario 4); 4) in the comparison of scenario 5 (NDVILand, NDVIMOD) and scenario 6 (LSTLand, LSTMOD) in both RF and MLP models, scenario 6 has the best performance in estimating monthly ET0; and 5) in the comparison of monthly ET0 estimation in both arid and semi-arid climates, the best performance with a high correlation coefficient was obtained with the MLP model in semi-arid climates.

Evapotranspiration is one of the main components of water balance in agriculture and is one of the effective and efficient factors for accurate irrigation planning and management. Direct measurement of evapotranspiration values is time consuming and costly. On the other hand, modeling such a complex process in which many parameters interact with each other is so difficult that it is not possible to simplify the issue without multiple assumptions. Therefore, accurate estimation of this parameter has always been considered by the researchers. In the other point of view, the FAO-56 method was used as the accurate and accepted method for calculating reference evapotranspiration. One of the weaknesses of this model is its dependence on various meteorological variables. Therefore, it is necessary to use methods which need low number of meteorological variables and estimate the reference evapotranspiration with high accuracy. Additionally, due to the use of many meteorological variables and the complexity of the calculations, it is difficult to use FAO-56 method in all regions. Therefore, in the recent years, many researchers implemented machine learning methods to estimate reference evapotranspiration. Most studies in the field of reference evapotranspiration estimation use experimental models that require all the effective reference evapotranspiration parameters to provide an acceptable estimate. Hence, the aim of the current study was to present a superior model from three machine learning models, including random forest (RF), gradient boosted tree (GBT) and generalized linear model (GLM) for estimating reference evapotranspiration in three synoptic stations located at arid, semi-arid and wet climates of Iran. To the best of our knowledge, the proposed GBT and GLM methods have not been used for estimating reference evapotranspiration in the mentioned stations.

In this research, the FAO-56 method was used to estimate the reference evapotranspiration. Also, three machine learning methods including GBT, GLM and RF were implemented to estimate the amount of reference evapotranspiration. Daily parameters of some fundamental and effective meteorological variables on evapotranspiration during 21-years statistical period (2000-2020) were collected in three stations located at different climates including Yazd station (arid), Birjand station (semi-arid) and Sari station (wet). In order to investigate the possibility of using different combinations of meteorological parameters to estimate the reference evapotranspiration as accurately as possible, seven different combinations of meteorological parameters were defined. The accuracy of the utilized methods was evaluated using three criteria such as correlation coefficient, scattering index and Nash-Sutcliffe coefficient. Additionally, Taylor diagrams were implemented for evaluating the accuracy of the used methods. It should be noted that the Taylor diagram shows the three parameters of root mean square error, correlation coefficient and standard deviation simultaneously in one figure. Also, the most suitable combination of meteorological parameters that had good accuracy for estimating reference evapotranspiration, was suggested.

The results showed that in the best model at Birjand Station, and Yazd stations scenario number three by two meteorological variables of temperature and wind speed and in Sari station the scenario number two with temperature and relative humidity, the gradient boosted tree model was reinforced with Nash-Sutcliffe coefficient of 0.804, 0.826 and 0.733, with correlation coefficient of 0.997, 0.997 and 919 and scatter index of 0.249, 0.218 and 0.361 and the generalized linear model with Nash-Sutcliffe coefficient of 0.892, 0.931 and 0.869 correlation coefficient of 0.952, 0.966 and 0.933 and scatter index of 0.185, 0.137 and 0.252, respectively. Finally, the RF method with Nash-Sutcliffe coefficient of 0.954, 0.956 and 0.929, correlation coefficient of 0.978, 0.978 and 0.965 and scatter index of 0.121, 0.110 and 0.186 had good performance for estimating the reference evapotranspiration. On the other hand, in all methods, the scenario number seven using the meteorological parameters of temperature, relative humidity of sunny hours and wind speed in all three stations, presented the most accurate performance. Therefore, all three methods may be proposed as models with high degree of accuracy for estimating reference evapotranspiration.

Reference evapotranspiration is one of the main components of water balance in agriculture and is one of the effective and influential factors for accurate irrigation planning. Therefore, accurate estimation of this parameter has a significant role on reducing excessive water consumption. In this study, three data-driven models of RF, GBT and GLM were used in three stations of Yazd, Birjand and Sari stations. The obtained results indicated that the seventh scenario using all four meteorological parameters in all stations with the highest correlation coefficient, the lowest scatter index and the highest Nash-Sutcliffe coefficient provided most accurate estimates of the reference evapotranspiration and may be recommended for proper estimation of reference evapotranspiration.

Estimating reference evapotranspiration (ET0) is a fundamental requirement of agricultural water management. However, the lack of necessary meteorological data makes it difficult to estimate ET0 using the FAO-Penman-Monteith equation wider areas. Therefore, this research examines the estimation of daily reference evapotranspiration using MODIS Land Surface Temperature (LST) from satellite imagery in two climates of Tabriz and Rasht. ET0 has been estimated using two random forests (RF) and random forests optimized with genetic (GA-RF) algorithms. The parameters used in both stations include the combination of daily land surface temperature (LSTday), nightly land surface temperature (LSTnight) and average land surface temperature at night, and day (LSTmean). The obtained results indicated that LSTmean has an excellent ability to estimate ET0 in both stations. In Tabriz station with a semi-arid climate, GA-RF-7 model with RMSE=0.516 and in Rasht station with a very humid climate, the GA-RF-5 model with RMSE=0.868, have the best performance among the studied models. Moreover, the evaluations revealed that the temperature of the earth's surface at night is as important as the temperature of the earth's surface during the day, and by combining these two parameters, satisfactory results may be obtained.

In the present research, three data-driven models including M5P, REP tree, and random forest were used to estimate daily reference evapotranspiration. The abilities of these three models to estimate reference evapotranspiration were studied in single and combined modes. To this end, the daily meteorological data of five synoptic stations in Kerman province in the period from 2000 to 2020 were used. A combination of meteorological variables, using sensitivity analysis versus the reference evapotranspiration values ​​obtained from FAO-Penman-Monteith, was considered as input for each of the mentioned models. Finally, the accuracy of the mentioned models and empirical methods in estimating the evapotranspiration of the reference plant were compared using statistical indicators, and the superior model was selected. The results of validation data showed that the M5P model in the form of individually (RMSE = 0.083 and NS = 0.998 in Bam station) and the weighted averaging in the form of the ensemble (RMSE = 0.155 and NS = 0.994 in Bam and Sirjan stations) in all stations had better results for estimating evapotranspiration rates than other methods. In general, tree models, especially M5P, had better results in estimating daily evapotranspiration than empirical models.

Detection of trends in streamflow characteristics such as low flows is so important in optimal water resources management. This is especially true in arid and semi-arid climates that water is vital for human being and all other living things. Lorestan province, located in the west part of Iran was considered as the study area. Daily mean streamflow data of hydrometric stations during the time period provided by Lorestan Regional Water Company located in Khorramabad city. Eight hydrometric stations selected for this purpose. The altitude of the chosen stations varied between 770 and 2050 m above the mean sea level. Literature review on this subject indicated that low flow trends in Lorestan province river has not been before studied. On the other hand, such a study is so important for better management of fresh water in the region, therefore, conducting this study seems to be necessary.

In the first step of this study, flow duration curves (FDC) plotted for the stations. Two indices including the Q0.05 and Q0.10 were considered here as measures of low flows. The Q0.05 index value extracted from the FDC as a five percent low flow quantile. This index shows that the streamflow discharge is less than that in five percent of the days in a year. In addition to Q0.05 the second measure namely Q0.10 is read from FDC of the selected sites. Therefore, for each site, these two indices were gathered during the used time period. Then, trends of the mentioned indices are analyzed using the Mann-Kendall method. In this regard the effect of serial correlations removed from the time series. Moreover, the slope of trend lines estimated using the Sen’s estimator approach. Then the selected quantiles fitted for suitable statistical distributions. In this regard the well-known method namely Kolmogorov—Smirnov was used.The parameters of the selected distribution estimated using the maximum likelihood method. Finally, at each site the values of low flows corresponding to different return periods i.e. 2, 5, 10, 25 and 50 years were estimated. It is worthy to mention that the missing data are not reconstructed here, because the used approach (Mann-Kendall) is a non-parametric method and no need for reconstruction of the missed values.

Results showed that two stations namely Sokaneh-Nahaee and Cham-Chit had significant first-lag serial correlation for Q010 time series. The other six sites had no significant serial correlation for this quantile. Furthermore, in the case of Q0.05, three sites showed significant first-lag serial correlations. So, the modified Mann-Kendall method was used for these time series. This analysis indicated that the mentioned series auto-correlation was significant in 5% level. The conventional MK method was used to detect trends in other time series which their serial correlations are not significant. Results showed that trends of Q0.10 quantile series in four out of the eight hydrometric stations were downward and two of them were statistically significant at 1% level. The two others had no significant trends. At the same time the other sites showed upward trends in Q0.10 series. However, among these series one station namely Cham-Chit had statistically upward trend at 1% level. Trends in the other three sites are not statistically significant.  In the case of Q0.05 series, the six out of the eight stations showed negative trends, in which two sites had statistically significant trends at 1% level. The names of these sites are Sokaneh-Nahaee and Vanaee. In contrast, the two other time series showed positive trends, in which only one of them (namely Cham-Chit station) had statistically significant trend at 1% level. The trend line slopes of Q0.10 quantile time series are ranged between -0.0844 (in Sokaneh-Nahaee) and +0.12 (in Cham-Chit). However, in the case of Q0.05, this range was between -0.0885 (in Sokaneh-Nahaee) and +0.008 (in Cham-Chit station).

Some of the stations showed upward trends in low flows in Lorestan province rivers and some others showed downward trends. It is worthy to note that the time periods of the used data of the stations are not same. Although Masih et al. (2011) reported that the mean daily stream flows (i.e. Q0.50 or 50th quantile also called median) of Zagros Mountain rivers had downward trends. Investigation of sites location indicated that no obvious pattern in trends of low flows existed in the area under studied. This is true for both two low flow indices (i.e. Q0.05 and Q0.10) used for hydrometric stations. The findings of this study would be helpful in better management of surface water in Lorestan province.

The gradual increase in the world’s population requires continues increase in agricultural production. Climate change is one of the challenges of our society and frequent droughts affect large areas of the world, which requires more accurate management of water resources, both globally and in local catchments. Accurate estimation of components of the hydrological cycle is essential for proper irrigation scheduling. Most of the precipitation received by the earth is returned to the earth’s atmosphere by the process of evapotranspiration. On the other hand, because every process that takes place in the plant is dependent on water and one of the most common uses of water in the plant is evapotranspiration, so reducing amount of the water will have adverse effects on photosynthesis, crop production, product quality, etc. The complex and nonlinear relationship between the factors affecting the process of evapotranspiration, has caused researchers today to use new methods to accurately identify and predict this parameter. Reference evapotranspiration is a concept that uses the crop coefficient to obtain the actual water requirement. According to the FAO proposal, the FAO- Penman- Monteith equation was introduced as a benchmark method for calculating reference evapotranspiration values when measurements of this parameter are not available and there is no access to lysimetric data. One of the major advantages of this model is its physical basis and global validity, but this equation needs a large number of meteorological parameters that are often not available, instead empirical equations with low meteorological variables or modern methods such as artificial intelligence and machine learning methods can be used.

In this study, meteorological data related to two stations of Astara located in the humid region and Sirjan located in the arid region of Iran in the period of 2000-2020 were studied to predict the crop evapotranspiration values. As mentioned, the FAO- Penman- Monteith method has used as a standard method for calibration and evaluation of the other functional equations and machine learning methods. In this study, four types of empirical equations including Hargreaves –Samani, Makkink, Turk and Dalton were evaluated against the FAO- Penman- Monteith model. Also, modelling was performed using Support Vector Regression, Random forest and M5P Tree model. In this study, 70% of data were considered for training and 30% for testing. Finally, statistical parameters including root mean squared error (RMSE), correlation coefficient (R), scatter index (SI), Nash-Sutcliffe coefficient (NS) and Wilmot index (WI) were used to determine the performance of each mentioned methods in estimating reference evapotranspiration values.

Using different meteorological parameters in accurate prediction of evapotranspiration using 4 combined scenarios, calibration calculations were performed on 70% of data and validation calculations were performed on 30% of testing data implementing Weka software. The obtained results showed that the SVR3 and M5P3 models in Astara station with all meteorological parameters and having R= 0.993, RMSE= 0.201 and also, the SVR3 model in Sirjan station with R= 0.982, RMSE= 0.410 compared to the studied empirical methods provided better results in estimating the reference evapotranspiration and scenario 3 with all meteorological parameters was introduced as the top scenario. Among the empirical methods, Hargreaves- Samani was superior to some models only in Astara station. At Sirjan station, none of the empirical models performed better than the machine methods.

Accurate estimation of reference evapotranspiration in water resource management is essential. In this study, meteorological data from Astara and Sirjan stations were used to evaluate the ability of machine learning methods including SVR, RF and M5P to estimate the values of reference evapotranspiration and compared the results with empirical methods. The results showed that the high accuracy of the SVR3 model in both stations and in the next position M5P3 model for humid area. Empirical methods except Hargreaves- Samani had poor performance compared to data- driven models. Finally, the use of SVR and M5P methods in irrigation scheduling is recommended.

One of the climate variables with relatively large gaps in observation and significant importance in estimation of evapotranspiration is sunshine hours. In the present study, in order to reconstruction the sunshine hour data of several selected stations in Tabriz province, Iran namely,Tabriz, Sarab, Sahand and Maragheh during the period of 1990 to 2019, skill of intelligent approaches of SVR, ANN and RF was compared with statistical methods of normal ratio, geographical coordinates and weight correlation coefficient. Statistical indices of R, RMSE, MAD and Taylor diagrams were used for evaluation of comparisons. The obtained results showed that ANN and geographical coordinate methods have the highest accuracy in reconstruction sunshine hours among the selected intelligent and statistical methods, respectively. In Tabriz and Sahand stations, the geographical coordinate method with RMSE of 1.04 and 1.13 hours, respectively, in the Sarab station SVR with RMSE of 1.58 hours and in Maragheh station the normal ratio method with RMSE of 1.45 hours showed the highest accuracy in generating sunshine hours. Besides, RF method had the lowest accuracy in reconstruction of sunshine hours data. It can be concluded that in Tabriz, Sarab and Sahand stations, both types of intelligent and statistical methods have almost same accuracy, but in Maragheh station, statistical methods provided slightly better estimations.

Solar radiation is one of the key factors in the fields of agriculture, hydrology and meteorology and plays an essential role in various physical, biological and chemical processes such as snowmelt, evaporation, photosynthesis and crop production. Thus, accurate estimation of this parameter is very important. Accordingly, in this study, the amounts of daily solar radiation were estimated using artificial neural network and artificial neural network-genetic algorithm in six stations of Ardabil province including Ardabil, Bilehsavar, Sareyn, Germi, Meshgin Shahr and Nir. The data used in this research include maximum, minimum and average temperature, relative humidity and wind speed of the mentioned stations in a time period of two years (2017-2018) which are used in eight different combinations as input data of the models. Also, statistical indices of correlation coefficient, root mean square error, Wilmot index, Kling-Gupta efficiency and Taylor diagrams have been used to compare the obtained results. Generally, the obtained results indicated that among the artificial neural networks, the model of Bilehsavar station and among the artificial neural network-genetic algorithms, the model of Ardabil station recorded the most accurate results. Also, MLP-VIII model in Bilehsavar station with a correlation coefficient of 0.856, root mean square error of 0.319 (MJ/m2d), Kling-Gupta efficiency of 0.659 and Wilmot index of 0.893 have the best performance in the utilized models. Therefore, it is recommended to use artificial neural network-genetic algorithm method for estimation of solar radiation.