EVAPOTRANSPIRATION is one of the major components of hydrologic cycle and estimation of irrigation needs. In recent years the use of intelligent systems for estimating hydrological phenomena has increased significantly.In this study the possibility of using fuzzy inference system efficiency, creating a bridge between meteorological parameters and EVAPOTRANSPIRATION, and comparing the accuracy of reference EVAPOTRANSPIRATION using these systems were investigated. After analyzing the different models and different combinations of DAILY meteorological data, five models for estimating DAILY reference EVAPOTRANSPIRATION were presented. For these models, the calculated EVAPOTRANSPIRATIONfrom Penman- Monteith-FAO equation was considered as a baseand the efficiency of other models was evluated using statistical methods such as root mean squared error, error of the mean deviation, coefficient of determination, Jacovides (t) and Sabbaghet al. (R2/t) criteria. The used data were collected from Mashhad’s meteorological synoptic station for a period of 50-years (from 1339 to 1389).From the available data, 75 percentwas used for training the model and the rest of 25 percent was utilized for the testing purposes. The results derived from the fuzzy models with different input parameters as compared with Penman-Monteith-FAO and Hargreaves-Samani methods showed that fuzzy systems were very well able to estimate the DAILY reference EVAPOTRANSPIRATION.Fuzzy model so that the highest correlation with the four input variables (r=0.99) had in mind and evaluate other parameters, the model with two parameters, temperature and relative humidity (RMSE=0.96, MBE=0.18, R2=0.95, t=22, = and R2 / t=0.04) match very well with the model Penman - Monteith - FAO had stage training. In the test phase, training phase was very similar results and the model with the second phase of temperature and relative humidity will get the best match. According to the results of this study it can be concluded that fuzzy model approach is an appropriate method to estimatethe DAILY reference EVAPOTRANSPIRATION. In addition, the fuzzy models do not require complex calculations which are required forcombination methods.

EVAPOTRANSPIRATION plays an imperative role in management of regional water resources, climate change and agricultural production. In this study efficiency of some data-driven techniques, including support vector machine (SVM), artificial neural networks (ANN) and its hybrid with wavelet transform (WANN), multi linear regression (MLR) and decision tree (DT) for predicting EVAPOTRANSPIRATION rates at Scottsbluff Station in Nebraska have been monitored. For this purpose, 5 meteorological parameters utilized as inputs for the models. DAILY meteorological information, data used in this study, were between 2005-2013 years to train and test the models. In order to implement each of the models 8 scenarios were considered according to combination of input parameters. For evaluate performance of the studied techniques, three different statistical indices were used which included root mean square error (RMSE), correlation coefficient (R) and Nash-Sutcliffe coefficient (NSE). In addition, Taylor charts were used to test similarity between observation and prediction data. The results showed that at the Scottsbluff station, WANN8 (is the eighth scenario for the WANN model) according to the root mean square error (RMSE), correlation coefficient (R) and Nash-Sutcliffe equal to 0. 097, 0. 999 and 0. 999 performed better than ANN, SVM, MLR and DT. The SVM and ANN models also showed excellent accuracy, and the DT and MLR models performed worse than the other models despite their acceptable accuracy. As a conclusion, the results of the present study were proved that WANN provides reasonable procedures for modeling Scottsbluff at the Scottsbluff station.

In this research the ability of artificial neural networks (ANN) method was studied in estimation of DAILY potential EVAPOTRANSPIRATION (ETp) of grass reference crop and then compared with Penman-Monteith method. We used clamatic data for a 5-years period of Ekbatan station in Hamadan. The input data for ANN were maximum and minimum temperature, maximum and minimum relative humidity, wind speed and sunny hours and ETp were set as output data. The best ANN architecturewas selected on the basis of minimizing the root mean square error (RMSE). The architecture of one hidden layer with one processing element gave the least RMSE of 0.7 mm/day and determinationco efficient of 0.84. Whereas, the RMSE and determination coefficient of Penman-Mantieth were 1.2  mm/day and 0.84 respectively. Based on these results, it could be concluded that the ANN predicted ETp better than Penman-Mantieth method. The sensitivity analysis also showed that the minimum temperature and maximum relative humidity had the most and the least effect on input respectively.

Background and Objectives: 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. Methodology: 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. Findings: 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.Conclusion: 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.

Since a considerable part of the available water is wasted due to EVAPOTRANSPIRATION, a precise estimation of it in short-term and long-term periods is of great importance. In this paper, the capability of the M5 model tree and random forest (RF), as the artificial intelligence approaches, and in combination with the wavelet preprocessing, investigated to estimate the potential DAILY and weekly EVAPOTRANSPIRATION in the synoptic station of Babolsar. Given the time series structure of the input data, the two functions of Coiflet mother wavelet and Daubechies 6 wavelet in the decomposition levels of 3 to 8 were chosen. The four indices of correlation coefficient (R), index of agreement (Ia), Nash-Sutcliffe model efficiency coefficient (NSE) and root mean square error (RMSE) used to evaluate the presented models. The obtained results indicated that although all individual models have desirable efficiency in modeling the EVAPOTRANSPIRATION, the use of wavelet preprocessing enhances the performance of individual models in all cases while allows the simpler input scenarios to provide more desirable results. For instance, in the third input scenario (wind speed, maximum temperature, relative humidity, and dew point), the use of Daubechies 6 wavelet in the decomposition level of 5 increased the correlation coefficient of the DAILY model from 0. 908 to 0. 928 while reduced the RMSE from 0. 833 mm/day to 0. 722 mm/day. Similarly, the use of Coiflet-4 mother wavelet in the decomposition level of 5 raised the correlation coefficient of the weekly model from 0. 948 to 0. 961 while lowered the RMSE from 4. 55 mm/week to 4 mm/week. Therefore, in the present study, the efficiency of both individual and hybrid approaches in estimating the EVAPOTRANSPIRATION of DAILY and weekly periods is satisfactory. However, if the hybrid approaches employed, even the use of simpler and more accessible meteorological parameters will provide satisfactory results.

Downscaling methods seem to be a reasonable solution to solve the problem of having no simultaneous high spatial and temporal satellite data, and it is possible somehow to meet the requirement of having high spatialtemporal resolution satellite data for monitoring the natural phenomena such as EVAPOTRANSPIRATION, through these methods. Sentinel-2 satellite launched in 2015 enables to provide 10-m spatial resolution data with a 5-day revisit time,however, its sensor does not acquire data in thermal infrared wavelength. This study aims to generate 10-m DAILY EVAPOTRANSPIRATION maps based on Sentinel-2 and MODIS data fusion for Amir-Kabir Agroindustry farms. For this purpose, STARFM and improved TSHARP methods were applied for downscaling MODIS data to Sentinel-2 data. To achieve this goal, First, MODIS visible and near and middle infrared bands were downscaled by STARFM to 10-m spatial resolution. Then, improved TSHARP was applied for downscaling MODIS thermal band to 10-m spatial resolution and SEBAL algorithm fed by the downscaled bands, was used to produce DAILY EVAPOTRANSPIRATION map with 10-m spatial resolution. Assessing downscaled EVAPOTRANSPIRATION maps with those derived from FAO Penman-Monteith equation indicated a RMSE of 0. 64 mm/day showing efficient performance of the downscaling framework proposed for 10-m DAILY EVAPOTRANSPIRATION mapping in this study.

EVAPOTRANSPIRATION (ET), a major component of the hydrologic cycle, is important in water resources management and irrigation scheduling. Nowadays, due to the lack of the lysimetric data in weather stations, the ET values calculated by the standard FAO Penman-Monteith model (𝐸 𝑇 0) are used as benchmark values of grass reference crop. Also, the Penman-Kimberly model is widely applied for computing the alfalfa-reference crop ET (𝐸 𝑇 𝑟 ). In the present study, the meteorological data from 6 weather stations located in the Sistan-Va-Baluchestan Province covering a period of 10 years were used to calculate the 𝐸 𝑇 0 and 𝐸 𝑇 𝑟 values. Then, the 𝐸 𝑇 𝑟 to 𝐸 𝑇 0 ratios were computed for all six stations during the studied period. The Penman-Kimberly model at Mirjavah station had the worst result compared to other stations. The NS coefficient values for this station are the lowest (0. 07) and the SI and RMSE values for this station are 0. 43 and 2. 48, respectively, which is the highest value among the study stations. Finally, the contributions of the energy balance and aerodynamic components on the final ET values were determined using the Penman-Kimberly model, which showed the important influence of both components on the ET process. Consequently, the use of radiation-based models e. g. Priestly-Taylor model in these stations should be carried out by special care.

Extended abstractIntroductionSegzai plain, 40 kilometers from Isfahan city, with an area of about 40,000 ha, is considered a serious threat to this historical city. This plain, which until a few decades ago was a relatively prosperous reed and meadow, has now become a huge danger in terms of nature destruction and environmental pollution. Two natural and human factors play a role in the desertification of this region. Among the natural factors are low rainfall, high evaporation, the presence of limiting layers in the soil and strong winds and from human factors, excessive grazing and overgrazing of livestock as well as bush-cutting, rapid population growth and excessive exploitation of existing resources decline Underground water and most importantly, exploitation of surface mines, especially gypsum mines, can be mentioned. The main goal of this research was to evaluate the effectiveness of the SEBAL model for estimating the actual evaporation and transpiration of the Segazi Plain, considering the arid and semi-arid location of the region using the landsat 8 image. Materials and methodsTo do this research, first, landsat 8 images were processed. Extraction of required information from satellite images in this research was done during three main stages, i.e. pre-processing, processing and post-processing. In other words, in the pre-processing stage, after performing atmospheric, geometric and other necessary corrections, the image was referred to the ground. In the area of data processing, different highlighting methods and statistical analyzes and remote sensing were done in order to achieve the information layers of the plan. In order to evaluate the results in the image processing stage, the post-processing of the data based on various analyzes was used to evaluate the reliable layers in terms of accuracy and precision. After that, the SEBAL algorithm was implemented.  first the amount of net radiation (Rn) was calculated according to the temperature of the earth's surface and vegetation and the amount of energy reaching the earth, then the heat flux of the soil (G) was obtained to determine the amount of transfer capability The heat into the soil was determined, then it was determined to calculate the amount of sensible heat flux (H), which determines the loss of energy from the soil to space. Finally, after determining the sensible heat flux, evaporation and transpiration were calculated. The SEBAL algorithm calculates the energy balance equation in order to calculate the actual evaporation and transpiration of the plant. Results and discussionSurface albedo parameters (the highest and lowest weighted values are around 0.85 and 0.16), soil surface temperature (the highest and lowest weighted values are around 326 and 299 degrees Kelvin), NDVI vegetation index (the highest and lowest weight values related to areas with good vegetation close to +1 and related to water and water bodies close to -1), the amount of net energy reaching the surface of the earth (the highest and lowest weight values are about 703 and 210 Wm-2, soil heat flux (the highest and lowest weight values are about 130 and 35 Wm-2), sensible heat flux (the highest and lowest weight values are about 323 and 23 Wm-2 , momentary evaporation and transpiration (the highest and lowest weight values are about 0.842 and 0.225 mm) and DAILY transpiration evaporation (the highest and lowest weight values are about 20.2 and 5.4 mm) are among the most important effective parameters in this Sabal algorithm which were investigated in this research. Changes in actual transpiration evaporation (the highest weight values about 0.85 mm and the lowest weight values about 0.16 mm). The obtained results showed that the SEBAL model has well predicted evaporation and transpiration in areas that have vegetation, mostly agriculture and gardens, so that the amount of water loss through evaporation has been predicted close to the values found in the eastern synoptic station of Isfahan (airport Shahid Beheshti) is registered. ConclusionThe amount of error obtained in SEBAL calculation was 0.1%. The amount of real momentary evaporation and transpiration has been calculated in the range between 0.22 and 0.84 mm, according to the weather conditions of the region and the temperature of the air near the surface (27 to 50 degrees) and the amount of evaporation and transpiration recorded by the Penman-Monteith equation (30.0 mm in the east of Isfahan synoptic station), this value is in a reasonable range. Comparing the outputs of Sabal model with the amount of evaporation and transpiration obtained in the same station, which shows the root mean square error (RMSE) value of 0.1, indicates the suitability of this algorithm in calculating evaporation and transpiration in Segazi region. Considering the growing need of the country to prevent the wastage or excess consumption of water in the agricultural sector, either through changing the cultivation pattern or changing the irrigation methods, the application of the developed tool of the Sabal algorithm in this research can provide valuable information to the experts and managers of the water sector put agriculture. The results obtained from this implementation of this research showed that remote sensing has a good potential for estimating actual EVAPOTRANSPIRATION (ETA) by having different algorithms such as SEBAL algorithm and minimum ground information.

The SIMDualKc model is an irrigation scheduling simulation model that uses dual crop coefficient method for estimating ETc by computing two separate soil water balances in DAILY time-step, one for the soil evaporation layer from which Ke is computed, and the other one for the entire root zone to compute the actual Kcb adjusted to the soil moisture conditions. In this study, lysimetric measurements of EVAPOTRANSPIRATION rates relative to (Coriandrum sativum L.) during 2 years were used for model calibration and validation. Kcb values for coriandrum were found as 0.21 for the initial, 1.12 for the mid-season and 0.79 at harvesting period. Model results have shown a good agreement between the actual DAILY EVAPOTRANSPIRATION predicted by the model and the ones resulting in water balance calculation on drainable lysimeters, and root mean square errors of estimates (RMSE) of about 1.64 mm and 1.53 mm for the calibration and validation, respectively.The modeling efficiency EF and the index of agreement dIA were equal to 0.8 and 0.93, respectively, thus indicating good performance of modeling with SIMDualKc. Model estimates of evaporation (E) for validation and calibration years displayed an average of 181 mm, representing 25% of ETc. In conclusion, results show that the model is appropriate to simulate the DAILY EVAPOTRANSPIRATION adopting the dual Kc approach for coriandrum in west regions of Iran.

In recent years, automatic weather stations have been widely used for recording meteorological data in different time scales. Therefore the accurate estimation of ETo by combination equations can be evaluated using these set of short time scales data. DAILY ETo can also be calculated by summation of hourly ETo values. The purpose of this study is to compare the ETo values estimated by hourly and DAILY data. Totally, 7270 hourly meteorological data obtained from the automated weather reference station where placed in Shahid Bahonar University of Kerman, Iran during April to December 2005 and January to March 2006. The Penman-Monteith equations proposed by the Food and Agriculture Organization (FAO-56) and American Society of Civil Engineers (ASCE) were used for hourly and DAILY (24 hours) ETo estimation. The paired t- student test was used for comparison of estimated ETo values by two methods (DAILY and hourly summation) in each month. The results of this study showed significant differences between ETo values estimated by DAILY and hourly summation data in both equations at 5 percent level. The hourly summation method overestimated ETo values from 5.8 to 44.6 percent in different months using FAO-56 Penman-Monteith equation and from 7.4 to 47.6 percent using ASCE Penman-Monteith equation. The regression coefficients of correlation equations between the DAILY and hourly summation method in both combination models were strongly significant.