Population growth has resulted in rapid changes in urban landscapes in many countries, including Iran. Monitoring urban areas can be accelerated by utilizing remote sensing images and spectral indices in urban planning. This requires evaluating the performance of indices according to the application in different conditions, which can be challenging for users. This study was conducted to compare and analyze suitable solutions for analyzing urban indicators using satellite imagery and their effectiveness. For this purpose, Landsat-8 and Sentinel-2 images were first analyzed to extract spectral index; then automated threshold algorithms were applied to separate constructed areas. Results indicate that Sentinel-2 images perform better than Landsat images in general. Among the spectral indices, the UI index for Landsat and Sentinel-2 images in Rafsanjan with overall accuracy of 86.28 and 98.19, the NBI index for Landsat and Sentinel-2 images in Amol city with overall accuracy of 87.21 and 97.48, and the UI index in Landsat and IBI in Sentinel-2 for Isfahan with overall accuracy of 78.73 and 91.69 have the best performance. Furthermore, applying the manual threshold limit to weak indicators has increased accuracy in most cases. Another study used Sentinel-1 images with user-controlled thresholds to identify built-up areas, and the results for Amol, Rafsanjan, and Isfahan were 89.24, 80.03, and 76.10, respectively. The findings of this study revealed that the performance accuracy of indices can vary depending on parameters such as the type of climate, different sensors, and thresholds. Therefore, as a strategic model, the results of this analysis can provide researchers with a better understanding of indicators as a result of considering different parameters.

Satellite time series data play a key role in characterizing land surface change and monitoring of short and long-term land cover change processes over time. While coarse spatial resolution optical sensors (e.g. MODIS) can provide appropriate time series data, the temporal resolution of high to intermediate spatial resolutions sensors (1-100 m e.g. Landsat) does not allow for having temporally frequent measurements because of the orbital configuration of such sensors and cloud contamination. A promising approach for addressing this challenge and producing Landsat-like imageries is the blending of data from coarse spatial resolution sensors like MODIS. Among different approaches proposed in the literature, the ESTARFM model has been reported to outperform other models in generating Landsat-like imageries with reasonable accuracy over heterogeneous areas. Despite the large body of studies implementing ESTRAFM for downscaling MODIS data, quantitative evaluation of the model under different conditions has not yet been investigated. This study quantitatively evaluates model performance over different land cover types, resampling methods and time-difference analysis between input and synthetic images. The results demonstrated that employing bilinear resampling in the ESTARFM produces results slightly better than nearest neighbor and cubic resampling methods. Moreover, the ESTARFM model accurately predicts Landsat-like surface reflectance images with RMSE better than 0.02 and correlation more than 90% over different land cover types. However, the model performance significantly degrades as the time difference between the input and synthetic images increases.

Wind erosion is one the most important factors of land degradation in the arid and semi-arid areas and it is one the most serious environmental problems in the world. In Fars province, 17 cities are prone to wind erosion and are considered as critical zones of wind erosion. One of the most important factors in soil wind erosion is land use/cover change. Therefore, accurate mapping of land use/cover and wind erosion evidences in arid and semiarid regions is the utmost importance. Moreover, for discrimination of land covers resulting from wind erosion such as sand sheets and Nebka, we need accurate remote sensing methods. In this study, capability of the advanced machine learning techniques on Landsat 7 and 8 imageries in mapping land use/cover related to wind erosion is evaluated. The study area is located in the Fars province, in the southern part of Iran, (from 28°07′15″ to 28°13′07″N and 52°07′36″ to 52°23′55″E, covering an area of 17,230 ha), which is considered as the most critical wind erosion area of the province. Landsat 7 (2006) and Landsat 8)2013) images were corrected radiometrically using Dark Object Subtraction method. Although images from USGS website are corrected geometrically, we checked the images using stream and road maps. According to the variations in land use/cover spectral behavior across the study area, it was difficult to define training samples representing thematic classes in a supervised classification procedure. Then different image enhancement techniques were applied. Classification stopped using Support Vector Machine with four different types of kernels including linear, polynomial, Radial Basis Function, sigmoid and Kohonen’s Self-Organizing Map neural network. Results were compared with Maximum Likelihood method. Using separability analysis, the best input band combination for classification was selected. The Overall Accuracy and Cohen’s Kappa coefficient, derived from the error of matrix which were used for the accuracy assessment of the final maps. Results from accuracy assessment showed that the best map of the land use/cover in the relation to wind erosion was produced using a combination of original and processed bands and RBF vector machine (overall accuracy of 88 and 90.87 percent for L7 and L8, respectively). According to the separability metrics, the near infrared (NIR) and short infrared band (SWIR1), the WDVI, SAVI, LI indices, and processed bands by edge analysis in the aspect of E were finally selected as the best input band combination. The difference between accuracy of this method with linear, polynomial, SOM, sigmoid and ML methods were 1.5, 2.9, 8.3, 12.4, and 16.4 percent for L7 and 2.16, 4.16, 6.19, 13.89, and 14.67 percent for L8, respectively. In addition, results indicated that there was a significant change in wind erosion potential and land use/cover in relation to wind erosion in the study area in a short period of time. Rangelands were decreased by 73 percent and 10 percent of these areas are covered by sand sheets. More than half of rangelands were converted to agricultural lands. Insusceptible areas with surface crust or rocks were decreased by 59 and 2.39 percent, respectively. Discussion & Conclusions: The accuracy of classification increased using a combination of processed and original bands in comparison with using original bands alone. This indicates the fact that processing image classification without paying attention to the quality of input bands, will not results in accurate classification map. One of the advantages of active learning algorithm is its less training samples requirement. This is very important for areas which are difficult to have access to them. Although there were not distinct and large sand dunes in the study area like what can be seen in desert areas of Iran, but discrimination of these small sand dune and nebkas were done accurately using the combination of original and processed bands of Landsat imageries and support vector machine methods. Goodarzimehr et al., (2012) also indicated that support vector machine was a better algorithm for discriminating lithology units comparing to maximum likelihood and neural network methods. Sandification was also recognized using remote sensing methods in this study which is one the indices of land degradation and wind erosion. Sand sheets showed and expansion mostly to the southeastern parts. The results indicated the change of rangelands into agricultural lands which will increase wind erosion potential. Low-efficiency irrigation systems combined with an increase in soil loss from arable lands leads to reduction in productivity. This is in line with findings by Minwer Alkharabsheh et al. (2013) who reported the progressive decrease of the agricultural areas and mixed rain-fed areas as the main reason of declining in soil erosion in Jordan. Generally, this study showed the capability of Landsat imageries and support vector machine learning in study of wind erosion potential in arid areas.

Evapotranspiration is one of the key components of the hydrological cycle and its quantification is essential to understand the processes such as vegetation phenological changes, environmental hazards such as floods and droughts, and, in general, the ecosystem water balance. The use of remote sensing methods based on surface energy balance has been increased to estimate evapotranspiration. The purpose of this study was to estimate the evapotranspiration of corn based on integration of Landsat 8 and MODIS satellite images using the SEBAL algorithm in in Mahidasht, Kermanshah province. Linear with Zero Intercept (LinZi) method was used to integrate satellite images. Also, actual evapotranspiration of corn in 15 farms in the study area was estimated based on ground data. The results of the SEBAL algorithm were compared with ground-based evapotranspiration using MAE, BIAS and RMSE indices. The results indicated that the combination of satellite images has led to an improvement in the accuracy of estimated evapotranspiration compared to Landsat 8 images. The mean absolute error of estimated evapotranspiration during the growth period was determined as 0.44 and 0.42 mm.day -1 respectively based on Landsat 8 and combined images. In general, the results of this study showed that the estimation of evapotranspiration using the SEBAL algorithm and based on the integration of satellite images with different spatial and temporal resolutions could have acceptable results.

Reference evapotranspiration (ET0) is a major research area of both hydrology and water resources management, especially in irrigation agriculture. The most important and direct application of ET0 is in the field of irrigation. One of the conventional methods for estimating reference evapotranspiration using meteorological data is the Penman-Monteith-FAO equation. This equation due to satisfactory results has been used in a variety of climates around the world. However, the lack of necessary meteorological data makes it difficult to estimate spatially distributed ET0 using the FAO-PM method in the wider ungauged areas. Penman Monteith method requires air temperature, wind speed, relative humidity, solar radiation and etc.To overcome the existing limits of the FAO-PM model, various attempts aiming to estimate ET0 with limited observed data have been conducted. At present, remote sensing methods are the only way to obtain the various variables at the temporal and spatial scales needed to estimate evapotranspiration. In recent years, several algorithms have been proposed to estimate reference evapotranspiration using remote sensing data. Some of these models, which are based on the relationship of energy balance, are called surface energy balance methods. In addition to remote sensing, data analysis techniques based on machine learning (ML) are more frequently used in agricultural studies in recent years, especially in evapotranspiration. Therefore, analyses performed with ML algorithms, when coupled with remote sensing data, have the potential to predict the biophysical variables, mainly due to the adaptive capacity of the models to find patterns in nonlinear behavior variable, such as ET0. Machine learning methods are well known and have been widely used in other engineering sciences. The purpose of this study is to estimate the reference evapotranspiration using machine learning algorithms and remote sensing data and finally to analyze the algorithms used. In general, the final results of evapotranspiration estimation depend on factors such as the type of data and the method for estimating evapotranspiration.In this study, the standard method of estimating ET0 with meteorological data, Penman-Monteith FAO equation has been used. The NDVI vegetation index indicates the amount of vegetation on the ground and is sensitive to the early stages of phenology. But the enhanced vegetation index (EVI) minimizes atmospheric effects and differences in blue and red reflections. The SAVI index is used to calculate the vegetation of the land surface that has moderated the effect of soil on it. Three machine learning algorithms were introduced to train the ET0 models, including random forest (RF), gradient boosting regressor (GBR) and support vector regression (SVR). Random forest are one of the machine learning methods that performs classification and regression using Bootstrap and Bagging methods. In this research, three machine learning algorithms with different input data (vegetation indices and all bands of Landsat 7 and 8) are used and after comparing the results, the best model was selected. Performance Evaluation Indicators to compare and evaluate the performance of the studied models, the parameters of mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R2) and correlation coefficient (CC) are used. Finally, according to the results of the two approaches used in this study, using the values of all Landsat bands, the reference evapotranspiration can be estimated with more accuracy.Accurate estimating of reference evapotranspiration is necessary to estimate irrigation needs and in general, to accurately manage water resources. Conventional methods of measuring evapotranspiration are reference using meteorological data. These measurements are point-based, so they are only suitable for very small scale areas. At present, remote sensing methods are the only non-terrestrial way to obtain the various variables at the temporal and spatial scales needed to estimate reference evapotranspiration. In order to reduce the dependence on climatic data and better resolution, machine learning methods are used to calculate the reference evapotranspiration. In this research, RF, GBR and SVR models have been used. In the present study, there are two approaches Used. In the first approach, the values of all bands of Landsat images are as model input, while in the second approach, vegetation indices are calculated with only a few bands of Landsat images and then used as model inputs. By examining, it can be seen that the information obtained from the Landsat image bands is related to the phenological behavior of the products, and it is also possible to contract very relevant information related to agricultural products that are examined temporarily and spatially. One of the factors influencing the accuracy of estimating reference evapotranspiration is the use of other Landsat bands in addition to the bands related to vegetation indices.

The use of SPOT and Landsat satellite images as combination with field test presents a very useful information on the identification of alluvial fans and their geometry. Existence of very typical alluvial fans belongs to the Plio-Quaternary on the Binalud mountain brow is a very interesting environmental laboratory in which these relationships can be studied and analyzed. This study is done by experimental and laboratory method based on fielddata analysis and interpretation of satellite images. So that identification of fans were done through SPOT and Landsat satellite images along with control of the 1/4000 aerial images of Binalud blocks. For clarification of alluvial fans boundary, ground control operations was carried out in order to their Geomorphometry results have less error. The main purpose of this research is to identify the geomorphometryan quantitative relationships of south Binalud's alluvial fans through reconciliation of round prospectand field observations. Comparison of SPOT and Landsat satellite images in identification of 20 large and small alluvial fans of southern Binaloud mountains forehead revealed that SPOT resolution strength and accuracy of images in geometric reviewing of alluvial fans is higher than Landsat but Landsat satellite images is more applicable in identification of large-scale forms of alluvial fans surfaces.

Agricultural products frost in spring imposes heavy financial losses to agriculture particularly in northwest of Iran’s orchards. Not only temperature is one of the most important climate parameters but also it is a very crucial element in the agricultural sector. Untimely temperature fluctuations and rise and fall which are usually unexpected will cause shock and heavy damages. Therefore taking into consideration the agricultural products frost and offering an approach would be of great importance for reducing relevant damages. In studies carried out by Omidvar and Dehghan Banadoki (2012) and Hesari et al. (2015) characteristics and different types of frosts have been considered in relation to the agricultural products. Different models were introduced to predict flowering date in different investigated regions. In more studies, in addition to determining the best model for predicting the date of occurance of flowering stage, probable date of last frost has been estimated as well. Investigating long term temperature changes is a method which applied by Martínez-Lüscher (2017) and Vitasse et al. (2018) to find out about established changes in flowering date and also changes in the last frost date. Nasr Esfahani and Yazdanpanah (2019) realized that 48-hour early warning for frost occurrence can be performed with adequate precision. Despite all studies in the field of products frost particularly during flowering date, it seems a rapid frost warning system must be established and provided to make early warning for each orchard. In this essay, since our goal is to make such early warning three days before frosting, so we have to investigate accuracy and validity of 72-hour minimum temperature simulation using WRF model. On the other hand, we must know phonological stage of each product in each orchard to inform the farmer about frost hazards based on critical temperature, therefore the second goal of this research is to detect phonological stages through Landsat 7 and Landsat 8 images.

In order to achieve the aim of current study, 72-hour minimum temperature simulation through the Weather Research and Forecasting (WRF) model was investigated and values of vegetation index were derived for a 30 meters pixel at an experimental orchard in Kahriz, West Azerbaijan Province, in 2016-2107. Computational grid for 2 meters temperature simulation using WRF model contains of three nested grid with horizontal resolution of 27, 9 and 3 kilometers. Horizontal resolution of terrain height and land use data is equal to 30 second (about 1 km). The initial and 3-h boundary conditions with 0.5º horizontal resolution from the Global Forecast System (GFS) were obtained from National Centers for Environmental Information (NCEI). Based on the previous research KFMYJ physical scheme configuration for WRF model were used in this research. Model's hindcasts at 03:00 UTC hour for each of 51 synoptic weather stations of northwest of Iran in internal computational grid were interpolated by MATLAB software with interp 3 function using linear method, then the obtained values were compared to minimum temperature observed in the stations by using MAE, MSE, RMSE and MSSS indicators. Phenological statistics, the time of beginning and end of growth stages were obtained from Iran Meteorological Organization. Besides, 77 Landsat 7 satellite images of ETM+ sensor, and 41 Landsat 8 images of OLI sensor were downloaded from United States Geological Survey website from March to September 2007-2016 with a spatial resolution of 30 meters. In this research, atmospheric and radiometric correction were performed with the FLAASH method on the metadata file in the ENVI software environment and then vegetation index was calculated using NDVI index.

Examining the evaluation indicators of the WRF model, results revealed a significant correlation and regression model between 2 meters temperature variable from WRF model output and minimum temperature variable observed in the entire stations for 72-hour simulation. As a result WRF model can be applied in 72-hour temperature simulation in the area of study. Another finding of this research indicated that in comparison to the field-recorded data, NDVI values gained from Landsat images properly indicates changes of phenology stages in the relevant apple orchard. In this study, the indicators used to evaluate the model error showed model hindcasts are more accurate for 24-hour and then 48-hour simulations than for 72-hour simulation, but the 72-hour simulation accuracy is not much different from 24-hour and 48-hour simulations. In northwestern Iran, which is a mountainous region, it is very difficult to simulate airflow in areas with complex topography, therefore the total correlation coefficient of all stations in all three simulations is in the range of 0.5, and the error rates of MAE and RMSE, respectively reaches about 2.8 and 3.8 Celsius. According to the second finding of this research, the NDVI indicator obtained from Landsat 7 and Landsat 8 satellite images can show the progress and changes in the phenological stages of apple trees.

 This study showed the efficiency of the WRF model for 72-hour simulation of the minimum temperature as well as the potential of Landsat 7 and Landsat 8 images in detecting apple phenological stages in the study area. Therefore, by using the WRF model for 72-hour minimum temperature simulation and recognizing the phenological stages from Landsat images, if the temperature in any orchard reaches a critical level in the next 72 hours due to the phenological stage, frost warning can be announced and then frost mitigation should be done by the farmer.

The SEBAL algorithm is used to estimate spatial distribution of actual evapotranspiration using remote sensing imageries of MODIS or Landsat. Despite having a better spatial resolution than MODIS imageries (30 m instead of 1000 m), Landsat imageries do not have an appropriate temporal resolution (every 16 days instead of daily). On the other hand, the daily imageries of MODIS can be difficult to use under cloudy condition. Additionally, it is also a time-consuming process to interpret all the imageries. In this research, we chose the appropriate imageries from MODIS to be able to monitor the sudden weather changes as well as rainfall events and to reduce the interpretation time, while keeping the important information of the daily MODIS imageries in order to obtain the better actual evapotranspiration estimates. Due to the importance of hot and cold pixel selection, whose selection needs time and proficiency, we applied the automated method of hot and cold pixel selection (without user-intervention) using Landsat imageries. To integrate evapotranspiration over time, we used linear-logarithmic interpolation method in addition to linear interpolation method. The estimated actual evapotranspiration by SEBAL was compared to the estimated actual evapotranspiration from water balance equation and SWAT model for 3 years including a wet year (2004-2005), a normal year (2005-2006) and a dry year (2007-2008) in the Neishaboor-Rokh watershed. Furthermore, we used the Budyko framework to validate the evapotranspiration estimated by SEBAL and SWAT. The results showed that in comparison to SWAT, the linear-logarithmic interpolation method performed better than the linear method to estimate evapotranspiration. For linear-logarithmic method, RMSE, MBE, and MAE were 20.4, 0.09, and 18.4 mm year-1, respectively; and for the linear method, they were 21.8, -2.4, and 20.8 mm year-1, respectively. The results also demonstrated that the SEBAL algorithm with automated cold and hot pixel selection is able to have a good estimate of actual evapotranspiration at annual time scale and watershed scale. But, the algorithm does not perform well at HRUs and monthly scale in comparison to SWAT model. Results showed that by taking irrigation into account, evaporation estimated by SEBAL and SWAT follows the Budyko framework.

One of the most important parameters of the water balance equation is evapotranspiration which is effective factor in the management of water resources. Also in different sciences it has been shown the transformation of hardware methods to software methods. One of these few cases is determination actual evapotranspiration using remote sensing and satellite images. According to the importance of actual evapotranspiration in the allocation of water resources in current research by using satellite images from Landsat 8 (suitable spatial resolution) and MODIS (acceptable temporal resolution) were determined the amount of mention parameter of sugarcane in Amir Kabir Sugarcane Argo-Industry and was compared with lysimeteric data. For this purpose, Landsat 8 and MODIS images were merged in the period of 16 days by Gram-Schmidt method and the actual evapotranspiration of sugarcane was estimated by SEBAL algorithm. In addition, the amount of actual evapotranspiration was calculated using Landsat8 images and SEBAL algorithms. Finally, the results of two mention methods were compared with lysimeteric data and were analyzed by statistical methods. The results indicated that the average of absolute difference between actual evapotranspiration of fusion images and lysimeteric method was 0.55 (mm/day). This index was 0.063 (mm/day) between Landsat 8 images and lysimeteric data and the average of absolute difference between two methods of remote sensing was obtained 0.58 (mm/day). Also at the level of five percent, there is not a significant difference between the two methods of remote sensing.

Evapotranspiration (ET) is one of the most important parameters in agricultural water management which has spatial and temporal variations. Remote sensing-based algorithms of ET estimation have been applied in several studies. Using MODIS satellite images ET can be estimated on a daily basis at the pixel size of 1000 meters while using Landsat 8 images can be estimated every 16 days in the pixel size of 100 meters. Various methods are available for combining satellite images with low (such as MODIS) and medium (such as Landsat 8) spatial resolution to estimate evapotranspiration on a daily basis in the lower pixel size. Downscaling is one of these methods which was evaluated in this study is one of the plains in Kermanshah province. For this purpose, the actual ET over the study area was calculated during the summer of 2014 using the SEBAL algorithm based on six satellite images of Landsat 8 and MODIS. Although there are several methods for downscaling the estimated evapotranspiration based on MODIS images, in this study two simple downscaling methods (ratio and subtraction). were used to convert the Landsat 8 image scale. Results of downscaled images of MODIS were compared with the results of Landsat 8 images graphically and statistically. Given the fact of small size and mixed land use types in the study area results of downscaling methods were not acceptable.