جستجوی مقالات مرتبط با کلیدواژه « Remote Sensing » در نشریات گروه « آب و خاک »

The relationship between intensity-duration-frequency of rainfall is a significant tool for estimating flood discharge. According to the sparsely available rain gauge stations and the development of technology, it is possible to use satellite rainfall data with different temporal and spatial resolutions. PERSIANN rainfall data with a time resolution of 1 and 6 hours were used in this research. Also, the spatial resolution of these data is 0.04 x 0.04 degrees. Rainfall data from synoptic stations around the Kan basin were also used. Three common continuous probability distributions of Gamble, Pearson type 3, and Log Pearson type 3 with return periods of 2, 5, 10, 25, 50, and 100 years were investigated to calculate and check the IDF curve. In general, the precipitation intensity obtained from Gumble's method was more than Pearson Type 3's method. Log Pearson type 3 distribution did not provide acceptable results in this research. The two interpolation methods of inverse distance weighting and empirical Bayesian kriging were used to generalize the frequency intensity curves to the entire Kan basin. The results showed little difference between these two methods, except for Pearson type 3 probability distribution.

One of the common methods to estimate the yield of crops before their harvest is the use of satellite images and remote sensing technology. One of the efficient methods extracted from remote sensing data to monitor crop yield is the use of spectral indices. This study was carried out to estimate maize yield before its harvest using Landsat 8 satellite images in a part of the lands of Shahid Beheshti agro-industry, Dezful. Eight spectral indices including NDVI, TNDVI, GNDVI, SAVI, OSAVI, NDWI, MNDWI, and NDMI were used in this study. A correlation relationship was formed between the indices and yield with 70% of the data. Then the relationships were evaluated with 30% of the data. MNDWI index had the highest correlation with the field data in December and January, respectively, with a coefficient of determination of 30% and 13%. R2 and RMSE between the observed and predicted yield values by this index for the mentioned months were 72%, 1/71 tons per hectare, and 48%, 1/54 tons per hectare, respectively. Multivariable equations produced for both dates in January and December were obtained with R2 and RMSE, 31%, 0/06 tons per hectare, and 55%, 1/19 tons per hectare, respectively. According to the results, by using the average MNDWI ، SAVI, and NDVI indices in the produced relationships, the errors caused by the spatial changes of yield at the farm level are minimized, and it is possible to estimate the yield before harvest.

The effect of drought as a complex phenomenon on the economy and environment can be destructive. Identifying the drought-prone areas is essential for planning and adopting mitigation measures. This study is focused on introducing a multi-scale method based on satellite datasets to assess drought vulnerability in areas without data. In this regard, two steps were considered and drought monitoring was carried out for the northwest part of Iran as the study area. In the first step, vulnerable areas were identified using multi-criteria kernel-based techniques that integrated 17 geo-environmental parameters extracted from ground-based and satellite datasets to develop a drought vulnerability map. The considered models were evaluated with different criteria and the most important variables were determined using sensitivity analysis. Results showed that the southern and central parts of the selected region are more prone to severe droughts. Among the considered variables, soil moisture, precipitation, air humidity, and vegetation condition were the most effective parameters. In the second step, due to the limitation of ground-based data, drought-prone areas were identified only by using the variables of precipitation, vegetation condition, and ground surface temperature extracted from satellites. For this aim, a new multiscale method was developed based on wavelet transform (WT), variational mode Decomposition (VMD), and kernel-based methods. The obtained results show the appropriate efficiency of the proposed multi-scale method in identifying areas prone to drought with different intensities.

Examining the changes in the water quality parameters of the Karun River using satellite data and determining the modified quality indicators can be used to assess the vulnerability of irrigation water. In this research, the data of seven qualitative parameters: Na+, SAR, pH, Cl-, HCO3-, EC and TDS were used in six water measuring stations of Abbaspur, Ahvaz, Farsiat, Gotvand, Molasani and Soosan of the Karun River (1392-1398) and NSFWQI general water quality index was calculated. Correlation relationship and estimation errors were determined for two principal component reduction (PCA) and multivariate linear correlation methods. The results showed that multivariate correlation method is more suitable. The coefficient of determination for the seven water quality parameters was calculated as 0.44, 0.43, 0.03, 0.43, 0.09, 0.45 and 0.46 respectively, and for the NSFWQI index it was calculated as 0.46. The statistical correlation for pH and HCO3- is at a very low level; but for the other five parameters and the NSFWQI index, it is in average state. The significance level of estimation for Na+, SAR, Cl-, HCO3-, EC and TDS parameters is acceptable (P<0.001), and for pH is unacceptable (P<0.122). In general, there is an acceptable correlation between the bands extracted through the Landsat 8 satellite and most of the quality parameters of the Karun River, but necessary actions are proposed to improve the correlation relationships. Also, the NSFWQI index shows that the quality of water in the Karun River along the Khuzestan plain is not good enough.

There are two approaches in dealing with environmental changes. The first approach is based on ignoring these changes and continuing the current situation, which will result in further environmental destruction. The second approach is based on identifying these changes from the past to the present and formulating an environmental management plan to control these changes and plan for improving the environmental situation. Wetlands are one of the most important natural habitats in the world and have many values and benefits, especially in energy circulation in the environment. In the last 20 years, the area of many wetlands has decreased due to the increase in industrial and agricultural development and the lack of water in arid and semi-arid regions (Cui et al., 2009). One of the effective tools in the field of wetland area changes is the use of remote sensing technology and satellite data. The use of satellite images, due to their wide spatial coverage, high resolution, low cost, temporal archive, free access to satellite images, and the availability of practical software and spectral indices, has become very important in estimating the area of aquatic zones. Monitoring and assessing the water level of wetlands using remote sensing to protect this natural heritage has become a focus for many countries in recent years, and this is of particular importance as the first step in identifying problems and attempting to solve them. Heshilan wetland plays a significant role in nourishing and increasing the stability of underground waters, preventing floods, and promoting agriculture in the region, as well as providing a unique habitat for native and migratory birds to easily pass winter. The aim of this research is to monitor changes in the water level of Heshilan wetland over a 22-year period using remote sensing and geographic information systems.

Landsat satellite images were downloaded from the United States Geological Survey website. After downloading the Landsat satellite images, the Heshilan wetland area was delineated, and the images were radiometrically and atmospherically corrected. To enhance the spatial resolution of the study area, the 30-meter pixel size image was converted to a 15-meter pixel size image for better spatial resolution (the 15-meter resolution provides more accurate information than approximate surface area estimates of wetlands), then we normalized the surface reflectance values. The Target Detection Wizard tool in ENVI 5.6 software was used to determine the aquatic zone area of the wetland in Murch of each year during (2000-2022), and the output file was imported into ArcMap 10.8.2 to calculate the aquatic zone area of Heshilan wetland in square kilometers on the date of image acquisition.

The results of interpreting satellite images over the years under study indicate that in 2018, the wetland had its lowest surface area in two decades, with an area of 0.34 square kilometers in that year. Additionally, the highest area of the aquatic zone of the wetland occurred in 2005, with an area of 3.83 square kilometers. The results show that over the past 22 years, the wetland has faced a decrease in water level by 0.79 square kilometers for the specific month.

The research results indicate that analyzing satellite images using remote sensing techniques can effectively show changes in wetland areas over time intervals. The results of interpreting satellite images over the years under study show a reduction in the extent of Heshilan wetland, especially in the western and southwestern regions, which can be attributed to natural phenomena such as drying up some springs due to droughts and periods of low water levels, as well as undesirable effects of human activities such as increased human access to wetlands through access roads in this area, land grabbing by villagers converting them into agricultural lands, deep wells around the wetlands, and utilizing wetland water through agricultural canals without considering proper water inflow. In these conditions, the wetland ecosystem has completely changed, and other aquatic birds no longer live in this area, with many migratory birds moving to tropical regions, depending on their habitats along the migration route. Given the unfavorable trends in Heshilan wetland developments, continuing the current conditions could jeopardize the existence and integrity of Heshilan wetland irreversibly. Ecosystem management of wetlands by developing a management plan to preserve and revitalize the structure and functions of this ecosystem with long-term stability can be a solution.

Given that conventional ground-based methods require significant costs, time, and manpower, there is an increasing inclination towards using indirect methods such as remote sensing. Therefore, the aim of this research was to calculate dry biomass, harvest index, and grain yield of irrigated wheat using remote sensing in the Urmia Lake Basin. For this purpose, the Urmia Lake Basin was divided into six sub-basins, and the Radiation Use Efficiency (RUE) model was utilized. In this study, 1115 irrigated wheat fields were used. Monitoring results of the fields and the NDVI index indicated that irrigated wheat germination in the basin began on average from November 11th, and harvesting of this crop continued until July 21th. The values of correlation coefficient (R), Nash-Sutcliffe coefficient (NSE), normalized root mean square error (nRMSE), and coefficient of residual mass (CRM) in the calibration step were 0.90, 0.76, 15%, and 6.38%, respectively, and in the validation step, they were 0.92, 0.72, 14%, and 7.21%, respectively. Examination of the harvest index (HI) indicated that the average of this index in different sub-basins ranged from 0.40% to 0.45%, with an overall average of 0.42% for the Urmia Lake Basin. The results of biomass and grain yield assessment revealed significant differences in their values among different sub-basins. The highest biomass and grain yield were observed in the Zarrineh-Simineh sub-basin with averages of 12098 and 5261 kilograms per hectare, respectively, while the lowest values were observed in the West-Lake sub-basin with averages of 8651 and 3723 kilograms per hectare, respectively.

Fresh water availability and its shortage is one of the most important issues in the world today that some countries are facing. In the last two decades, Kabul province, Afghanistan, has seen a decrease in water resources under the influence of natural and human factors. The purpose of this research is to use satellite data and remote sensing techniques to investigate changes in surface and underground water resources in Kabul province. For this purpose, the satellite data and products available in the Google Earth Engine in the period 2000 to 2022 and the climate data of ground stations in the period 2006 to 2021 have been used, which include: evaporation data- Transpiration, Enhanced Vegetation Index (EVI), Global Product of Surface Water Areas (JRC), GRACE data, OLS Satellite Night Images, Sentinel 2 Satellite Image, Landsat 7 Satellite Image, Temperature, Humidity and Rainfall Data. The change process of the used data was analyzed through the Mann-Kendall test and the significance level of these data was checked. The supervised classification method was used on the two mentioned images to calculate the area of vegetation, water area, residential areas, and barren lands. The obtained results show the reduction of underground water resources (significant reduction trend of GRACE satellite data) and the reduction of the surface water area changes in Kabul province, under the influence of natural and human factors, which among these factors can reduce He pointed out the amount of rainfall, increase in temperature, increase in evaporation-transpiration, increase in the level of vegetation and physical development of Kabul city and increase in the population using water resources.

Agricultural water management studies require accurate information on actual evapotranspiration. This information must have sufficient spatial detail to allow analysis on the farm or basin level (Sanchez et al., 2008). The methods used to estimate evapotranspiration are grouped into two main groups, which include direct methods and indirect or computational methods (Alizade and Kamali, 2007). Basics of the indirect methods are based on the relationship between meteorological parameters, which impedes the use of these data with a lack or impairment. On the other hand, this information is a point specific to meteorological stations, and their regional estimates are another problem of uncertainty of their own. To this end, the use of remote sensing technology can be a suitable approach to address these constraints. Real evapotranspiration can be estimated by satellite imagery that has short and long wavelengths and is estimated using surface energy equations (Chihda et al., 2010). Examples of such algorithms include SEBAL (Bastiaanssen et al., 1998 Bastiaanssen, 2000;), METRIC (Allen et al., 2007), SEBS (Su, 2002). Among the above mentioned algorithms, energy billing algorithms have been used (Bagheriharooni et al., 2013; Teixeira et al., 2009). Among the factors of superiority of the SEBAL algorithm, in comparison with other remote sensing algorithms, is a satellite imagery analysis algorithm based on physical principles and uses satellite simulation and requires minimum meteorological information from ground measurements or air models (Bastiaanssen et al., 2002).

This study identified and described drought using multiple MODIS-based indicators, so the temporal-spatial characteristics of the intensity and frequency of drought in the entire country in the period from 2001 to 2021 using the standardized precipitation index in the form of one month SPI-1. Three-month SPI-3 and one-year SPI-12, based on CHIRPS precipitation data set with spatial resolution of 5 km, vegetation condition index (VCI), temperature condition index (TCI) and vegetation health index (VHI) were investigated. the distribution of rainfall in the southeastern and central regions of the country is less than 200 mm per year. Examining the ratio of drought classes based on the TCI index shows that the area ratio of the areas that are in the severe drought class in 2020 and 2021 is 36.7% and 43.2%, respectively, which has increased by about 7%. The comparison of the area of the drought class of the TCI and VCI indices also shows that the VCI index has overestimated the areas in the severe drought class by 3.7% and 5.1% in 2020 and 2021. Also, the VHI index shows that 6 provinces in the southern region of the country have experienced long-term drought between 2009 and 2021.

Determining the amount of soil erosion and its spatial distribution can effectively provide appropriate management practices to reduce erosion problems. Direct measurement of soil erosion takes a lot of time and money, and results are often regional and limited. This issue has led to the development of various models for estimating soil erosion and sediment production. Since most of the watersheds in Iran lack sufficient and accurate information, models that require relatively few inputs make more sense than models with high inputs. Along with empirical and process-based models, a number of erosion estimation models are known as hybrid models. One of the hybrid models is the Thornes model, which requires relatively little input data, and there has been no research related to this model in Iran. Therefore, this study was conducted to determine spatial variation the soil erosion rate and sediment yield in a part of the Sanandaj Gheshlagh Dam watershed using the Thornes model utilizing GIS and remote sensing (RS).

Two hundred soil samples were collected using a stratified random sampling method and the parameters of soil texture, particle size distribution, organic carbon, and soil CaCO3 equivalent in the laboratory were measured by conventional methods. In order to determine the input parameters of the studied model, laboratory results, Landsat 8 satellite images during a 6-year period, and some monthly meteorological data including precipitation, precipitation days number and potential evapotranspiration were analyzed. Finally, using ArcMap, Saga GIS, and ENVI software, the required parameters, and maps of the models were prepared, and the studied models were run. Sediment delivery ratios (SDRs) are assumed to be a function of the travel time of surface runoff from catchment cells to the nearest downstream channel.

The results showed that the estimated average erosion of the Thornes model was 0.76 mm per year or 10.24 tons per hectare per year (assuming a bulk density of 1.4 gr/cm3), and according to the calculated SDR, the estimated sediment was calculated by the model as 4.34 tons per hectare per year. The results of the Thornes model showed that the sensitivity of this model to some parameters, including potential evapotranspiration and potential water storage capacity, was very high. Small changes in these parameters caused a significant difference in the results, which would reduce the efficiency of the model.

According to the field observations and the investigation of erosion and sedimentation situations in the studied watershed, as well as long-term information about sediment discharged from the hydrometric station (3.10 tons per hectare per year), it seems that the Thornes model has been a relatively reasonable estimate of erosion in many parts of the studied watershed. Although, the type of model used to estimate the sediment delivery ratio and then the sediment yield can have a significant effect on the model's efficiency. Considering that this model requires relatively few data, it may be possible to use it to predict erosion in watersheds with no information or with poor information.

The different land uses in the irrigation water area of the eleven streams of Khansar city during 1969, 1995, 2014, and 2019 have been identified and their area has been determined by analysis of the aerial photos as well as the satellite images of QuickBird, and Landsat in the Google Earth Engine (GEE) environment. Then, the net and gross areas of land under irrigation water, area of non-agricultural land uses, location and area of agricultural land uses under irrigation of the streams are separated according to the type of agricultural activity (orchard or farmland) for each stream. Aerial photos of the study area dated 1969 are the basis for the assessment of agricultural conditions before the law of Fair Water Allocation. The results showed that non-agricultural and particularly urban and residential land uses have increased since 1969. In other words, land use of part of the agricultural lands has been changed to residential and urban land uses. Despite the decreasing trend of agricultural land uses in the last 50 years, these changes have not been the same between the farm and orchard land uses and the area under orchard plantation showed an increasing trend. These changes have dramatically influenced on water demand of the streams. Land use has not significantly changed from 2014 to 2019 and no noticeable change was observed in the area of the agricultural and green agricultural lands as well as the percentage of the orchard and farming lands during these years. The results of this study confirmed the significant changes in agricultural land use and consequently water consumption in the district of the eleven streams of Khansar in recent decades. This study also highlighted the high efficiency of the combined use of aerial photos, spectral satellite images with medium spatial resolution, and visible spectral satellite data with high spectral resolution, as well as using cloud system capabilities of the Google Earth Engine to study changes in agricultural land uses during last decades.

Water supply remains a significant challenge in arid and semi-arid regions, and in addressing this concern, unconventional water sources have gained prominence. Notably, the extraction of water from air humidity, classified as an unconventional water source has seen increased adoption. Diverse techniques have been developed to achieve this goal, with the utilization of mesh networks being particularly prevalent. Consequently, this study assesses the evaluation of the performance of the ERA5 dataset in the simulation of atmospheric variables that influence the ability to assess water harvesting from air humidity (including temperature, wind speed, and water vapor pressure). Also, the possibility of water harvesting from air humidity was investigated in Qazvin Province. The outcomes demonstrated the benefit of incorporating adjustment coefficients in estimating temperature and wind speed using the ERA5 dataset. Based on these findings, the northwestern and southern regions of the province (Kuhin and Takestan) exhibit notable potential during spring and summer for water harvesting from the atmosphere. The peak water harvesting for these stations in the summer is estimated at 10.2 and 9.7 l/day.m2, respectively. Using the ERA5 reanalysis dataset, the annual average potential for water harvesting in the stations was evaluated at 7.9 and 4.6 l/day.m2, respectively. Notably, the minimum water harvesting capacity during the summer season recorded in Qazvin is equal to 3.39 l/day.m2, which can be planned for use in irrigation requirements of green spaces, fields, or gardens.

Evapotranspiration is one of the key components of water balance and irrigation planning. Thus, the accurate estimation of this component and the water consumption of plants can improve the management of water use and increase the efficiency of water consumption. Due to the limitation of tools for measuring evaporation-transpiration, remote sensing methods can be used for this purpose. There are several remote sensing algorithms for actual evaporation estimation including SEBAL, SEBS, Metric, etc. In this study we used the triangle method which only was used by Salimifard et al. (2022) in Mashhad Plain. They evaluated the results for the agricultural products, i.e., wheat and maize. The aim of this study is to evaluate the triangle method for a horticultural crop, i.e., pistachio in Kerman Plain. 

The study area is Kerman Plain in which pistachio is one of the most important agricultural products. Due to water scarcity in this plain, determining the water requirement of the crops is crucial for agricultural activities. Accordingly, it is important to have an appropriate estimation of actual evapotranspiration in the plain. In this paper, the triangular algorithm was used to estimate actual evapotranspiration in the Kerman Plain in the growing seasons of 2020 (1399) and 2021 (1400). For this purpose, the Landsat 8 satellite images with less than 10% cloudiness were used. The variables such as NDVI, LST, etc., were calculated by using the JAVA programming language in the Google Earth Engine code (GEE) system environment. The required meteorological data of Kerman station were acquired from IRIMO. The triangular algorithm is based on the two-dimensional spatial plot of normalized LST and normalized NDVI, which were calculated using bands 10, 5, and 4 of the Landsat 8 in the GEE. Estimation of the wet and dry edges was conducted by MATLAB code. the actual evapotranspiration obtained using the triangular method for a pistachio orchard, which was under irrigation management, was compared to the values obtained by the FAO-56 method. The results were evaluated by correlation coefficient (r), Root Mean Square Error (RMSE), and Mean Error (ME).

The results showed that the amount of evapotranspiration for pistachio was estimated with acceptable accuracy (r= 0.73 and RMSE=1.8, nRMSE=0.4, ME=-1.6). However, the NSE less than zero (-1.3) shows that the observed (FAO-56) mean is a better predictor than the Triangle algorithm. The values obtained from the triangular algorithm were lower than the values of FAO 56, which was in line with the results of the previous studies for both Agricultural and horticultural crops. This underestimation could be due to the uncertainty of the algorithm, uncertainty in the measured data, or due to the time difference between the date of the selected images and the date of irrigation. Moreover, inappropriate quality of water and soil in Kerman Plain and the uncertainty of plant coefficients used are among the factors that can underestimate evapotranspiration values by the algorithm. 

In this study, the triangular algorithm was used to estimate actual evapotranspiration in Kerman plain using remote sensing data. Actual evapotranspiration values obtained from the triangular algorithm were lower than FAO 56 values, which might be due to the uncertainty of the algorithm, uncertainty in the measured data, uncertainty of plant coefficients, or due to the time difference between the date of the selected images and the date of irrigation. To have a better evaluation of the remote sensing algorithms, it can be suggested to develop and apply a micro lysimeter in the farms and orchards, or to use the soil water balance of the farms and orchards. These may help to choose the more appropriate algorithm for the given study area, leading to providing the more proper and applicable advices for the farmers for managing the shortage of the water resources. Furthermore, it may help to update the crop coefficients which may lead to better estimation of evapotranspiration.

Earth's climate is the result of complex interactions between its effective components and a function of solar radiation, which has a significant role on the afore said components. Among the most important climatic factors that are effective in the vegetation of humid, dry and semi-arid regions, we can mention the variables of vapor pressure and soil moisture, which play an important role in the process of plant photosynthesis. Chlorophyll plays a significant role in photosynthesis of plants, including coniferous. According to the research conducted in Chitgar and Nowshahr, the effect of two different components has been evaluated. The effects of the season on the fluorescence value of two components can’t be denied. The highest value of correlation in soil moisture and its effect on the amount of fluorescence in Chitgar forest park in autumn and winter seasons is estimated with R²=0.44 and 0.56, respectively. The RMSE were calculated 7.4 and 6.7(mg/m2), respectively. In Nowshahr, the highest correlation value with total depth moisture was obtained in summer season. The numerical value of R² is calculated as 0.21. Also, P-Value is estimated at 0.498. The effects of environmental stresses on the amount of soil moisture in different depths are undeniable, especially in the seasons when the plant activity is high and the amount of photosynthesis will be more exposed to drought and salinity stresses. Regarding the effect of vapor pressure in Nowshahr, the highest degree of correlation has been calculated with the fluorescence value in the autumn season. The peak of the rainy season in the north of the country can be estimated in the autumn season, and with the increase in relative humidity, the water vapor pressure will increase.

Statistics show that the occurrence of severe and long-term droughts, especially in sensitive and fragile areas of the country has caused severe economic and social losses, and the occurrence of drought, increased dust, storms, and desertification has caused a decrease in agricultural production. Extensive and dynamic monitoring of dryness by traditional methods is very difficult and costly due to the lack of soil moisture display points. Remote sensing technology is a practical and applied method for large-scale land monitoring. In this study, we tried to identify the drought in the Siah Kooh watershed area with TVDI dryness-temperature indices and the NDVI index resulting from MODIS sensor images and to investigate the relationship between drought and atmospheric elements in the region. The results of correlation as a total showed that the correlation values of TVDI index SPI6 and SPI12 are 0.68 and 0.71, respectively, and the correlation rates of NDVI values with SPI6 and SPI12 are 0.49 and 0.51, respectively. As a result, it can be said that the TVDI index, due to the use of thermal and reflective bands and soil moisture, is more accurate than the NDVI index, which considers only the amount of vegetation in the region. The TVDI index had an inverse correlation with the average of two months of rainfall of 0.54 and a direct correlation of 0.64 with the surface temperature of the earth. In contrast, the NDVI vegetation index with a two-month average rainfall has a direct correlation of 0.54 and an inverse correlation of 0.6 with the temperature. These linkages show that the correlation between vegetation and temperature is inverse (negative) and the correlation between vegetation and rainfall is direct (positive).

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

Methods and Materials:

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

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

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

In recent years, the use of machine learning algorithms has been a promising way to improve crop yield predictions, especially when using non-linear relationships. This research was conducted with the aim of evaluating the yield estimation of irrigated and rainfed barley as well as the total yield of barley produced in the provincial centers of Iran using remote sensing data and machine learning methods including XGBoost and SVM. The results showed that by using climatic data, drought indices and plant indices of remote sensing and also XGBoost and SVM algorithms, it is possible to reliably estimate barley yield in different regions of the country with different climates. In general, the RMSE error obtained for both models was acceptable (0.41 and 0.77 t/ha). The R2 determination coefficient values for XGBoost and SVR algorithms in modeling rainfed barley cultivation performance were equal to 0.2 and 0.22 respectively, in irrigated barley performance were equal to 0.52 and 0.55 and for total barley were equal to 0.66 and 0.65, indicating that the rainfed yield modeling were not as suitable as irrigated and total barely yield modeling. The RBF kernel was chosen as the best kernel to use for the SVM algorithm. Also, in this research, while examining the effects of change in train and test data dividing, the parameters of precipitation, temperature, and evapotranspiration were determined as the most important parameters affecting the performance of the barley yield for both algorithms in different evaluated conditions.

Soil organic carbon (SOC) is one of the most important components of soil physical and chemical properties that have an important role in sustainable production in agriculture and preventing soil degradation and erosion. Data mining approaches and spatial modeling besides machine learning techniques to investigate the amount of soil organic carbon using remote sensing data have been widely considered. The objective of the present study was the evaluation of SOC using the remote sensing technique compared with field methods in some areas of the Gonbad Kavous and Neli forests of Azadshar. The soil samples were collected from the soil surface (0-10 cm depth) to estimate the SOC. Data were categorized into two categories: 70% for training and 30% for validation. Three machine learning algorithms including Random forest (RF), support vector machine, extra tree decision, and XGBoost were used to prepare the organic soil carbon map. In the present study, auxiliary variables for predicting SOC included bands related to Lands 8 OLI and sentinel 2 measurement images, topography, and climate. The results showed that the extraction of the components related to the bands along with the calculation of indicators such as normalized vegetation difference, wetness index, and the MrVBF index as auxiliary variables play an important role in more correct estimation of the amount of soil organic matter. Comparison of different estimation regressions showed that the Sentinel 2 random forest model and in Landsat8 with the values of coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MEA) of 0.64, 0.05, and 0.17, respectively, was the best performance ratio compared to other approaches used in the study to estimate the organic carbon content of surface soil in the study area. In general, the results of this study indicated the ability of remote sensing techniques and learning models in the spatial estimation of soil organic carbon. So, this method can be used as an alternative to laboratory methods in determining soil organic carbon.

Due to the upcoming climate threats, challenge of water shortage and its impact on the food security of the growing population in Iran, the optimal use of soil and water resources is very important. With the development of remote sensing technologies, free access to a variety of field data has become widely available, which can be used to reduce the uncertainty of simulation models. The aim of this study was to simulate actual evapotranspiration (ETa) and rice crop coefficients (Kc) during its growth stages using the SWAP model updated with satellite data and evaluate the accuracy of the results with/without updating. This research was conducted at the National Rice Research Institute of Iran in Rasht in the year of 2017. Based on the obtained results, total ETa measured by lysimeter and simulated by SWAP model with and without updating were 395.4, 373.2 and 363.6 mm, respectively. The average crop coefficients during the growth stages of vegetative, reproductive and ripening were estimated as 1.13, 1.49, 1.21, respectively. The crop coefficients for the proposed stages estimated by SWAP model without using satellite data were 1.02, 1.39, 1.04, respectively. After updating with satellite data, the crop coefficients were modified as 1.05, 1.43 and 1.07, respectively. Finally, the statistical analysis indicated that the SWAP model has a reasonable performance in estimation of ETa (RMSE=0.89; EF=0.98; R2=0.74) and rice crop coefficients (RMSE=0.53; EF=0.96; R2=0.63). The results indicate that the SWAP model combined with satellite data improved the accuracy of ETa estimation (RMSE=0.75; EF=0.99; R2=0.86) and rice crop coefficient (RMSE=0.40; EF=0.99; R2=0.74) at field scale.

One way to ensure food security is to produce strategic agricultural products on a large scale using industrial methods. Managing large-scale farms consistently and cohesively is a challenging task that requires the utilization of modern technologies. Crop anomalies refer to uncommon and limited factors during agricultural production, leading to localized differentiation in the crop cultivation process. Factors contributing to crop anomalies in agriculture include imbalances in soil nutrients and fertilizers, grazing during crop growth, pests, variations in soil texture and slope in pastures, weed growth, and drought. Detecting and remediating factors limiting crop growth in vast agricultural lands is difficult and these issues are often noticed at harvest time. This article suggests a solution for continuously monitoring of large agricultural fields by analyzing the time series of Sentinel-2 satellite images. The effectiveness of this solution in detecting various anomalies of farms, in agrarian areas has been demonstrated by the results. The proposed solution offers features such as timely diagnosis, the ability to monitor the continuation of irregularities, and the measurement of compensatory measures' effectiveness. The method has successfully identified over five types of anomalies in the selected farms, achieving a detection accuracy of 95.60%.