جستجوی مقالات مرتبط با کلیدواژه « maximum likelihood » در نشریات گروه « جغرافیا »

This paper evaluates land-use changes in Sracheshmeh copper mine using temporal Landsat satellite imageries during period of 1972 to 2017. This aim was accomplished based on maximum likelihood classification method and post classification change detection method. The study area was classified considering 4 main classes including mining area, industrial area, bare land and vegetation class. The results were validated by comparing to real data classes using overall accuracy and kappa coefficient methods with 95% and 0.94, respectively. Land use changes in Sarcheshmeh mining region were investigated through comparison between pair images of time period of 5 years including 1972-1984, 1984-1988, 1988-1993, 1998-2003, 2003-2008, 2008-2013, 2013-2018 and time periods of 16 years including 1972-1988, 1988-2003, 2003-2018 and time period of 48 years from 1972 to 2018. years indicating severe increase in mining and industrial classes to 15.4 and 3.6 km2, respectively. Based on the results, experts and managers can identify the amount of changes among different land-use classes and establish development and environmental policies toward sustainable development in mining areas.

Land use mapping is very important in optimal land management. There are different methods of land use mapping that each of them has its own advantages and disadvantages. This research aimed to land use mapping by combining supervised, unsupervised, object-oriented, spectral methods and using vegetation and soil indices and ancillary maps (DEM and slope) in the Fandoghlo region.

This research was carried out by a descriptive-analytical method in the Fandoghlo region. At the first, the Landsat8 image was pre-processed and then the normalized difference vegetation index and brightness index were extracted and stacked with image bands. Agriculture, fallow, pasture, and water body classes were extracted using the maximum likelihood method. Then matched filtering analysis and density slice methods were used to extract barren lands and forest classes respectively. Residential and garden classes’ were extracted using object-oriented method. Finally, using expert knowledge and recognition of the study area and based on ancillary maps (slope and DEM), the final land use map was extracted.

The overall accuracy and Kappa coefficient of the synthetic method were 97.28% and 0.96, respectively, that is more suitable and practical for land use planning and management than the conventional methods of satellite image classification and land use mapping.

Based on the results of this research, it can be said that in order to land use mapping, according to the characteristics of each region in terms of homogeneity and the number of classes, as well as the type of satellite image, it is better to use different combinations of methods, indices, and ancillary maps are used for land use mapping.

According to the objectives of the present study after reviewing the statistics and information of precipitation in Haraz watershed and due to the lack of long-term statistics in the study area, finally 3 stations of Panjab-Haraz,Karsang-Haraz and Mahmoudabad-Haraz in different parts of the river from mountain to plain in 44-year common statistical period from the water year of 1968-69 to 2011-2012 was selected for this study. After analyzing the changes in annual precipitation of the selected stations, the results of Residual sum of squares (R.S.S) test were extracted by the method of ordinary moments and the maximum likelihood were compared with the method of linear moments. Residual Sum of the Squares (R.S.S in the linear moment method were also calculated by a written computer program for the studied distributions .Based on the results of this study and using the scoring and ranking method, it is determined that in Panjab-Haraz station, the maximum likelihood method has the lowest R.S.S, with the total score of 6 has the best fit with the annual precipitation data and ordinary and linear moments methods with a total score of 15 are equally in the next ranks .At Karsang-Haraz station, the maximum likelihood method has a total score of 10 and the best fit with the annual precipitation data, followed by the ordinary moment method with a total score of 14 and the linear moment method with a total score of 15, respectively. At Mahmoudabad station the maximum likelihood method with obtaining a total score of 3 has been the best method selected at this station, followed by the ordinary moment and linear moment methods with a total score of 6 and 15, respectively.

IntroductionStudying land cover changes has a very long history which coincides with the beginning of human life. Following the formation of societies, primitive humans began to change the cover of wasteland to form suitable lands for agriculture and animal husbandry. More than half of the world's population recently lives in cities, urbanization and urbanism is rapidly increasing, and this trend will continue to reach its peak. Due to their extensive coverage, reproducibility, easy-access, high accuracy and reduction in necessary time and expenses, remote sensing data are generally considered a preferred method used to study land cover, vegetation, and their changes. Many researchers have shown an interest in land cover change in different cities of the world. The history of land cover studies dates back to the early nineteenth century and the studies performed by von Thünen (1826). Von Thünen have determined the economic benefits of different land covers based on their distance from the central city and found an optimal distribution for production and land cover in the form of a series of concentric circles. Land cover changes due to human activities are considered to be an important topic in regional and development planning. Since land cover changes and urban development in the study area have not been previously studied, Landsat time series satellite imagery and a combination of Landsat 7 and 8 panchromatic and multispectral bands were used to identify and detect changes in land cover and urban development in the urban areas of Abarkooh from 2000 to 2020. Materials & MethodsSatellite remote sensing data are used in the present study (Landsat 7 and 8 multi-temporal satellite images collected in 2000, 2010 and 2020). 3 images were retrieved from US Geological Survey website and used in the present study. Raw remote sensing images always contain errors in geometry and the measured pixel values. The former category is called geometric errors and the latter is called radiometric errors. Atmospheric corrections were performed for all images used, and stripping in the imagery collected in 2010 image was also corrected. For image enhancement and extraction of more information from the images, false color composites were used (5-4-3 infrared, red and green bands) for Landsat 8 and Landsat 7 (3-4-3 near infrared, red and green bands) images. Using this technique, vegetation is shown in red. Compared to other methods, Gram-Schmidt based pan sharpening method produced higher spatial resolution images of the study area and thus was used to combine the selected images. Maximum likelihood method is considered to have the highest efficiency among various supervised classification methods. Results & DiscussionThis method assumes the presence of a normal distribution for all training areas. The accuracy of this classification has to be calculated following the classification. To do so, the kappa coefficient and overall accuracy of each class were calculated in ENVI5.3. The results are shown in the error matrix. Overall accuracy is the average of classification accuracy. The kappa coefficient calculates the accuracy of classification as compared to a completely random classification. Based on the available data, spatial resolution of the images and the information researcher has access to, 5 classes of training data (urban constructed space, roads, barren lands, arable lands, and gardens) have been selected for each image. Results obtained from the maximum likelihood classification method in ENVI5.3 environment were changed into the vector format and then used as a shape file in GIS environment. After compiling the land database, land cover maps and its changes were extracted in three periods and the area of each land cover class was determined. Each of the land cover maps, 5 classes with different colors are determined and shown. To ensure the accuracy of the classification, the accuracy of the classification has been evaluated. ConclusionThe resulting kappa coefficient for 2000 and 2020 equaled 86% and overall accuracy equaled 89%, while for 2010 kappa coefficient equaled 90% and overall accuracy equaled 92%. Thus, the error rate is small and acceptable. Finally, post-classification comparison method was used to investigate the nature of changes. 13 square kilometers of land cover were investigated in the present study. To identify the exact type of land cover changes, categorized images collected in these years were compared. Total area of residential land use showed an increasing trend: a total 4.25 square kilometers in 2000 (32.69 percent of the total area under study) has reached 5.58 square kilometers (42.92 percent) in 2020. Overall area of arable land use did not change much in the period of 2000 to 2010. However, a declining trend was observed in 2020 changing a part of this land use into residential and barren lands. Results of satellite image processing and classification indicate that supervised classification and maximum probability algorithm were close to ground realities and had an acceptable accuracy. In general, results indicate that significant amounts of vegetation and agricultural lands have been converted into urban areas and thus, planning for urban growth in these areas should be in favor of preserving gardens and agricultural lands.

Surface temperature is one of the important parts of the climate system that changes in land use and land cover cause its change and intensification. This study aimed to investigate the effect of land cover changes on Spatio-temporal changes in land surface temperature over 30 years using remote sensing and Landsat satellite images in Darab plain. After the required preprocessing on the images, classification maps of different types of land cover in the study area were prepared and the changes that occurred in each class were investigated. According to the studies, the rangeland class had the highest rate of changes and transformations with 72.14%. In the next step, Land surface temperature (LST) maps were extracted using the normalized index in 5 different classes. Among the temperature classes, the moderate temperature class had the largest area during the study period, which is distributed in almost all areas. Findings indicate that the vegetation areas with an average temperature of 29.82 ° C had a lower temperature than other areas without vegetation. In terms of land uses in the study area, the highest surface temperature during 30 years with an average of 38.07 degrees Celsius belongs to the barren land class. Another significant finding of the research is that the average temperature of pastures (32.03) and residential areas (33.37) of the study area during the study period are close to each other.

Soil erosion is an important factor that’s not dependent to only geo-ecological factors, rather dependent to land use changes and landscaping too. In this study, assessments the land use changes and its effect on soil erosion in Hoor al-Azim wetland located at southwestern of Iran and southeastern of Iraq countries. To do this study, using Landsat satellite imagery in May 1986 and 2016. For classification imagery, using the maximum likelihood classification method. The land cover map of Hoor al-Azim wetland was prepared. The accuracy values of classification assessments with calculating Kapa coefficient and general accuracy assessments with using error matrix. For TM sensor image, Kapa coefficient and general accuracy calculated are respectively 85.0 and 92.0 and for OLI sensor image respectively 89.0 and 94.0. Next, the soil erosion of study area, assessments with using the Universal Equation Assessment of Soil Erosion (RUSLE) in a period from 1986 to 2016. The general results indicate that in the period between 1986 and 2016, the area of land cover floors with low erosion class has been reduced and the area of high erosion classes has been increased and mainly the erosion class of more than 5 tons per hectare per year. According to the information obtained for 1986, about 26% of the area and for 2016, about 41% of the area, the amount of erosion is more than acceptable and in some parts is critical. Therefore, the results of this study clarify the need to address this issue and provide protection and management solutions.

 Urbanization is a continuous process and the spatial patternsof urban growth havealways played an important role in the transformation of human life throughout history. Urban growth has two dimensions: demographic and spatial, meaning that with increased urban population, the need for shelter increases and cities are faced with spatial growth. Expansion of cities in the spatial dimensions have several consequences,including changes in land use and land covers of areas surrounding cities.Land use change is currentlyone of the major concerns ofthe environmental approach, since land use changes in areas surrounding cities have led to changes in the economic structure of cities and the destruction of vegetation and agricultural lands as one of the main foundations of production in these areas. They have also seriously damaged other water resources, wildlife habitats, and resulted in the reduction of soil organic matter, changes in soil humidity and saltiness, increased energy consumption, increased urban heat islands, climate changes, as well as negative effects on the mental and physical health of urban residents. Nowadays, rapid growth in remote sensing technology and geographic information system, as well as the advancements in computer science and its application in environmental sciences and urban planning have created spatial modeling techniques such as Markov chain, Cellular Automata, intelligent neural networks and statistical models. Due to its dynamic nature, the capability of showing spatial distribution of land use changes, as well as its unique characteristics in modeling of natural and physical geographic featureson the ground and simpler adaptation with remote sensing data and GIS, a combination of Markov chain model and Cellular Automata are used as an important supporting toolfor decision making in urban planning and environmental sciences in many studies performedrecently.  Over the past few decades, the population of Iranhas increased from 27 million in 1955 to 79 million in 2016. And according to the 2016census, 74 percent of the population lives in urban areas. In recent years, the population of Kurdistan province has experienced a 1.42% (2011 to 2016)average annual growth rate (especially in Baneh, Marivan and Saghez), which isaround 0.18% more than the average annual growth rate of the country (1.24%). Investigating census data shows that Baneh, Marivan and Saqezhave experienced a higher urban growth rate as compared to other cities in the province, and thus monitoring this growth and predicting its negative effects on the surrounding land use seems crucial.Destruction of vegetation and agricultural lands not only results in climate change, but also directly affect the lives of residents in the region. Therefore, understanding the growth rate is necessary for properplanning and managementofthese areas.

Images received from Landsat in 1987, 2002 and 2017 were downloaded from the US Geological Surveywebsite and used in the present study. Google Earth images, land useand topography maps, and ground control points (GCP) were also used to perform imagepreprocessing, classification operations, and accuracy assessment. The study area includesBaneh, Marivan and Saqqez cities, which have recently experienced a high level of population growth. Considering the impact of population growth on increased rate of construction and physical development of urban areas, it is therefore necessary to study urban growth. In order to reduce the city’s impact on land use in future, it is necessary to modelurban growth. Using these models, planners can guide the urban development back to the optimal and appropriate routes and minimize the destruction of the land use.Image pre-processing in the present research was performed in ENVI5.3 environment. Then, using Maximum Likelihood algorithm, the images were categorized into five classes of water, residential areas, vegetation, agriculture and open spaces. Then, the overall accuracy of the classification maps was assessed using ground control points. To predict the urban growth, CA-Markov model was used in the IDRISI TerrSet software.

Findings indicate that the classified images have an accuracy of above 80%, and thus, land use maps of the study areas are valid.Investigations shows that the growth inMarivan and Baneh has most severely affected vegetation and agricultural land use. In the time period of 1987 to 2017, 897. 39 and 801 hectares of vegetation in Marivan and Banehhave been transformed into urban areas, respectively.During the same time period, 790.38 hectares of agricultural land in Marivan and 772.29 hectaresinBanehhave changed into urban areas. It is also important to note that unlike Saqez, the degradation of vegetation and agricultural lands in Marivan and Banehwas more severe than bare lands. In other words, bare landsinSaqez were more severely affected (as compared to vegetation and agricultural land), and about 1249,29 hectares of bare lands have turned into urban areas, while only 121.50 hectares of vegetation, and 509.04 hectaresof agriculture lands haveexperienced such a change.Also, results of the CA-Markov model showed that the growth of Baneh and Marivan cities in the 2017-2032 period will be in the Northeast and East directions, respectively. Results also indicate that this urban growth will affect agricultural and bare landsmore significantly. It is predicted that about 511.29 hectares of agricultural lands and 722.70 hectares of bare lands (in Baneh city) and 1080 hectares of agricultural lands and 2402.101 hectares of bare lands (in Marivan city) will turn into urban areas in this time period. 

Based on the findings, it can be concluded that planning urban growth inthe study areas should be performed in a way that vegetation and especially the surrounding agricultural lands are preserved, and the negative effects of land use changesare minimized. Also,plannerscan apply the results of the present study in their future plansto guide the development of Baneh, Marivan and Saqeztoward optimal ways and reduce land use degradation.

The process of identifying landforms is a subject that has been researched by many researchers. All the definitions of geomorphology emphasize the study and identification of landforms. Understanding landforms and how they are distributed are some sort of essential requirements in applied geomorphology and other environmental sciences (Shayan et al., 2012). On the other hand, remote sensing is a powerful tool for studying different ecosystems of the earth to produce valuable temporal and spatial data (Rezaei Moghaddam and Saghafi, 2006). Arekhi (2014) used ETM+ digital data to map the land use of the Abbas plain. To classify images, artificial neural network, supporting vector machine and maximum likelihood were used. Based on the results, neural network classification method has the highest accuracy of land cover mapping. Also, De laet et al. (2007), by studying the development and stability of desert pebbles in Turkey, concluded that desert pebbles in this area are formed likely (in situ) by mechanical erosion of the surface fragments and minimal Tophonomic effects, in sediment with diameters greater than 2 cm. The purpose of this study is to evaluate the efficiency of Landsat imagery in identifying and classifying desert pavement comprehensively using satellite imagery classification strategies.

The studied area with an area of ​​47645/98 ha, in Semnan city is located in 53° 28¢ to 53° 53¢ 43° east and 35° 20¢ to 35° 40¢north. ETM+ multispectral satellite data were selected for this study because of spatial, temporal and especially radiometric resolution. The data of this sensor comprises seven spectral bands, obtained from the USGS site. In order to distinguish different types of desert pebbles in terms of cover density using EDRISI Selva and ENVI 4.5 software and ETM+ sensor images of Landsat satellite, 4 methods including supervised classification methods, maximum likelihood, Mahalani distance, minimum distance from mean and Parallel surfaces were used. Each classification method was compared for classification accuracy using overall accuracy coefficients, kappa, user accuracy and producer accuracy.
The error matrix table was also presented for each method. In this matrix, the degree of compatibility of each class with the ground reality is shown, in which the degree of overlap of one class in the other classes can be observed. The error matrix diameter and the percentage of correctly classified classes and other cells show the number of assigned errors (column of each class in the error matrix) and deleted row of each class in the error matrix) (Lillesand et al. 2004, Ahmadpour et al. 2011). Finally, the spatial mapping of each method was plotted in Arc GIS 10.2.

Supervised Maximum Likelihood (MXL) classification method According to the results, the mentioned method has less interference than the other classification methods and except for the class with 40-70% pavement density which has 22.41% interference with the class with 70-90% density, the rest of the applications have less than 8% interference. According to the results, desert pavement with 20-40% density had the highest percentage of 56.62%.  Minimum Distance to Average (MinDis) supervised classification method The overall kappa coefficient for the minimum distance from the mean is 75.54% and the overall accuracy is 81.61%. According to the results, this method has less interference in two classes of 20-40 and 70-90% of desert pavement density than the other two classes. According to the results, desert pavement with a density of 40-70% had the highest percentage of area with 41.88% (9935.79 ha) and the exposed rock with 537.7 ha (1.12%) compose the lowest area in the region.Mahalani Distance Monitoring Classification Method (MahD)In this method, there is a high degree of overlap between the classes, with the highest interference being between 40-70% and 70-90% of the desert pavement, which accounts for 25.86% of pixels for the 70-90 class. According to the zoning, the desert pavement with a density of 20-40% with an area percentage of 53.55 have the widest class in this method. Also, the lowest percentage of area with 13.39% (6376.43 ha) of the whole area is related to the rock outcrop.Supervised Classification Method of Parallel SurfacesThe overall kappa coefficient for this method was 21.06% and the overall accuracy was 41.25%. The estimated coefficients indicate the inefficiency of the model in separating the pavement classes. The lack of recognition and separation of the two rock outcrops and pavement classes with density of 20-40% has increased the area belonging to the two classes of pavement and the mismatch with real conditions and ground reality, so that, with pavement with 70-90% density and the area covers of 34/99,995 ha (73.52%) of the region.

Given that for optimal use of multispectral data, it is necessary to identify the best band composition. Choosing the best bonding combination is difficult and time consuming visual comparison. Therefore, a technique called Optimal Determination Factor (OIF) can be used to determine the most appropriate band composition to produce the best false color image and to determine the most appropriate bands for digital classification (Alavi Panah, 2000). The results of applying the optimum index in the present study showed that the best band composition for the detection and separation of the desert pavement in the south of Semnan is a combination of 6-4-3 with the optimum index value equal to 71.45 that are located in visible and infrared thermal band (VNIR +TIR). Climatic and geographical differences, satellite harvest time, physicochemical and biological properties of landforms and other effects in the area can produce different results. On the other hand, the classification methods used in this study differ in terms of the structure and complexity of the algorithm, which were calculated to evaluate the performance of the methods, kappa coefficients and overall accuracy. The classification results show that the coefficients of the classification results accuracy obtained from the used methods are considerable. Since the classes, bands, and other conditions used for all methods are the same, the difference in accuracy depends only on the computational algorithms of the methods. In all the investigated methods (except for the least distance from the mean), the class with desert pavement of 20-40% has the lowest kappa coefficients and accuracy, indicating the low ability of the investigated methods in spectral resolution of this class. In general, spectrally separable classes show pretty high accuracy in all methods, and vice versa. The use of other object-based classification methods as well as better spatial and spectral resolution sensors images and the incorporation of properties such as particle diameter can be effective in mapping desert pavement classes.

The forests of the Zagros vegetation area cover about six million hectares (40%) of Iranchr('39')s forest area, which is dominated by oak species. These forests are exposed to a number of threats, including land use change, deforestation, over grazing, deliberate and unintentional fires, pest and disease attacks, and climate change. Although accurate and timely identification of changes at the Earthchr('39')s surface is the basis for understanding the relationship between human functions and natural events and the use of natural resources, it is important to gather information about continuous changes in forest cover. Field operations require a lot of time and money. Therefore, the study of forest cover changes using satellite imagery has become one of the most important sub-branches in forestry science and is a tool for monitoring and controlling various changes in forest ecosystems. On the other hand, soil erosion in forest areas is lower than the other areas such as agricultural and rangeland areas, but extensive deforestation to produce wood and crops in recent years has significantly reduced sediments. Typically, the concentration of suspended sediments is estimated by the method of measuring the scale of sediment and discharge. Such curves are often generated using linear logarithmic regression of sedimentation and discharge data or conventional data curve in which the relationship between discharge and suspended sedimentation is a logarithmic linear equation. In the present study, land use changes in three forest watersheds in Kohgiluyeh and Boyer-Ahmad and Fars provinces were investigated using satellite imagery. Then, the effect of land use changes, especially good forest and rangelands on the values of sediment measurement equations in the study areas were analyzed.

The studied area with an area of 2400 square kilometers is part of the Zagros forests, which includes three forest watersheds of Seyedabad and Shah Bahram in Kohgiluyeh and Boyer-Ahmad provinces and Shivzohreh catchments in Fars province. At first, forest cover map of the last three decades (1987-2017) was prepared using Landsat satellite images. After initial pre-processing of Landsat images, the Maximum Likelihood (ML) supervised algorithm was used to prepare the land use map and 11 land use classes were separated. An error matrix was used to evaluate the classification accuracy of the land use classes, which includes criteria of producer accuracy, user accuracy, overall accuracy and Kappa index. Based on this, 532 field samples were prepared using a combination of field visits and Google Earth. After preparing the land use change maps in four time periods of 1987, 1997, 2007 and 2017, the annual discharge changes and the sediment rating curve were extracted in three ten-year periods using the data of the hydrometric station at the output of the catchments. For this purpose, rating curves were drawn in the three periods of the mentioned decade and the values of equation coefficients of the curve were compared during the mentioned periods.

The results showed that the total accuracy of the land use map of 1987, 1997, 2007 and 2017 was 87.34, 87.62, 87.07 and 90.4%, respectively, and their Kappa coefficient was 0.85, 0.86, 0.85 and 0.89, respectively. The forest land use had a good producer and user accuracy. Also, in Seyedabad area during the first two decades, soil erodibility (coefficient α) increased, but in the period 2007-2017 due to a significant increase in the area of mostly good forest lands (F1), has decreased. In the catchments of Shah Bahram and Shivzohreh, with decreasing forest lands of mainly weak (F3) and pastures of mainly good (R1), during three consecutive decades, soil erodibility has decreased. On the other hand, with the decrease in annual discharge, especially in the period of 2007-2017 in Seyedabad and Shah Bahram catchments, the value of coefficient b has decreased, but in the Shivzohreh catchment, despite the decrease in discharge in three consecutive decades, it seems that due to the hydrological changes of the river as a result of human activities and the availability of new sedimentation resources, the value of the coefficient b of the sediment rating curve has increased.

Since the rate of erosion in forest lands is lower than rangeland and agricultural lands, so in Seyedabad catchment, despite increasing the area of ​​medium rangeland lands (R2), with decreasing area of ​​good rangeland lands (R1) along with reducing forest lands during the first two decades of the year, soil erodibility (α coefficient) increased and therefore the value of α coefficient of sediment rating curve during the period 1997-2007 compared to the previous period 1987-1997 increased by about 0.05. However, in the period 2007-2017, despite a slight increase in the area of ​​rangeland lands, due to a significant increase in the area of ​​mostly good forest lands (F1), soil erodibility has decreased and therefore the value of the α coefficient of the sediment rating curve compared to the former period has decreased by 0.11. In the Shah Bahram catchment, over the last 30 years, the area of forest lands has steadily decreased by about 43 square kilometers every three decades, while the area of rangelands has increased by about 39 square kilometers. However, the α-coefficient of the sediment rating curve has been steadily decreasing during the studied periods, because on one hand the area of mostly weak forest lands (F3) has decreased over 10-year periods and on the other hand the area of mostly good rangelands (R1) has increased, so soil erodibility (α coefficient) has also decreased. In Shivzohreh catchment, although the area of forest lands has decreased by about 8 square kilometers in the last 30 years, these forest lands are mainly related to weak forest lands (F3). On the other hand, the area of rangeland lands has increased by about 39 square km, which is mainly related to good rangeland lands (R1), so such changes in the coverage of this area have reduced soil erodibility and therefore the value of the α-coefficient of the curve has been steadily declining over three decades.

Extended Abstract Introduction Currently, two general methods are used for classification of digital satellite images: pixel-based and object-oriented processing. Unlike pixel-based Methods, object-oriented techniques employ different geometric, spatial, spectral, and form-based algorithms, and selecting the most efficient algorithm in this process requires a lot of experience in image processing. In addition, multiple algorithms usually offer different results and this in many cases makes the selection of efficient algorithms difficult. In general, pixel-based classification includes supervised and unsupervised methods. Examples of these methods include maximum likelihood, neural network and support vector machine. Maximum likelihood method is one of the most effective methods used for image classification. Object-oriented methods take advantage of knowledge-based algorithms, and thus overcome problems pixel-based method faces because of not using geometric and textual information. In order to achieve high classification accuracy, two methods of pixel-based and object-oriented classification are compared in this research. On the one hand, integrated planning and management of urban areas, and on the other hand, collecting reliable information regarding land use makes this kinds of studies indispensable. Materials&Methods Present study seeks to extract urban land use map. Thus, necessary data was received from Sentinel-2. Moreover, ENVI 5.3, eCognation 9, SNAP, ArcGIS 10.3, Google Earth, and land-use data were also used to process images and analyze data. In SNAP, atmospheric correction process was performed on images collected from the study area using SEN2COR plug-in. Samples collected from each class of Sentinel-2 satellite image were mapped on the image area. Pixel classification algorithms, support vector machines, maximum likelihood, artificial neural network, Minimum Distance to Mean (MDM), parallelepiped and Mahalanobis distance were used. Finally, land use classes (residential, gardens and green spaces, wastelands and passageways) in the study area were mapped using different classification algorithms. For object-oriented classification using nearest neighbor algorithm, the satellite image was first segmented in eCognation software using the Multiresolution Segmentation Algorithm. Parameters such as scale, shape and compactness were also studied in the image segmentation stage. Through trial and error, an appropriate value was selected for parameters used in segmentation. For practical comparison of the results, the same educational data was used in both object-oriented and pixel-based classification methods. Then, the most important methods for assessing accuracy including overall precision and kappa coefficient were extracted. Results & Discussion As one of the most important methods used for extracting information from remotely sensed images, classification allows users to produce various types of information such as coverage maps, and land-use maps. Classification of satellite data includes segregation of similar spectral sets and classification of sets with the same spectral behavior. Regarding the resolution of images used (10 m) in this study, only 4 land-use classes possessed the required resolution capability for pixel-based classification of Sentinel-2 satellite images. These classes include built-up (residential) area, waste land, urban green space and street network. In this regard, support vector machine, maximum likelihood, artificial neural network, Minimum Distance to Mean, parallelepiped and Mahalanobis distance were used for classification. Classification results indicate that compared to other pixel-based methods, maximum likelihood method and Minimum Distance to Mean method show a precision of 85% or higher. In present study, geometric properties of land use classes (including scale, shape, and compactness) were used for segmentation and this process was performed by multiresolution method. For this purpose, results of image segmentation process were analyzed based on different parameters (with different scales) and spatial resolution of the image. In this way, appropriate values for segmentation were selected based on the specific features of the study area (an urban environment) through trial and error. Then, the proper image segmentation was selected and prepared for the classification stage using the above mentioned parameters. In the next step, 20 effective parameters including statistical indices, mean score of bands, NDVI index, standard deviation of the bands and geometric index were used for classification. Conclusion The present study took advantage of six pixel-based methods (Support Vector Machine, Maximum Likelihood, Neural Network, Minimum Distance to Mean, Parallelepiped, and Mahalanobis) along with object-oriented classification method to produce a land-use map for Zanjan city. The accuracy of classification in different methods were compared and statistically analyzed using overall accuracy coefficient, kappa coefficient, user’s accuracy, and producer’s accuracy. The results of statistical analysis of the accuracy coefficients indicated that Minimum Distance to Mean and Maximum Likelihood method -with a Kappa coefficient of 90% and 85% respectively- are acceptable methods for land use mapping. Moreover, comparing pixel-based and object-oriented methods, it is possible to conclude that object-oriented approach with a Kappa coefficient of 0.95% and overall accuracy of 97.9% shows a higher potentiality. Nearest Neighbor algorithm is one of the most important reasons for achieving this high accuracy in object-oriented classification. In addition to the spectral information, this method uses information collected about issues like texture, form, position, and content for the classification process. Methods used in this study prove the accuracy of objective-oriented technique by employing effective parameters and developing rules to modify the initial classification of object-oriented technique. Another advantage of object-oriented method (as compared to pixel-based methods) is that apart from spectral information and statistical data, it is possible to apply several other indicators such as shape, texture, color, dimensions and altitude of the phenomena in the final land use map produced by this method. Finally, it should be noted that object-oriented classification has been developed for high resolution spatial data.

In this paper, data of the annual fastest wind speed in Bushehr station in south of Iran were used and graphical and numerical methods were applied to compute scale and local parameters of the Gumbel Distribution Function (GDF). Then, different return periods for the annual fastest wind speed were estimated. In the estimation process of local and scale parameters, Standard analytical procedures such as Method of Moments (MOM), Method of Order Statistics Approach (OSA), Least Squares Method (LSM) and Maximum Likelihood Method (MLM), were used.  
Numerical computations show that the Method of Moments (MOM) provides better results compared to other methods and computed values for the scale and local parameters in estimation of annual fastest wind speed in Bushehr station are the best estimation.
Computations of the annual fastest wind speed for return periods of 25, 50,100 and 1000 years, estimated to 29.7 m/s, 32.8 m/s, 35.8 m/s and 45.9 m/s, respectively. Moreover, we can say that, in the confidence level of 95%, every 207.2 and 82.9 years, annual fastest wind speed of 39 m/s and 35 m/s can happen, respectively.

The purpose of this research is to extract changes of shore line in Bushehr Province using satellite imagery processing. In this study, land use maps produced by +ETM and OLI Landsat sensor images by Maximum Likelihood method in 2006 and 2016, has been classified in 5 classes: Vegetation, water, man-made, pastureland and bay. According to given Kappa coefficient and overall accuracy, the results of this monitoring showed process of coastal changes during the 10-year period has been most affected by the construction of offshore structures and the largest amount of coastal morphology has been the forefront of this complication at the edges of the breakwaters to the sea.

Monitoring of land use changes in Lahijan County is the purpose of this study. In this study, land use maps produced by +ETM and OLI Landsat sensor images by Maximum Likelihood method in 2002 and 2015, has been classified in four classes: water, forest, agriculture and human made, with a kappa coefficient of 0.87 and 0.92 percent, as well as a total accuracy of 89.73 in 2002 and 93.68 in 2015. Then, the changes of land use maps were monitored using Change detection method. The results of this monitoring showed the urban use class had the highest increase with 4437.16 hectares, and in contrast, the forest class had decreased by 3347.48 hectares which is largely due to the construction of tourism in the second homes and catering centers in the city of Lahijan.

Cold and frost waves are are among the most important natural phenomena, occuring in the cold period of the year. The reason why the frost phenomenon has been considered is it's feedbacks on the nature and human life, which sometimes has been associated with negative severe tension and sometimes positive feedbacks, particularly in agriculture and gardening. This study has tried to analysis of daily, as monthly and seasonal, frosts of Southern Khorasan province. To do this, the minimum daily temperature of synoptic stations of Southern Khorasan province were used for a 27 years period (1988-2014). And to investigate the probability and frequency of the frost days, Markov chain model was used. Results illustrated that Ghaen city in the north, and Birjand city in center of Southern Khorasan province, had the maximum occurrence and frequency of the frost days, respectively. Among the stations, Nehbandan city has experienced the minimum probability of frost days. Two-days continuities in all stations, revealed the minimum return period, indicating the less continuity of frost days in Southern Khorasan province.. All the analyzed stations in the studied area, except for Nehbandan, which generally hasn't experienced any frost day, are characterized by Markov chain, first class. In other words, any occurrence of frost days, depend on climate conditions of past days. The beginning of autumn frost days of Southern Khorasan province, is in November, known as the first autumn frost; and the beginning of winter frost is concentrated in January. The maximum frosty cycle in October have been occurred in Ghaen station about 0.058, and in November in Ferdos and Boshrooye stations about 0.05 and 0.043, respectively. Results confirmed the obvious role of high and mountain regions in the frequency and continuity of frost days in the province.

Desertification is associated with the process of destroying and demolishing the natural ecosystems in ultra-arid, arid, semi-humid arid regions, leading to reduced biomass production and the appearance of soil degradation or erosion effects. More than 80% of Iran is located in ultra-arid, arid, semi-humid arid regions of the country with fragile ecological conditions and are influenced by desertification phenomenon.
In order to study the desertification and to analyze the trend of its changes, a wide range of spatial and temporal information such as geomorphology and land-use are needed. In fact, analyzing their changes is the process of identifying differences in the status of an object or a phenomenon by observing it at different times, which provides a basis for better understanding of human relationships and interactions with natural phenomena for managing and making better use of resources. In environmental management, the most common contributions of geomorphologists are to provide a map of landscapes with emphasis on its selected features, to understand the nature and causes of landscape changes, and to organize them according to trend predictions during the formation processes and the transformation of landforms. Human's specific use of territory as land use is also an important consideration in land tenure assessment. These applications change at time intervals. In arid and semi-arid regions, these changes usually lead to increased desertification.
The identification of deserts' landforms and land-use, their classification and mapping at various time intervals are considered as a method for change detection in these areas. Today, using remote sensing (RS) instead of the visual interpretation to identify landforms and land use and their change detection is a necessity. One of the steps in identification of change detection is the classification of remote sensing data. There are various methods for the classification of satellite images. These methods can be used for separation of different geomorphological landforms and land-uses and their variations. Each method has its own advantages and limitations. The choice of the research method in geomorphology depends on the purpose of the study and the available data. Today, the use of satellite data and remote sensing techniques are considered as a modern method in geomorphological studies.
The most common classification methods can be referred to as the maximum likelihood classification. Other classification methods such as the minimum distance, Mahalanobis distance, and neural network have attracted much attention. The main objective of this study is to investigate and analyze the temporal variations of geomorphologic landforms and land-use in desertification part of Yazd-Ardakan Plain. For this purpose, time series satellite observations of Landsat sensor were used from 1986 to 2016 (over 30 years). In this research, a part of the Ardakaan-Yazd basin is considered for desertification analysis due to the issues and problems related to land destruction and the critical focus of wind erosion. This district, according to the latest political divisions, includes central zone and Khezerabad zone of Sadoogh county in Yazd. The area of the study area is 1563.11 km2.
The research method in this study is analytical survey. To study the changes of desert's landforms and land uses, two satellite imageries of TM and OLI of Landsat satellite of 1987 and 2016 were used. First, the radiometric and atmospheric corrections was performed using Flaash algorithm, and then the geomorphological landforms and land use were introduced and the training samples were selected by field observations, topography and geomorphology maps, and Google Earth images. To classify the landforms and land use, the supervised classification of maximum likelihood algorithm was used. Then, the accuracy of classified maps was evaluated using the overall accuracy and the Kappa coefficient metrics. Finally, to evaluate the changes of landforms and land-uses, the post classification method was used. To analyze the database, ENVI 5.3, ArcGIS 10.4.1 and Excel 2013 software were used. In the present study, 15 landforms were identified in the study area with regard to field observations, available resources and geomorphologic map of Yazd-Ardakan plain.
Totally, 15 landforms were identified in the study area, including Alluvial Fan, Glacis Pediment Plain, Clay Pan, Glacis Dennoyage Plain, Inselberg, Glacis Epandage Plain, Kalut, Erg (barchans, longitudinal dunes, barchanoid), hills, mountains, Salt Dome, Sebkha and Sand Sheet. In addition, 8 land-use classes were identified in the study area. After the image correction, the geomorphological and land use maps were prepared. Finally, to investigate the nature of the changes, the comparison method of post classification was used, which was applied on maximum likelihood algorithm. Then, the changes of landforms were calculated in terms of its area and percentage. The results showed that the dominant class was the Glacis Epandage Plain in the both satellite images of 1987 and 2016. Then, hills with 17/58 percent of the total area are ranked as the highest area in 1987, while this class had downward trend with 11/58 percent in 2016. In 1987, Barkhan class had the lowest area with 0/17 percent, whereas this class had downward trend with 0/11 percent in 2016.
Changes in land use classes over a 30-year period in terms of area and percentage indicate that the predominant class in 1987 was the low-density rangelands of the range of 25-5%, which, remains the prevailing class in this year even with the decrease in the area of this class in 2016.
The saline lands with 22312.63 hectares of the entire region are of the next order of the most area in 1987 but have the decreasing process to 1.14% in 2016. In 1987, the urban class occupied 0.46% of study area with a growth rate of 2.33% by 2016. The construction of forested trees for deforestation also shows a growth rate of 15.36% over 30 years. The results of the landforms and land use classification showed that the maximum likelihood algorithm offers a detailed classification method. The area and the percentage of landforms and land use changes over 30 years showed that landforms such as Barchan, Clay Pan, Longitudinal Dunes, Barchanoid and Kalut had a downward trend, because they were located in the context of the development of the city. The results showed that Sabkha area has followed a downward trend over 30 years. The comparison of our results with the results of previous studies showed that the increase of wells in Yazd-Ardakan plain has helped cultivate the large areas of saline lands. Therefore, the natural and human factors were involved in changing the desert landform and land use in the study area.
It should be noted that this study shows that the separation and analysis of the landform variations, such as the Salt Dome and Inselberg created in long time intervals, cannot be easily accomplished using the maximum likelihood algorithm. Because they were of ascendant trend during 30 years according to the outcomes, and this is because of similarity of their adjacent spectral reflections in which case the pixels of these landforms have been replaced by more pixels. However, according to the results, separating and analyzing the changes of the sandy hills is possible with the maximum similarity algorithm method during 30 years (from 1986 to 2016). In general, the results of this research were in the line of the previous studies that confirm above statement.

Obtaining more accurate and updated information about the forest area is one of the basic factors in sustainable management of this area. Acquiring this information is more beneficial in terms of time and cost through classification of remote sensing data. In this paper, Landsat8 (OLI) data from Maroons Behbahan riparian forest that is located in Khoozestan province of Iran were used for mapping and better management of riparian forest. Preprocessing operation including radiometric and atmospheric correction was applied to the data. Supervised classification algorithms including maximum likelihood (MLC) and support vector machine (SVM) with seven and three classes were used for classification. In order to evaluate the capability of support vector machine, three categories of training data with 241, 141 and 41 numbers with four kernels of SVM (linear, radial basic function, sigmoid and polynomial) were used. The results indicate that mapping of Maroons riparian forest using Landsat images is possible and the best result was acquired using SVM –polynomial method by three classes with overall accuracy and kappa coefficient of (99/24) % and (0/97) respectively. Also, the findings showed that with reduction of number of classes from seven to three, the accuracy of classification is increased. By reducing the number of samples to moderate, significant difference in accuracy of classification was not observed, but by more reduction of samples, the accuracy of results is reduced.

Land management leading to sustainable development requires reliable and update data on land cover/use and mapping its changes at various spatial and temporal scales. In this aspect, water resources management also needs to assess land use and its changes across the basin to maintain water quality for a variety of uses. Thus, the primary goal of this study is to evaluate the effectiveness of various spectral-based supervised classification methods of Operational Land Imager (OLI) data for mapping land use across the Kan and Karaj Rivers basin. At the Anderson Level 1 and 2, the basin’s land use was mapped in five and nine classes, respectively using a broad range of different supervised classification methods, including Parallelepiped, Minimum Distance, Mahalanobis Distance, Maximum Likelihood, Spectral Angle, Binary Encoding, Spectral Information Divergence, Neural Net and Support Vector Machine. All classification methods were verified using the Google Earth images and accurate ground control points, in which the Maximum Likelihood method of both levels with Kappa coefficient of 0.77 and 0.76 and overall accuracy of 84.94 and 80.70 percent, identified as the optimum method to map the land use at the local and regional scales respectively. In addition, following the named method, the Neural Net, Support Vector Machine and the Mahalanobis Distance methods also showed acceptable accuracy indicating that like the choice of classification method, precision in procedures and accuracy assessment of land use classification map is very important and could affect the results.

Because the various algorithms have been developed for the land use classification by using remote sensing, the suitable algorithm selection plays an important role in achieving good results. For this purpose, by efficiency comparison of two algorithms classification i.e. support vector machines (SVM) and maximum likelihood (ML), the more precision method was determined and it was used for investigating land use changes trend. The present research was carried out using TM, ETM and OLI sensors images in Siminehroud watershed. The research results showed that SVM algorithm classified satellite images better than ML algorithm and radial basis function (RBF) kernel has the highest overall accuracy among the studied methods. Therefore, SVM algorithm with RBF kernel was used to derive land use maps and monitor land use changes in the studied periods. By analysis of land use changes trend using this kernel, it was found that during studied periods, irrigated farming from 30535ha to 67210ha, dry farming from 79909ha to 123387ha, residential from 474ha to 1934ha land uses have been increased but rangeland from 259811ha to 178397ha and water resources from 30535ha to 67210ha land uses are decreasing.

Among the important factors in urban planning and management, particularly in line with the achievement of the sustainable development in the urban areas as well as regarding the optimal use of the land, is on-time access to the data of land cover conditions in these regions. The remote sensing data has a high potential for the preparation of the update urban land cover maps. In order to present on-time and digital satellite data, a variety of shapes and possibility of processing during land cover maps are of high significance. In order to use the satellite photos Landsat/ETM+ and two algorithm of supervised classification including the maximum likelihood and the artificial neural network, land cover maps were prepared. During classification, the neural network algorithm of a perceptron network with a hidden layer and 7 input neurons, nine middle neurons and 4 output neurons were used. The input neurons are the same in number as the bands of the Landsat photos and the number ofoutput neurons are the same as land cover map classes. Eventually, land cover map of the region has been classified into four classes of residential areas, barren lands, plant coverage, and roads. In order to evaluate the correctness of the classification results, many photos have been taken using GPS. Using overall accuracy and Kappa Coefficient the precision evaluation results of these two methods indicate that perceptron neural network has an overall accuracy of 98/24 and Kappa Coefficient 97/03 compared to the algorithm of maximum likelihood with an overall accuracy of 94/23 and Kappa Coefficient 90 / 34 is of higher precision. The findings of this study also show that the classification method for multilayer perceptron neural network as compared with the maximum likelihood method is of higher separation and capability for preparing the land cover map in the urban regions.