جستجوی مقالات مرتبط با کلیدواژه "classification" در نشریات گروه "محیط زیست"

The purpose of this study is to determine the quality of underground drinking water sources in Torbat Jam and Saleh Abad cities using quality index (WQI) and their zoning. In order to determine the quality index of water resources, the results of testing 9 parameters including: (PH, hardness, dissolved solids, calcium, magnesium, sodium, nitrate, chlorine and sulfate) were studied. Samples were taken from 110 spring wells and aqueducts in the region and transferred to the central laboratory of Khorasan Water and Wastewater Company headquarters, which has a standard certificate of 17025 for water chemical tests and the experiments were measured according to the latest standard version of the method in 2005 by the IC chromatograph device. In the final stage, after determining the quality status of drinking water wells, their quality zoning was done in ARC GIS10.2 software. Zoning maps of water resources quality showed that most of the water resources of Torbat Jam city are in the range of excellent and good water quality in terms of WQI index. Also, the results of statistical techniques (multiple regression) showed that sodium (Na) parameter had the highest influence coefficient in determining the WQI index, followed by sulfate, total hardness, chlorine and dissolved solids. Investigating the significance level of land use with quality index by Kruskal-Wallis test showed a significant difference between land use and water quality index.

Remote Sensing Technology is considered one of the most important sources of spatial and thematic data in the developed world of today. The objective of this work is a comparison of two different methods of change detection in forests using Landsat images. Therefore, sensor Landsat TM images of 1990 and 2011 (ETM+) satellite images have been used.

In the classification of images, the maximum likelihood algorithm, and artificial neural network to multilayer perceptron method were used.

Evaluated results showed that the algorithm approach, the maximum likelihood overall accuracy, and kappa coefficient maps classified in TM image, respectively, are 96.72 and 0.96 percent and image ETM+ 98.02 and 0.97 percent, and the method of artificial neural networks, overall accuracy and kappa coefficient map classified, TM image was 98.22 and 0.97% and ETM+ image was 98.34and 0.97 percent respectively. Following TM and ETM+ classification maps to detect the changes were marked and the map changes obtained.

The results of this study showed that using Landsat data along with data from have inventory capabilities of forest change mapping

National parks and wildlife shelter are the most important natural heritages; therefore, knowing of quantitative and qualitative changes in their land use plays an essential role in the quality of these areas' management. various algorithms have been developed to classify satellite imagery in remote sensing, selecting an appropriate classification algorithm is very important in achieving the accurate results. In this research, a more accurate algorithm was determined by comparing the classification accuracy of two artificial neural network and support vector machine algorithms, and it was used to examine the process of the land use changes. The present study was performed in Boujagh National Park, in the Guilan Province, during the years 2000 to 2017, using satellite imagery ETM and OLI of Landsat 7 and 8. The results of the research revealed that the support vector machine algorithm with overall accuracy and Kappa coefficient of 86.42 and 0.83 respectively for the year 2000 and, 90.65 and 0.88 for the year 2017, classified the satellite images more precisely, in comparison with the artificial neural network algorithm with overall accuracy and Kappa coefficient of 83.71 and 0.80 respectively for the year 2000 and overall accuracy and Kappa coefficient of 89.25 and 0.87 for the year 2017. Therefore, the land use maps of the support vector machine algorithm were used to determine the land use changes. The study of land use change by this method concluded that the areas of the waterbody, sea, grassland and agriculture have decreased and marshland, woody and bare lands classes showed an increase during the study period.

Wheat is one of the strategic agricultural products in Iran and the world. Having statistics data and information about the area under cultivation of this crop and estimating the amount of its production in one crop year can help the planners of agriculture and industry parts in order to manage the production and consumption of the mentioned product as effectively as possible. One of the tools that can calculate the area under wheat cultivation in the shortest time and with low cost and appropriate accuracy is the remote sensing system. In this study, the area under cultivation of rain wheat crop in Sojasroud village of Khodabandeh city of Zanjan province was estimated using multi-time satellite images of Sentinel-2 measuring satellite and its results were compared with the agricultural cadastral map of 2017-2018. Supervised classification and two methods of support vector machine and maximum likelihood were used to extract information and by comparing the two methods, the most appropriate method was selected and suggested. The error matrix was used to evaluate the accuracy of the classification. The overall accuracy of the support vector machine method was 89% with a capa coefficient of 0.80 and in the maximum llikelihood method it was 88% with a capa coefficient of 0.79. The evaluation results showed that the support sector machine classification method has a higher accuracy than the maximum likelithood, so to extract the area under cultivation in the study area, the support vector Machine classification method is proposed. Comparison of the results of the area under cultivation with the statistics of Jihad Keshavarzi showed a deviation of 18% and the amount of wheat crop using the area under cultivation obtained by classification method was compared with the statistics of the Rural Cooperative Organization which showed a deviation of 17%. The results showed that the classification of the support vector machine is an acceptable and appropriate method for identifying and separating wheat from other agricultural crops.

Since agricultural plain lands of Ardabil have been important in providing food stuffs, and due to the necessities of land usage management in this section, determination of process and change-rating of land cover I important for developers. In this regard, dynamic temporal data of remote sensing can play an important role in searching and analyzing of land usage change which is done by means of numerical change detection techniques in which the descriptive process of changes in covering variety and situation of land use is based on the temporal series image data. Basic hypothesis in using remote sensing data is on the base of these criteria that claims the ascending or descending nature of changes between two or more periods is recognizable, and by comparing the related data from different years, we can detect mutual relationships between natural, social and economic parameters. In this study, maximum likelihood supervised classification and change detection techniques were applied to Land sat images acquired in 1990 and 2007, respectively, to map land cover changes in the Ardebil city. A supervised classification was carried out on reflective bands for the four images individually with the aid of ground truth data. Ground truth information collected were used to assess the accuracy of the classification results. Using ancillary data, and expert knowledge of the area through GIS further refined the classification results. Change detection technique was used to produce change image through cross-tabulation Changes among different land cover classes were assessed. During the study period, a very severe land cover change has taken place as a result of agricultural and urban development projects. These changes in land cover led to vegetation degradation and cropland in part of the study area.

There was a possibility to study earth coverage on a large scale using remote sensing data. The support vector machines (SVM), artificial neural network ‏)ANN( and maximum likelihood )ML‏( algorithms were used to Land cover classification on OLI sensors data and 4 kernels in Guilan province.

Classifications were based on training samples of 10 different covers in the entire Guilan province. To improve the classification accuracy on OLI image data, the MODIS atmospheric products used in 6SV atmospheric correction model. The OLI atmospheric corrected image segmented to 219000 polygons based on homogeneity. In this study 2% of polygons were used to test and training samples by the random statistical method. Polygons labeled to classes by field survey.

Applying ANN, SVM and ML algorithms on the OLI images after atmospheric corrected by 6SV model, the overall accuracy of classification improved 0.11%, 0.8%, and 1.9% respectively. The results indicated that the land cover map by RBF-SVM had overall accuracy and kappa coefficient with 75.6% and 0.72 respectively. In this algorithm accuracy of agriculture, range‏ shrub land and water body classes were ‏93.16%, 72.55% and‏ 96.57% respectively. The results of this study indicated that SVM algorithm improved overall accuracy 1.67% compared to the ML algorithm.

This research indicated that in land cover classification and mapping of Guilan province, the nonparametric SVM algorithm had more accurate than the ML parametric algorithm. According to the results of this research, it is suggested that atmospheric correction models should be used especially on the large and local images.

In this study, the ecological status of Gorgan Bay is classified by using the results of biological indicators and diversity index. For this aim, data on macrobenthose and  the sedimentation characteristics were recorded at 22 sampling points during 2011 to 2012. According to the changes in the depth of the bay in different parts, the stations were classified into four groups of depth less than 1 meter, 1-2 meters, 2-3 meters and more than 3 meters. The total Range of organic matter, gravel, silt and clay in the Bay was recorded in (1.3-4.7), (47.1-57.7), (37.6-51.7) and (6.2-8.4) percent. The positive relationship between the total organic matter and the texture of bed indicates the accumulation of organic matter in the depths of the bay. By using multivariate tests the classified and distinct high depth from low depth of the bay, based on environmental conditions and parameters. The amplitudes change of Shannon index, BO2A and M-AMBI in the Bay were, calculated in range of (0.1-96.69), (0.02- 0.06) and (0.6- 0.8). Overall, according to the average of the calculated indices, Shannon weakened the whole ecological status of the bay and BO2A and M-AMBI indices the desired results were obtained. On the other hand, evaluation of the indicators showed that the condition of the shallow western part is better than the deep eastern part. This is can because of the region's hydrodynamic conditions and the adverse conditions for different benthic species due to the proximity to the River and other entrance around the bay.

In the past decade, remote sensing has been widely used to identify surface changes of different vegetation and their classification. Increasing the level of Canebrake of the Zarivar Lake and its risks for aquatic organisms living in the lake has become one of the most important issues in recent years. Therefore, the aim of this study was to identify surface changes of this Canebrake in the past three decades using Landsat TM and ETM. For this purpose, bands 3, 4, and 5 of images were geo-referenced. RMSE were less than one pixel for all bands. The supervised classification method with a maximum likelihood algorithm was also applied to detect the changes of water area on the combined images (bands 5, 4, and 3) of months with full water in the lake. NDVI index was utilized to identify the surface changes of Canebrake on the images taken in the months with low water in the lake. The results show that the rise and fall of water area and surrounding canebrake has a direct correlation with a rainfall and increase in both levels maybe occur at the same time. Study on the coastal strip of water area with GPS and combined images showed that the coastal line had not a significant change in the past three decades.

Since agricultural plain lands of Ardabil have been important in providing food stuffs, and due to the necessities of land usage management in this section, determination of process and change-rating of land cover I important for developers. In this regard, dynamic temporal data of remote sensing can play an important role in searching and analyzing of land usage change which is done by means of numerical change detection techniques in which the descriptive process of changes in covering variety and situation of land use is based on the temporal series image data. Basic hypothesis in using remote sensing data is on the base of these criteria that claims the ascending or descending nature of changes between two or more periods is recognizable, and by comparing the related data from different years, we can detect mutual relationships between natural, social and economic parameters. In this study, maximum likelihood supervised classification and change detection techniques were applied to Land sat images acquired in 1990 and 2007, respectively, to map land cover changes in the Ardebil city. A supervised classification was carried out on reflective bands for the four images individually with the aid of ground truth data. Ground truth information collected were used to assess the accuracy of the classification results. Using ancillary data, and expert knowledge of the area through GIS further refined the classification results. Change detection technique was used to produce change image through cross-tabulation Changes among different land cover classes were assessed. During the study period, a very severe land cover change has taken place as a result of agricultural and urban development projects. These changes in land cover led to vegetation degradation and cropland in part of the study area.

Despite of all the studies of aquatic invertebrates of Bahracan estuary, as yet Amphipoda inhibiting in the eastern shores muddy substrates of it, have not been studies from the point view of identification. The present investigation, aims to identify the Amphipods Bahracan shores (29˚ 50'-30˚ 15'N, 49˚ 30'-49˚ 55'E) of the Persian Gulf which was done during the seasons of spring and summer of 1392. Sampling was done by using vanveen Grab (with 0.0625m² surface areas) from stations in intertidal zone and 6-25 m depth. The samples were counted and identified through the valid identification keys. The obtained results of the study, identified six families were belonged to suborder Gammaridea, which are fallow: Ampithoidae, Ampeliscidae, Isaeidae, Gammaridae, Melitidae, Ischyroceridae. Frequency of each family was calculated throughout the study period; the families of Ampeliscidae and Ampithoidae were identified and introduced as the dominant families in Bahracan with 39.47%.

Classification of atmospheric aerosols is one of the important topics in the airborne and ground-based instruments remote sensing. Polarized sky radiance resulting from interaction between sunlight and atmospheric particles strongly depends on the presenceof aerosols in the atmosphere, and can be monitored by looking at the aerosol polarized phase function. In this paper, the ability the polarized phase function to classify atmospheric aerosols has been investigated for the atmosphere of the Zanjan. To do this, aerosol optical depth (AOD), Angstrom exponent (α), single scattering albedo (SSA), and polarized phase function have been retrieved from the measurements of SPM in the period of February 2010 to December 2012. The results show that the maximum valueof aerosol polarized phase function is strongly correlated (R = 0.95) with the Angstrom exponent. Furthermore the polarized phase function shows a moderate negative correlation with respect to the atmospheric aerosol optical depth and single-scattering albedo (R =−0.76 and−0.33, respectively). Therefore the polarized phase function can be regarded as a key parameter to characterize the atmospheric particles of the region –a populated city in the semi-arid area and surrounded by some dust sources of the Earth’s dust belt.

In this paper, has been tried to discriminate wheat_cultivated fields from those crops that have similar characteristics to this class, spectrally and phonologically, in bahar_hamedan region. So based on cultivation calendar of study region, decided to apply bitemporal or dual_season multispectral spot5 images for this aim. Both images divided to discrete objects(polygpns) using multiresoluion segmentation algorithm. The zonal attributes of segments entered to discriminant analysis as variables. After the stepwise discrimination analysis, all the segments were classified using outputted discrimination functions. ‘’discrimination accuracy’’ and ‘’ classification accuracy’’ were defined as discrete concepts. Also, with assuming the DNs of each band pixels as variables “pixel based” discriminant analysis was applied. Comparison of both methods results indicated that generally, accuracy of pixel_based classification is upper than other method.