ISO CLUSTER CLASSIFIER BY ARCGIS FOR UNSUPERVISED CLASSIFICATION OF THE LANDSAT TM IMAGE OF REYKJAVÍK

The paper presents the use of the Landsat TM image processed by the ArcGIS Spatial Analyst Tool for environmental mapping of southwestern Iceland, region of Reykjavik. Iceland is one of the most special Arctic regions with unique flora and landscapes. Its environment is presented by vulnerable ecosystems of highlands where vegetation is affected by climate, human or geologic factors: overgrazing, volcanism, annual temperature change. Therefore, mapping land cover types in Iceland contribute to the nature conservation, sustainable development and environmental monitoring purposes. This paper starts by review of the current trends in remote sensing, the importance of Landsat TM imagery for environmental mapping in general and Iceland in particular, and the requirements of GIS specifically for satellite image analysis. This is followed by the extended methodological workflow supported by illustrative print screens and technical description of data processing in ArcGIS. The data used in this research include Landsat TM image which was captured using GloVis and processed in ArcGIS. The methodology includes a workflow involving several technical steps of raster data processing in ArcGIS: 1) coordinate projecting, 2) panchromatic sharpening, 3) inspection of raster statistics, 4) spectral bands combination, 5) calculations, 6) unsupervised classification, 7) mapping. The classification was done by clustering technique using ISO Cluster algorithm and Maximum Likelihood Classification. This paper finally presents the results of the ISO Cluster application for Landsat TM image processing and concludes final remarks on the perspectives of environmental mapping based on Landsat TM image processing in ArcGIS.The results of the classification present landscapes divided into eight distinct land cover classes: 1) bare soils; 2) shrubs and smaller trees in the river valleys, urban areas including green spaces; 3) water areas; 4) forests including the Reykjanesfólkvangur National reserve; 5) ice-covered areas, glaciers and cloudy regions; 6) ravine valleys with a sparse type of the vegetation: rowan, alder, heathland, wetland; 7) rocks; 8) mixed areas. The final remarks include the discussion on the development of machine learning methods and opportunities of their technical applications in GIS-based analysis and Earth Observation data processing in ArcGIS, including image analysis and classification, mapping and visualization, machine learning and environmental applications for decision making in forestry and sustainable development.

Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering

The paper presents the cartographic processing of the Landsat TM image by the two unsupervised classification methods of SAGA GIS: ISODATA and K-means clustering. The approaches were tested and compared for land cover type mapping. Vegetation areas were detected and separated from other land cover types in the study area of southwestern Iceland. The number of clusters was set to ten classes. The processing of the satellite image by SAGA GIS was achieved using Imagery Classification tools in the Geoprocessing menu of SAGA GIS. Unsupervised classification performed effectively in the unlabeled pixels for the land cover types using machine learning in GIS. Following an iterative approach of clustering, the pixels were grouped in each step of the algorithm and the clusters were reassigned as centroids. The paper contributes to the technical development of the application of machine learning in cartography by demonstrating the effectiveness of SAGA GIS in remote sensing data processing applied for vegetation and environmental mapping.

Distance-based vegetation indices computed by SAGA GIS: A comparison of the perpendicular and transformed soil adjusted approaches for the LANDSAT TM image

Landsat-TM of 2001 covering Iceland (15.5°W-21°W, 64.5°N-67°N) was processed using SAGA GIS for testing distance-based Vegetation Indices (VIs): four approaches of Perpendicular Vegetation Index (PVI) and two approaches of Transformed Soil Adjusted Vegetation Index TSAVI. The PVI of vegetation from the soil background line indicated healthiness as a leaf area index (LAI). The results showed that the reflectance for vegetation has a linear relation with soil background line. Four PVI models and two TSAVI shown coefficients of determination with LAI. The dataset demonstrate variations in the calculated coefficients. The mode in the histograms of the PVI based on four different algorithms show the difference:-7.1,-8.36, 2.78 and 7.0. The dataset for the two approaches of TSAVI: first case ranges in 4.4.-80.6 with a bell-shape mode of a histogram (8.09 to 23.29) for the first algorithm and an irregular shape for the second algorithm with several modes starting from 0.11 to 0.2 and decreasing to 0.26. SAGA GIS permits the calculation of PVI and TSAVI by computed NDVI based on the intersection of vegetation and soil background. Masking the NIR and R, a linear regression of grids was performed using an equation embedded in SAGA GIS. The advantages of the distance-based PVI and TSAVI consists in the adjusted position of pixels on the soil brightness line which refines it comparing to the slope-based VIs. The paper demonstrates SAGA GIS application in agricultural studies.

Assessment of Forest Cover Change of Dang, an Inner Terai District of Nepal

This study analyzed the dynamics of changes of forest cover classes in the inner Terai District Dang, Nepal, based on Landsat Thematic Mapper (TM) images from two different years, viz., 1990 and 2011. Forest cover change analysis was performed through the analysis of a classified Landsat TM image using supervised classification. The overall classification accuracy for seven different land cover classes considered in this study were 80.37% and 80.56% for years 1990 and 2011, respectively. These classified images were further reclassified as forest and non-forest to analyze forest cover dynamics effectively using the post classification change detection. The results indicated that during 1990-2011, the total spatial areal coverage of forest land converted into other land cover was 20612 ha (shrub-land), 8571 ha (agriculture), and 2787 ha (others) non-forest classes. A significant portion of non-forest classes was also converted into forest (e.g., 11433 ha of shrubland, 5663 ha of agriculture, and 5581 ha of other non forest classes). Sand and water bodies remained more or less constant during this period. While forest cover was estimated to be disappearing at the rate of 0.2% per year, dense forest appears to be converting into a sparse forest at the rate of 0.1% per year. Future study to assess the causes and driving forces of forest cover change in Nepal should get guidance from this study on where to target interventions.

Advances in Application of Fuzzy sets in electrical engineering

<p>Initially a theory, today fuzzy logic has become an operational technique. Used alongside other advanced control techniques, it is making a discrete but appreciated appearance in various electric systems. In the majority of present-day applications, fuzzy logic allows many kinds of designer and operator qualitative knowledge in electrical automation to be taken into account. Fuzzy logic began to interest the media at the beginning of the nineties. The numerous applications in electrical and electronic household appliances, particularly in Japan, were mainly responsible for such interest. Washing machines not requiring adjustment, camcorders with Steadyshot (TM) image stabilization and many other innovations brought the term “fuzzy logic” to the attention of a wide public.</p>

Desertification Detected in the Udhaim River Basin, Iraq Based on Spectral Indices Derived from Remote Sensing Images

In this study, changes in Land Use Land Cover (LULC) have been investigated over the Udhaim River Basin in Iraq by using spectral indices. NDVI, NDBI, NDWI, NDBaI, and CI represent respectively the vegetation, built-up, water bodies, bare-land, and soil crust of LULC. Two different images were acquired for the analysis, namely a Landsat 5 TM image from 1 July 2007 and a Landsat 8 OLI from 5 June 2015, both representing summer conditions. Results show that the percentages of vegetated land and water body areas have decreased. On the contrary, the percentages of built-up, bare land and soil crust areas have increased. The loss of vegetated areas and water body areas is a signal of land degradation leading to desertification, due to the combined effects of climate conditions, water deficit and human activities. Field observation shows that human activities have a significant impact on land degradation.