EVALUATION OF EFFECTIVENESS OF PATCH BASED IMAGE CLASSIFICATION TECHNIQUE USING HIGH RESOLUTION WORLDVIEW-2 IMAGE

The aim of the current study was to evaluate the performance of patch-based classification technique in land use/land cover classification and to investigate the effect of patch size in thematic map accuracy. To reach desired goal, recently proposed ensemble learning classifiers (i.e., XGBoost and CatBoost) were utilized to classify produced image patches obtained from high-resolution WorldView-2 (WV-2) satellite image. . In order to analyse the effect of varying patch size on classification accuracy, three different window sizes (i.e., 3 × 3, 7 × 7 and 11 × 11) were applied to WV-2 imagery for extracting image patches. Constructed image patches were classified using XGBoost and CatBoost ensemble learning classifiers and thematic maps were constructed for varying patch sizes. Results showed that while XGBoost and CatBoost showed similar classification performances for varying patch size and the estimated highest overall accuracy were %68, %82 and %92 for 11x11, 7 × 7 and 11 × 11 patch sizes, respectively. These findings confirmed that defining class boundaries on the high-resolution image using smaller patches increases the accuracy of thematic maps. In addition, results of patch-based classification were compared the results of LULC maps produced by same classifiers using pixel-based classification method. Overall accuracy of pixel-by-pixel classification of WV-2 image reached to about %94. Furthermore, CatBoost showed superior classification performance in all time compared to XGBoost. All in all, pixel-based CatBoost was found to be more successful in LULC mapping of fine resolution image.

Assessment of groundwater potential zones using GIS and AHP techniques: a case study of the Lafia district, Nasarawa State, Nigeria

In the Lafia district, rising population has increased the need for groundwater resources for economic growth. Sustainable groundwater resource management demands accurate quantitative assessment, which may be accomplished using scientific theories and innovative methods. In present study, an integrated method has been employed to assess the groundwater potential zones in the Lafia district utilizing remote sensing (RS), geographic information system (GIS), and analytic hierarchy method (AHP). For this aim, eight thematic maps regulating to occurrence and transportation of groundwater (i.e., geology, rainfall, geomorphology, slope, drainage density, soil, land use/land cover and lineament density) were generated and converted into raster format utilizing ArcGIS tool. Weights were assigned to these eight thematic maps based on their importance. Moreover, the final normalized weights of these parameters were calculated adopting pairwise comparison matrix of the AHP. To create the groundwater potential zones (GWPZs) map of the research area, we employed the overlay weighted sum approach to combine the parameters. The map has been divided into four zones (good, moderate, poor and very poor), each of which represents 19.3, 12.9, 57.8, and 10% of the study area. Lastly, the GWPZs map was validated utilizing borehole data obtained from 50 wells scattered throughout the study area to examine the performance of the approach. The validation results demonstrate that the adopted procedure produces highly reliable results that can aid in long-term development and strategic use of groundwater resources in this area.

Site Specific Nutrient Management Options for Achieving Higher Yields in Cotton and Chickpea under Rainfed Condition

A study was undertaken to delineation of spatial variability of soil fertility status in order to prepare soil available nutrient maps for improved productivity in different crops grown in the study area of Kurnool revenue division in Kurnool district of Andhra Pradesh state using remote sensing and GIS techniques. The Knowledge of spatial-variability is critical for site specific nutrient management in soil fertility to obtain higher yields. Soil sample (350) were collected from surface from 350 selected sites for preparing precise digital maps using point, line and polygon tools of the Geographic Information System (GIS) with ArcGIS software 10.3 was used for database creation and for creating the union of various thematic maps. The spatial variability maps were generated and delineated into different zones for N, P and K. Soil available Nitrogen, Phosphorus and Potassium spatial variability values generated from the thematic maps of Kurnool division were used to establish fertilizer recommendations for cotton in kharif and Chickpea in rabi during 2018-19 seasons. The recommended doses of Nitrogen (RDN) that worked for cotton were 401 to 450, 351 to 400, > 450 and < 350 kg ha-1 for the areas with Nitrogen availability of 140 to 210, 210 to 280, <140 and > 280 kg/ha, respectively. The Phosphorous fertilizer recommendation for soils with available P of < 30 kg/ha and > 30 kg/ha was figured out as > 250 kg ha-1 and < 250 kg ha-1, respectively. For soil available Potassium recorded 230 to 560, < 230 and > 560 kg/ha, the K recommendation was figured out as 301 to 400, > 401 and < 300 kg/ha, respectively. Recommended doses of Nitrogen (RDN) was worked out for chickpea were 51 to 75, > 76 and < 50 kg/ha for the areas with available N ranges of 184 to 280, < 184 and > 280 kg/ha, respectively. The Phosphatic fertilizer recommendation for soils of available P of < 23.5 and 23.5 to 40 kg/ha was figured out as > 200 kg/ha and 171 to 200 kg/ha, respectively. For the soil available potassium recorded 253 to 412, 413 to 570, < 253 and > 570 kg/ha, the K recommendation was figured out as 66 to 100, 31 to 65, > 100 and < 30 kg/ha, respectively.

Extending the cartographic capabilities of desktop GIS – Implementing less common statistical mapping methods as web services together with students

For various reasons statistical mapping is receiving increased interest within the technological shift towards service-oriented web cartography. At the same time new teaching approaches are required at universities which combine both, the motivating of students to get a grip on active programming while learning also about less common thematic mapping methods. The paper points to those cartographic representation methods of visualizing areal distributions of quantitative area characteristics which are often overlooked either due to not being readily available in GIS software or because they are simply not known. Of the nine methods discussed in regard to their abilities and limitations, five are not readily implemented or supported by the ArcGIS Pro software. Within the new teaching course on web processing services (WPS) as part of the International Geomatics master programme at Karlsruhe University of Applied Sciences, the students learn how to conceptualize, program and publish a WPS by gaining a solution for those less common methods. The alternate band map method serves as teaching example, but students are asked to independently work on other methods, too. The WPS course acts here as an eye-opener for the students to the wider pool of cartographic visualization options, of how to get around the limitations of GIS software, and of how to automate processes including making them available to others. With that we hope to contribute to automatically rendered thematic maps becoming more versatile again.

Mapping of Groundwater potential zones in Lingasugur Taluk in North-eastern part of Karnataka, India using Remote Sensing, GIS and multi-criteria data analysis

Groundwater research has evolved tremendously as presently it is the need of society. Remote Sensing (RS) and Geographical Information System (GIS) are the main methods in finding the potential zones for the groundwater. They help in assessing, exploring, monitoring and conserving groundwater resources. A case study was conducted to find the groundwater potential zones in Lingasugur taluk, Raichur District, Karnataka State, India. Ten thematic maps were prepared for the study area such as geology, hydrogeomorphology, land use/ land cover, soil type, NDVI, NDWI, slope map, lineament density, rainfall and drainage density. A weighted overlay superimposed method was used after converting all the thematic maps in raster format. Thus from analysis, the classes in groundwater potential were made as very good, moderate, poor and very poor zones covering an area of 10.1 sq.km., 169.25 sq.km., 1732.31 sq.km. and 53.66 sq.km. respectively. By taking the present study into consideration, the future plans for urbanization, recharge structures and groundwater exploration sites can be decided.

CEVİZ (Junglas regia L.) YETİŞTİRİCİLİĞİNDE CBS TEKNİKLERİ KULLANILARAK MEKÂNSAL KARAR DESTEK SİSTEMİ (MKDS) GELİŞTİRİLMESİNDE ÇATAK-VAN (TÜRKİYE) ÖRNEĞİ

This study was carried out to determine the areas where walnut (Junglas regia L.), which is grown in different ecological conditions of the world and Anatolia and provides significant added value to the economy of the region and the country, can be grown within the borders of Çatak (Van) district by using GIS. Within the scope of the study, certain data sets were created by taking into account the factors affecting the cultivation of walnuts, previous studies and expert opinions in determining the optimum areas where walnuts can grow in Çatak district. These data sets were combined with the necessary elements in the raster thematic maps and climatic vector maps (E00 maps with the e-high curve) and then they transferred into the database. All the obtained data were compared with each other by using GIS software and the areas where walnut could grow were determined. Due to the topographic structure of Çatak district, it has been concluded that walnut can be grown in valleys, slopes and floors where the altitude and slope are relatively low, but it will not be suitable for cultivation in mountainous areas. Thanks to this study, it will be used both in revealing the agricultural potential of different areas where walnut orchards can be established in Çatak (Van-Turkey) district and it will be also used in managing information based on locations.