1st Istanbul International Geography Congress Proceedings Book
The forming of building density analysis maps from the Landsat-8 data with the use of machine learning algorithms: a case study of Adana cityEfdal Kaya, Fatih Adıgüzel, Mehmet Çetin, Tuğrul Avcı
In recent years, the increasing development of satellite technologies has played an important role in the development of remote sensing technologies. In particular, the development of high-resolution satellites that produce high-resolution spatial images and present spectral information to the public has provided significant convenience for obtaining spatial information. The decreasing prices of the satellite images and their presentation to the community have facilitated the implementation of many applications. In this study, a density map is created using Landsat-8 OLI data. To determine the usability of the density map, the data obtained from Landsat satellites are offered to users for free. The downloaded Landsat data were initially subjected to radiometric and geometric corrections. Then, the image is cut into different scenes based on the study area and data are classified using support vector machine, which is a machine learning algorithm. After classification, the building data were recorded in a polygon data structure. Each polygon in the structure was filled with dots and building density map was created using these point data.