Abstract

Sustainable land use and development require timely, accurate and detailed information of land resources as well as changes in the land resource. 'What is changing in where' question is answered by multiple observations over a period of time. Remote sensing technology provides such a monitoring requirement. The aim of this study was to analyze land use/ land cover (LU/LC) changes between 1975 and 2000 in GümüÅŸhane, Turkey, using satellite images. Three Landsat images from 1975, 1987 and 2000 were used to determine changes. A post classification technique was used based on a hybrid classification approach (unsupervised and supervised). Images were classified into five LU/LC types; urban, agriculture, forest, pasture and other lands. It is found that significant changes in land cover occurred between the years 1975 and 2000. The results showed an increase in urban, forest and agriculture and a decrease in pasture and other lands between 1975 and 2000. In this period, urban land increased from 1.25 to 3.78% of the total area. While the area of pasture decreased from 26.74 to 23.44% of the total area, the area of forest and agriculture increased from 37.32 to 39.51% and from 8.83 to 13.27%, respectively.

Key words: Image classification, change detection, remote sensing, land use/land cover.