Determination of environmental degradation due to urbanization and industrialization in Gebze, Turkey

被引:28
作者
Kavzoglu, Taskin [1 ]
机构
[1] Gebze Inst Technol, Dept Geodet & Photogrammetr Engn, TR-41400 Gebze, Turkey
关键词
environmental degradation; change detection; urban growth; urbanization; industrialization; classification; remote sensing;
D O I
10.1089/ees.2006.0271
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Industrialization has been one of the major factors in the development of the countries, and has caused a population increase in cities, resulting in urban sprawl. Because industrialization and urbanization often advance in an uncontrolled or unorganized way in developing countries, they can have destructive effects on the environment, particularly on basic ecosystems, wildlife habitat, and global biodiversity. One of the places that has been subject to intense industrialization and resulting urbanization is the Gebze district of Kocaeli in Turkey. Land use and land cover changes that occurred in the region were investigated using satellite images acquired in 1987, 1997, and 2002. In the detection of changes postclassification comparison approach is employed using an artificial neural network classifier, specifically a multilayer perceptron with backpropagation learning algorithm. Results show some important findings regarding the size and nature of the change that occurred in the study area. In the despoiled areas, a large number of pixels of pasture and forest lands have been replaced by urban pixels; as a result, the total area of urban pixels doubled in the 15-year period with a higher urbanization rate between 1997 and 2002. A significant amount of forest land, about 38% for deciduous and 22% for coniferous forest, has been destroyed. In addition to the statistical estimates of the change, its spatial distribution was also investigated through a map of change that helps to determine the areas where considerable degradation and deforestation have taken place.
引用
收藏
页码:429 / 438
页数:10
相关论文
共 21 条
[2]   The influence of relative sample size in training artificial neural networks [J].
Blamire, PA .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1996, 17 (01) :223-230
[3]  
Bruzzone L, 1997, PHOTOGRAMM ENG REM S, V63, P523
[4]   A REVIEW OF ASSESSING THE ACCURACY OF CLASSIFICATIONS OF REMOTELY SENSED DATA [J].
CONGALTON, RG .
REMOTE SENSING OF ENVIRONMENT, 1991, 37 (01) :35-46
[5]   Comparison of maximum likelihood classification method with supervised artificial neural network algorithms for land use activities [J].
Erbek, FS ;
Özkan, C ;
Taberner, M .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2004, 25 (09) :1733-1748
[6]   USING PRIOR KNOWLEDGE IN ARTIFICIAL NEURAL-NETWORK CLASSIFICATION WITH A MINIMAL TRAINING SET [J].
FOODY, GM .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1995, 16 (02) :301-312
[7]  
HEPNER GF, 1990, PHOTOGRAMM ENG REM S, V56, P469
[8]   The spatiotemporal form of urban growth: measurement, analysis and modeling [J].
Herold, M ;
Goldstein, NC ;
Clarke, KC .
REMOTE SENSING OF ENVIRONMENT, 2003, 86 (03) :286-302
[9]  
IMURA H, 1999, P 1999 NIES WORKSH I, P227
[10]   The use of backpropagating artificial neural networks in land cover classification [J].
Kavzoglu, T ;
Mather, PM .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2003, 24 (23) :4907-4938