Support vector machine classification to detect land cover changes in Halabja City, Iraq

Halabja city in Iraq has faced drastic landscape change since the IraqIran war, especially when this city and the surrounding areas were attacked with chemical bombs in 1988. This paper illustrates the results of land use/cover change in Halabja obtained by using multi-temporal remotely sensed data from 1986 to 1990. The support vector machine supervised classification technique was used to extract information from satellite data, and post-classification change detection method was employed to detect and monitor land use/cover change. Derived land use/cover maps were further validated by using high resolution images derived from Google earth. The results from this research indicate that the overall accuracy of land cover maps generated from Landsat Thematic Mapper (TM) data were more than 89%. The urban areas and vegetation classes decreased approximately 58.7% to 40.7% between 1986 and 1990, while bare land increased 25.4%. Also, some changes in urban areas were detected that have already been identified as bombed areas particularly around the main roads of Halabja city.

[1]  J. Rogan,et al.  Remote sensing for mapping and monitoring land-cover and land-use change—an introduction , 2004 .

[2]  J. Rogan,et al.  Remote sensing technology for mapping and monitoring land-cover and land-use change , 2004 .

[3]  Peter M. Atkinson,et al.  Predicting missing field boundaries to increase per-field classification accuracy , 2004 .

[4]  J. Mas.  Monitoring land-cover changes: A comparison of change detection techniques , 1999 .

[5]  Ashbindu Singh,et al.  Review Article Digital change detection techniques using remotely-sensed data , 1989 .

[6]  Gabriele Moser,et al.  Unsupervised change-detection methods for remote-sensing images , 2002 .

[7]  K. Dewidar,et al.  Detection of land use/land cover changes for the northern part of the Nile delta (Burullus region), Egypt , 2004 .

[8]  K. Green,et al.  Using remote sensing to detect and monitor land-cover and land-use change , 1994 .

[9]  C. Woodcock,et al.  Classification and Change Detection Using Landsat TM Data: When and How to Correct Atmospheric Effects? , 2001 .

[10]  M. Bauer,et al.  Digital change detection in forest ecosystems with remote sensing imagery , 1996 .

[11]  Mostafa Ghanei,et al.  Long-term pulmonary complications of chemical warfare agent exposure in Iraqi Kurdish civilians , 2010, Inhalation toxicology.

[12]  Philip J. Howarth,et al.  Procedures for change detection using Landsat digital data , 1981 .

[13]  D. Lu,et al.  Change detection techniques , 2004 .

[14]  H. Alphan.  Land‐use change and urbanization of Adana, Turkey , 2003 .

[15]  Alexander Siegmund,et al.  Automatic land cover analysis for Tenerife by supervised classification using remotely sensed data , 2003 .

[16]  R. Tateishi,et al.  Evaluating urban expansion and land use change in Shijiazhuang, China, by using GIS and remote sensing , 2006 .

[17]  Marta R Prescott,et al.  The Long-Term Psychosocial Impact of a Surprise Chemical Weapons Attack on Civilians in Halabja, Iraqi Kurdistan , 2008, Journal of Nervous and Mental Disease.