Multi-temporal Satellite Data for Land Use/Cover (LULC) Change Detection in Zakho, Kurdistan Region-Iraq
Historical and current status of the land is essential for efficient environmental management. This can especially be noticed in regions that are vitally affected by climate variability and human activities such as Zakho district, Kurdistan Region-Iraq. The information and status of land use/cover (LULC) help to design an efficient and sustainable environmental management program. The present study illustrates the spatiotemporal dynamics of LULC in Zakho district, Iraq. Landsat satellite imageries of two different time periods, i.e., Landsat Thematic Mapper (TM) of 1989 and Landsat Operational Land Imager (OLI) of 2017 were acquired and the changes in Zakho over a period of 28 years were quantified. Supervised classification methodology has been employed using Maximum Likelihood Algorithm. The images were categorized into eight different classes namely dense forest, sparse forest, grass, rock, soil, crop, built-up and water body. The results showed that during the last 28 years, build-up land had been increased from 9 km2 in 1989 to 49 km2 in 2017. Crops and rocks lands have been increased as well by about 102.1 and 15.39 km2, respectively. Moreover, a very slight increase has been observed in water body and soil by about 3.5 and 0.98 km2, respectively. On the other hand, dense forest, spare forest, and grass lands have been decreased by 92.83, 14.26, and 53.68 km2, respectively. This chapter concluded that a major change in Zakho district land happened in a negative trend regarding the natural environment.
Identification and mapping of tree species in urban areas using WorldView-2 imagery
Monitoring and mapping of urban trees are essential to provide urban forestry authorities with timely and consistent information. Modern techniques increasingly facilitate these tasks, but require the development of semi-automatic tree detection and classification methods. In this article, we propose an approach to delineate and map the crown of 15 tree species in the city of Duhok, Kurdistan Region of Iraq using WorldView-2 (WV-2) imagery. A tree crown object is identified first and is subsequently delineated as an image object (IO) using vegetation indices and texture measurements. Next, three classification methods: Maximum Likelihood, Neural Network, and Support Vector Machine were used to classify IOs using selected IO features. The best results are obtained with Support Vector Machine classification that gives the best map of urban tree species in Duhok. The overall accuracy was between 60.93% to 88.92% and κ-coefficient was between 0.57 to 0.75. We conclude that fifteen tree species were identified and mapped at a satisfactory accuracy in urban areas of this study.