A multi-scale modeling approach for simulating urbanization in a metropolitan region. (December 2015)

• Record Type: Journal Article
• Authors: Bhatti, Saad Saleem; Tripathi, Nitin Kumar; Nitivattananon, Vilas; Rana, Irfan Ahmad; Mozumder, Chitrini
• Is Part Of: Habitat international. Volume 50(2015)
• Page Start: 354
• Page End: 365
• Publication Date: 2015-12
• Subjects: Driving factors -- Land use/land cover change -- Multiple scenarios -- Neural network -- Peri-urban -- Urban growth modeling; Human settlements -- Periodicals; 307
• DOI: 10.1016/j.habitatint.2015.09.005
• Languages: English
• ISSNs: 0197-3975

Abstract

Abstract: Metropolitan regions worldwide are experiencing rapid urban growth and the planners often employ prediction models to forecast the future expansion for improving the land management policies and practices. These regions are a mix of urban, peri-urban and rural areas where each sector has its unique expansion properties. This study examines the differences in urban and peri-urban growth characteristics, and their impact at different stages of prediction modeling, in city district Lahore, Pakistan. The analysis of multi-temporal land use/land cover maps revealed that the associations between major land transitions and the factors governing land changes were unique at city district, urban and peri-urban scales. A multilayer perceptron neural network was employed for modeling urbanization, and it was found that the sub-models developed for urban and peri-urban subsets returned better accuracies than those produced at the city district scale. The prediction maps of 2021 and 2035 were also produced through this approach. Highlights: Land transitions and related driving factors vary within a metropolitan region. Metropolitan area and its urban/peri-urban subsets are modeled separately. Prediction accuracies rise by modeling urban and peri-urban areas independently. Analysis of multiple scenarios explains the growth dynamics of a region. Proposed approach improves growth modeling performance in a metropolitan area.