Remote Sensing Data and SLEUTH Urban Growth Model: As Decision Support Tools for Urban Planning

Abstract

Sri Lanka is experiencing speedy urbanization by converting the agriculture land and other natural land cover into built-up land. The urban population of Sri Lanka is expected to reach to 60% by 2030 from 14% in 2010. The rapid growth in urban population and urban areas in Sri Lanka may cause serious socioeconomic disparities, if they are not handled properly. Thus, planners in Sri Lanka are in need of information about past and future urban growth patterns to plan a better and sustainable urban future for Sri Lanka. In this paper, we analyzed the characteristics of past land use and land cover trends in Matara City of Sri Lanka from 1980 to 2010 to assess the historic urban dynamics. The land use change detection analysis based on remote sensing datasets reveal that the conversion of homestead/garden and paddy into urban land is evident in Matara City. The historic urban trends are projected into the near future by using SLEUTH urban growth model to identify the hot spots of future urbanization and as well as the urban growth patterns in Matara City up to the basic administrative level, i.e., Grama Niladari Divisions (GND). The urban growth simulations for the year 2030 reveal that 29 GNDs out of 66 GNDs in Matara City will be totally converted into urban land. Whereas, 28 GNDs will have urban land cover from 75% to 99% by 2030. The urban growth simulations are further analyzed with respect to the proposed Matara city development plan by the Urban Development Authority (UDA) of Sri Lanka. The results show that the UDA's city development plan of Matara will soon be outpaced by rapid urbanization. Based on the calibration and validation results, the SLEUTH model proved to be a useful planning tool to understand the near future urbanization of Sri Lankan cities.

Urban growth sustainability of Islamabad, Pakistan, over the last 3 decades: a perspective based on object-based backdating change detection

“…Most studies used Maximum Likelihood Classifier (MLC) combined with post-classification change detection. With this method and moderateresolution data, Dewan and Yamaguchi (2009) studied the urban expansion of Dhaka, Bangladesh from 1975to 2003Jin-Song et al (2009) revealed newly added built-in area in Hangzhou, China, from 2001to 2003Faid and Abdulaziz (2012) explored land cover change pattern from 1998 to 2008 due to agricultural development and urban growth in Kom Ombo desert, Egypt; Hepcan et al (2013) studied the urban growth of Izmir, Turkey; Moghadam and Helbich (2013) established the relationship between the expansion of urban built-up area and the retreat of open land and cropland in Mumbai, India, from 1973Boori et al (2015) found the land cover change and corresponding population growth and decline in Samara, Russia, from 1972Russia, from to 2009Hassan et al (2016) showed that cropland, built-up areas and water bodies increased, and forest and bare land decreased in Islamabad from 1992 to 2012; Pourebrahim et al (2015) revealed land cover changes in Kuala Langat district, Malaysia, from 1988 to 2010 and predicted urban growth pattern in 2025; Morshed et al (2017) indicated that the sprawl of Dhaka City, Bangladesh, were relevant to the shrinking of natural vegetation, farmland and water body from 1989 to 2014; Fenta et al (2017) showed the relationship between the growth rate of built-up area and land cover type conversion in Mekelle, Ethiopia, from 1984 to 2014; Sandamali et al (2018) studied the urban land cover change in Kuala Langat district, Malaysia, from 1980 to 2010; Enoguanbhor et al (2019) found that the urban growth in Abuja, Nigeria, was at the cost of the reduction of vegetation area from 1987 to 2017. Besides, few studies tried new methods.…”

Urban Development Modeling Using Integrated Fuzzy Systems, Ordered Weighted Averaging (OWA), and Geospatial Techniques

“…In addition to these, other methods have been utilized to predict urban development and to assess urban spatial patterns, examples of which include the artificial neural networks [21,26], analytic hierarchy process (AHP) [27], SLEUTH model [28,29], spatial patterns analysis (SPA) [30,31], decision trees [21,32], Markov chains [33,34], Shannon's entropy [35][36][37], fuzzy systems [20], principal component analysis (PCA) [36,38,39], and logistic regression [34]. Thus, the main contribution of this study is the designing of a method to predict the development of bare grounds into built-up areas using the fuzzy concepts and ordered weighted averaging (OWA) methods, which have not been applied in the literature, and to compare the results of these methods.…”

Comparison of Urban Growth Modeling Using Deep Belief and Neural Network Based Cellular Automata Model—A Case Study of Chennai Metropolitan Area, Tamil Nadu, India

“…The study implemented the urban growth model with transportation data and highlighted the efficiency of SLEUTH model when other socioeconomic data with high temporal accuracy were not available. SLEUTH was used to predict the urban growth of Matara city, Sri Lanka [9]. It was found out that out of 66 Grama Niladari Divisions (GNDs), 29 GNDs would be urbanized in 2030.…”