Doctoral Degrees (Industrial Engineering)

Permanent URI for this collection

https://scholar.sun.ac.za/handle/10019.1/775

Browse

Browsing Doctoral Degrees (Industrial Engineering) by Author "Cilliers, Pierre"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    A spatio-temporal framework for modelling informal settlement growth
    (Stellenbosch : Stellenbosch University, 2021-12) Cilliers, Pierre; Van Vuuren, Jan Harm; Van Heerden, Quintin; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Many developing countries grapple with the problem of rapid informal settlement emergence and expansion. This exacts considerable costs from neighbouring urban areas, largely as a result of environmental, sustainability and health-related problems associated with such settlements, which can threaten the local economy. Hence, there is a need to understand the nature of, and to be able to predict, informal settlement emergence locations as well as the rate and extent of such settlement expansion in developing countries. Although an abundance of research has been dedicated to developing computerised mathematical models for predicting future informal settlement expansion, there are no models in the literature for successfully predicting future informal settlement emergence and expansion which employ the considerable power of machine learning in a temporal setting. In this dissertation, a novel generic framework is proposed for machine learning-inspired prediction of future spatio-temporal informal settlement population growth. This data-driven framework comprises three functional components which facilitate informal settlement emergence and growth modelling within a user- specified area. The framework outputs are based on a computed set of influential spatial feature predictors pertaining to the area in question. The objective of the framework is ultimately to identify those spatial and other factors that in- fluence the location, formation and growth rate of an informal settlement most significantly, by applying a machine learning modelling approach to multiple data sets related to the households and spatial attributes associated with informal settlements. Based on the aforementioned influ- encing factors, a cellular automaton transition rule is developed, enabling the spatio-temporal modelling of the rate and extent of future formations and expansions of informal settlements. Furthermore, the framework facilitates a flexible, exploratory analysis of model results in com- bination with existing structured informal settlement expansion data in order to gain actionable insights into their management. Two separate instantiations of this framework are implemented on a personal computer as concept demonstrations. The first is applied to a real-world case study related to a densely populated informal settlement area of a South African municipality in order to illustrate the practical applicability of the proposed framework. The second implementation is aimed at comparing the model performance of the proposed framework with that of an existing model in the literature on the same real-world case study area.