Monitoring and modelling settlement growth using object-based classification techniques: a case study of Pretoria north, South Africa

Simple item page
dc.contributor.authorOliphant, Thando
dc.date.accessioned2023-11-17T07:01:19Z
dc.date.available2023-11-17T07:01:19Z
dc.date.issued2022
dc.descriptionA dissertation submitted in fulfilment of the requirements for the degree of Master of Science in Geographical Information Systems and Remote Sensing to the Faculty of Science, University of the Witwatersrand, Johannesburg, 2022
dc.description.abstractAccurate and up-to-date maps of settlement distribution are critical for urban planning, monitoring, and management decisions. Remote sensing is useful for monitoring the dynamics of urban growth over large areas. Over the year’s urban built-up areas have rapidly increased in Pretoria North. Built-up layers for 1990 and 2017 were used to model settlement growth for 2025 using cellular automata (CA) incorporated with the artificial neural network (ANN) model within modules for land use change simulations (MOLUSCE) QGIS plugin. A rule-based classification object-based image analysis (OBIA) approach was used for extracting built-up and settlement types from highresolution SPOT multispectral imagery. A total of seven SPOT images for the period 1990 to 2017 with a five-year interval were used to assess and quantify built-up area growth. The results from the study indicated urban increases from 65.2 km2 in 1990 to 144.4 km2 in 2017. Post-classification change detection technique was used to quantify built-up area growth. The results from the study also showed a significant urban expansion of 44.34 km2 , which represents a 47.3% growth that occurred during the period between 1994 and 2000. The overall accuracies from images for years 1990 – 2017 ranged from 80% to 87%. Settlement growth was measured by examining changes in built-up areas over the years. The study showed an increase in formal and a decrease in informal areas during the period 2005 to 2017 as a result of housing upgrades. The projected results for 2025 revealed that built-up areas will increase in the coming years. It was found from the results that SPOT satellite imagery and OBIA are valuable for modelling urban growth. Information derived from the study can be used by decision makers for planning and management purposes.
dc.description.librarianPC(2023)
dc.facultyFaculty of Science
dc.identifier.urihttps://hdl.handle.net/10539/37024
dc.language.isoen
dc.schoolGeography, Archaeology and Environmental Sciences
dc.subjectObject-based image analysis (OBIA)
dc.subjectSPOT
dc.subjectSettlement
dc.titleMonitoring and modelling settlement growth using object-based classification techniques: a case study of Pretoria north, South Africa
dc.typeDissertation
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
1813964 Thando Oliphant Msc Research Report Final Submission October 2022.pdf
Size:
3.61 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.43 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
ETD Collection