Browsing by Author "Singh, Kaveer"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Open Access
    Geospatial Analysis of Informal Settlement Development in Cape Town
    (2023) Fisher, Toufeeq; Singh, Kaveer
    A significant factor in the growth of cities is the development of informal settlements. Informal settlements are associated with negative socio-economic factors such as unemployment and a lack of secure land tenure. Over one billion people live in such settlements all around the world, and consequently, informal settlers are exposed to the effects of negative socio- economic factors. This research focuses on understanding how informal settlements develop within the City of Cape Town using spatial metrics. By understanding the development, informed steps can be taken to improve the quality-of-life informal dwellers are exposed to. The development of three informal settlements was monitored: Imizamo Yethu, Langa and Siqalo. Initially, machine learning techniques were used to determine the current development, complexity, and compactness of informal housing within settlements. High-resolution imagery was used to classify shacks in the targeted informal settlements. An accuracy assessment was conducted to validate any subsequent analysis that was completed from classified imagery. The overall accuracies ranged between 88-96%. Thereafter, change detection analysis would be used to understand how each informal settlement developed and would be compared to each other. Using the combination of change detection, linear regression, and ordinary least squares analysis across the selected informal settlements, results from this study showed that the major development characteristic was the densification of shacks. This densification followed along major formal and external transport routes, as well as informal and internal transport networks. Densification was also heavily driven by open space. There were also individual and unique internal development dynamics in each informal settlement. These were driven by slopes, employment opportunities, and neighbouring income areas. The most statistically significant factor that influenced development across all the informal settlements was open space. This was determined through ordinary least squares.
  • Thumbnail Image
    Item
    Open Access
    Integrating a web-based GIS in the optimization of the customer connection process for utility company: A case of Kenya Power; Lighting Company, Ltd.
    (2021) Munywoki, Margaret Ngeli; Singh, Kaveer
    Great strides have been made world over in the use of GIS as a tool for the management of resources and decision making in the utilities. Utilities are now integrating GIS with other company systems in a bid to reduce operational costs, maximize revenue as well as improve efficiency and care to customers. However, this use has been confined to ensuring optimised service delivery to existing customers and overlooks new prospective customers. With privatization and deregulations, utility companies are now faced with a new challenge to strive for the market share in the most efficient and cost-effective ways. This research sought to develop a complementary web-based GIS application that can be integrated with existing utility company systems to improve efficiency in the new customer connection process. Waterfall System Development Methodology (SDM) was adopted in this research. Its simplicity and straightforwardness gave it a niche over other SDMs in-terms of implementation as one only moved to the next stage once the previous stage had been fully completed and tested. Digital online map, counties information data, enquiry for supply forms as well as the supply contract forms were used as the main datasets in the study. The objectives of this research were achieved by the development of a geodatabase to record, store and retrieve customer information; and a web-based GIS application to facilitate recording and upload of this information. It is possible to develop a web based GIS application that can be integrated with existing company's systems. Through integration, the system will automate and augment most of the manual processes in the new connection work-flow. This development would greatly improve new customer connection efficiency, maximize revenue collection for the utility and elevate the customers' socio-economic statuses. The system would also provide a platform for the monitoring and analysis of the infrastructure development geared towards the achievement of Kenya's Vision 2030.
  • Thumbnail Image
    Item
    Open Access
    Remote sensing for detecting rapid post-fire recovery as Groundwater-Dependent Ecosystems in the Cape Floristic Region
    (2021) Chenge, Simcelile; Smit, Julian; West, Adam G; Singh, Kaveer
    Groundwater Dependent Ecosystems (GDEs) concentrate high levels of biodiversity and several species not found anywhere else. They prevail in the landscape through the ecological contribution of groundwater. They, GDEs, are vulnerable to drastic changes in groundwater depth. If, for example, bulk groundwater pumping drastically increases the groundwater depth and GDEs can no longer access it, they would die out. In the Cape Floristic Region (CFR), South Africa, there is limited information about the spatial distribution of groundwater dependent ecosystems. With the CFR having multiple locations with current and subsequent bulk groundwater pumping, identifying the spatial distribution of GDEs is a prerequisite for establishing their groundwater requirements. This dissertation presents a proposed novel method to identify rapid recovering wetlands predicted to be GDEs and uses Random Forest (RF) to predict their spatial distribution. The proposed novel approach leveraged the periodic fire disturbances in the CFR and applied the remote sensing index; Normalised Difference Vegetation Index (NDVI) extracted from high spatial resolution (1 m) aerial orthoimages. The proposed novel approach involves three levels of analysis. The first two levels used a one-way Analysis of Variance (ANOVA) to analyse the sensitivity of mean NDVI to discriminate wetland and non-wetland classes in burned and unburned study sites, and a post-hoc test: Tukey's Honest Significant Differences (HSD) pair-wise comparison to detect differences between the wetland and non-wetland mean NDVI and infer an NDVI threshold of wetland classes. In unburned sites, ANOVAshowed no statistical significance between wetland and non-wetland classes, F (2,15) = 3.53, p = 0.055. In burned sites, however, ANOVA showed there was a significant difference between wetland and non-wetland classes, F (2,15) = 9.66, p = 0.002. ANOVA and Tukey showed there were significant differences betweenwetland and non-wetland classes, with wetlands having between 0.22 and 0.37 greater NDVI than non-wetlands. The last level of analysis employed a kernel density estimator function to assess the recovery rate post-burn and use it to detect faster recovery as potential of wetlands to be GDEs; results showed that potential wetland GDEs experience rapid NDVI recovery > 236 days post-fire. In the fire prone CFR, leveraging fire data to detect GDEs provides a potentially simple and efficient way of building a local database for GDEs. The proposed novel approach showed leveraging fire data is a simple alternative to laborious field data to identify and map GDEs in the CFR. But because of the finite spectral bands in aerial orthoimages, Sentinel-2A multi-epochs dataset was utilised to carry out random forest for predicting the spatial distribution of potential wetland GDEs in the Kogelberg Nature Reserve. Sentinel-2A bands: Short-Wave Infrared (SWIR), NearInfrared (NIR), Red-edge, Red, Green, NDVI and Normalised Difference Wetness Index (NDWI) predictors and the potential wetland GDEs/non-wetland classes as the response. I tuned RF using five-fold repeated spatial cross-validation instead of the typical cross-validation tuning to account for the spatial structure of the data. The overall predictive accuracy of RF was between 59%-71%. This predictive accuracy may have been reduced by the application of spatial cross-validation that accounted for the spatial autocorrelation in the multi-date data. The dissertation showed that Sentinel-2A multi-date data applies in predicting the distribution of potential wetland GDEs but might not be effective for smaller (< 100 m2) wetlands. These small wetlands showed rapid post-fire recovery (less than a year post-fire) and were effectively detected with high resolution aerial orthoimages (1 m) spatial resolution.
  • Thumbnail Image
    Item
    Open Access
    Understanding landscape dynamics using spatial metrics: A case of Maseru City Council (MCC), Lesotho
    (2018) Ramotubei, Pheello; Singh, Kaveer
    Remote sensing provides accurate and timely data for earth’s change detections for better decision making. Both land use and land covers (LULC) are important dynamics in understanding the dynamics interaction between human activities and the environment and the changes within the environment due to these interactions. Rapid population growth together with an irreversible process of urbanisation results in productive agricultural land which serves as the main source of livelihood under pressure for residential purposes. The reason being rapid urbanisation led to rapid increase of informal settlement in the developing countries and hence information about location and the extent of these informal settlements is needed to guide resources allocation distribution for upgrading and decision making processes. Thus a quantitative measure like the spatial metrics is used in this research to provide information on the rate and pattern of urban expansion for urban planners to device a mechanism for proper spatial planning and provide a management policy direction for solving complex problem of population growth and the encroachment of the informal settlements into fertile agricultural land along the urban peripheries emanating from internal and international migrations. The study indicates that there has been an increase of 928 Ha in the built up land between 2005 and 2016, while at the same time the agricultural has decreased by 820 Ha at the expense of the built up land. This indicates that in 11 years, percentage decrease of 0.35% in agricultural land is lost for built up land annually. In the similar manner, around the urban peripheries there is a loss of 3.4% of agricultural land (60.36 Ha) annually for informal settlement between 2005 and 2016 The spatial metrics which provide the quantitative description of composition and configuration of landscape shows that the urban peripheries are gradually being transformed from being simple compact to being more fragmented and complex as indicated by Area Weighted Mean Patch Fractal Dimension (AWMPFD) greater than one. This study indicates a need for immediate intervention through planned settlement to cater for an ever increasing population growth from natural birth and different types of migrations.