Search

To realize the first sustainable development goal of ending "poverty in all its forms everywhere," local governments in South Africa need to implement informed targeted policy interventions based on up‐to‐date data and sound analytics. Statistics South Africa (Stats SA) Censuses reveal the socioeconomic circumstances of people living in South Africa but are only conducted every 10 years. As a result, most analytical studies done in‐between Censuses rely on outdated socioeconomic data. This study demonstrates how poverty levels in one of the provinces of South Africa, Gauteng, can be predicted when up‐to‐date Census datasets are not available. The spatial lag model is used to explain the relationship between the South African Multidimensional Poverty Index (SAMPI) and statistically significant variables extracted from land use datasets (i.e., land areas classified as built‐up, informal, residential, township, and non‐urban), and to ultimately predict the levels of poverty. Out‐of‐sample predicted poverty levels obtained based on the spatial lag model correlate with the actual levels of poverty thereby reflecting known spatial patterns of the levels of poverty in Gauteng province. [ABSTRACT FROM AUTHOR]

The accessibility to basic facilities and services plays a pivotal role in every society and city planning. Spatial accessibility can vary between cities and countries and is mainly defined by the ease at which facilities can be accessed by communities. Facilities can provide essential services and/or products such as pharmacies, clinics, schools, universities, etc. Spatial accessibility is dependent on the spatial impedance between a facility and the target population and can be illustrated with catchment areas. We propose a fuzzy lattice catchment area method which uses a semi-supervised learning algorithm to create overlapping catchment areas. This methodology is applied to determine the accessibility to hospitals in South Africa and provides an illustration on the difference for regions with high accessibility compared to low accessibility. The application can easily be adapted in a variety of fields based on industry type, drive-time thresholds, supply capacity and the target population. [ABSTRACT FROM AUTHOR]

Accessibility analyses quantify the level of access to certain areas or opportunities, such as employment and healthcare facilities. Since public data is often aggregated at the level of regions, such as administrative units, it is useful to quantify accessibility between regions. Many factors influence inter-regional accessibility, most notably the accessibility metric used, and the way in which regions are chosen. This paper investigates the effects of road network structure on accessibility, using a previously developed inter-regional accessibility model that bases its accessibility metric on travel distance via the road network. This paper considers an area within the City of Tshwane municipality in South Africa. We investigate the effects of road structure in two ways. Firstly, regions are chosen based on the road network structure, which is done by extending a previously developed road network clustering algorithm for this novel use. Different spatial scales of regionalisation are considered, and the accessibility between these regions is compared to the accessibility between administrative units within the study area. Secondly, the effect of road network homogeneity on accessibility is investigated, where homogeneity corresponds to a uniform concentration of roads across a region. The results show that although road network homogeneity does not significantly correlate with accessibility, the way in which regions are chosen and their spatial scale has a strong effect on the results of the accessibility model. Our novel method of obtaining regions thus provides fresh insights into road-based accessibility within the City of Tshwane. [ABSTRACT FROM AUTHOR]

Big data poses challenges for storage, management, processing, analysis and visualisation. One technique of handling big data is the use of a representative sample of the data. This paper proposes a sampling algorithm which makes use of multivariate stratification with the aim of obtaining a sample that best represents the population while minimising the number of images in the sample. The proposed sampling algorithm performs effectively on a big spatial image dataset of crop types. The results are assessed by measuring the number of images sampled and as well as matching the proportionality of the population crop percentages. The samples obtained from the proposed algorithm are then used for land cover classification. An ensemble method called random forest is trained on the samples and accuracy is assessed. Precision, recall and F1-scores per crop type are computed as well as the overall accuracy. The random forest classifier performed best on the proposed sample with the least number of images. In addition, the classifier performed better on the proposed sample than it did on a random sample as the proposed sample due to the more informative data. This research develops an effective way of sampling big data for crop classification. [ABSTRACT FROM AUTHOR]

Hotspot detection in spatial analysis identifies geographic areas with elevated event rates, facilitating more effective policy interventions aimed at reducing such incidents. In the current literature, several methods have been used to detect hotspots such as measures for local spatial association and spatial scan methods. However, the performance of these methods is limited for small-scale hotspots as well as spatial domains where the number of areas is small. In this work, we propose a new approach, making use of the Discrete Pulse Transform (DPT) to decompose spatial lattice data along with the multiscale Ht-index and the spatial scan statistic as a measure of saliency on the extracted pulses to detect significant hotspots. The proposed method outperforms the well-used local Getis-Ord statistic in a simulation study, especially on small-scale hotspots. The method is also illustrated on South African COVID-19 cases and South African crime data. [ABSTRACT FROM AUTHOR]