OpenUCT is the open access institutional repository of the University of Cape Town (UCT). It preserves and makes UCT scholarly outputs digitally and freely available, including theses and dissertations, journal articles, book chapters, technical and research reports, as well as open educational resources.
Recent Submissions
Item
Open Access
Essays on water resources management in the agricultural sector of South Africa: the role of technology, policy and institutions in mitigating farm level water scarcity
(2024) Apio, Alfred Tunyire; Thiam Djiby, Thiam; Dinar, Ariel
South Africa is a water-stressed country prone to multi-year droughts and water shortages, with varying impacts on several sectors, including agriculture. Agriculture, as the largest user of the country's freshwater resources, is the most sensitive sector to water scarcity and would be the hardest hit by intensifying climate change, droughts, and water shortages. Yet the agricultural sector has the largest potential to make adjustments and take actions to promote resilience to water scarcity by implementing water conservation, water quality regulation, legitimate allocation, and an appropriate management response in the face of growing water scarcity. This thesis, therefore, provides an understanding of how the agricultural sector of South Africa is responding to the water scarcity problem. Its general objective is to further the stock of knowledge in natural resources management, with special emphasis on water resources management in the agricultural sector. It consists of three core chapters (chapters 2, 3, and 4), alongside the introduction (chapter 1) and conclusion (chapter 5). The first core chapter (Chapter 2) examines the factors that drive farmers' multiple adoption of six water conservation practices (WCPs) and the intensity of their adoption. Using survey data from 555 farmers in the Limpopo River Basin (LRB) of South Africa, a multivariate probit model is estimated to determine these factors, and for the intensity of their adoption, an ordered probit model is estimated. The results show that gender, age, education, and farm size, among other factors, influence the probability and extent of adoption of WCPs. Furthermore, combinations like drip and/or sprinkler irrigations and cover cropping, drip and/or sprinkler irrigations, and intercropping, among other practices, are complements, suggesting the bundling of these WCPs. This chapter provides a clear framework in agriculture not only to prepare farmers to be resilient in the midst of intensifying climate change, droughts, and water shortages but also to enhance their water conservation efforts. This would help farmers become better acclimatized to the growing realities of water scarcity and enhance the sustainability of the resource, enabling them to continue to make meaningful contributions to economic growth. The second core chapter (Chapter 3) employs a discrete choice methodology to investigate farmers' willingness to accept compensation to control agricultural nonpoint source (agNPS) pollution in the LRB. The LRB is highly polluted, yet it is important for agriculture, mining, and industry, which contribute to employment, income, and poverty alleviation. Reducing this pollution is part of the restoration and protection plan for the basin. However, because agNPS pollution does not easily lend itself to traditional forms of regulation, monetary incentives that induce farmers to adjust their farming practices to reduce agriculture's impact on water quality are seen as an effective means of controlling it, hence this chapter. Conditional logit and restricted latent class models are used to estimate the survey data of 552 farmers. This chapter identified one random choice class and three preference classes of farmers (low, moderate, and high resistance) with dissimilar compensation requirements to improve water quality. The chapter offers new insights to enrich the efficient design of tailored water quality improvementrelated agri-environmental schemes for more persistent environmental benefits that would ultimately result in positive externalities beyond benefits to farmers and the environment. The third core chapter (Chapter 4) presents a meta-analysis of the empirical literature that investigates the performance of water institutions. This chapter synthesized and quantified the overall water institution-performance effect using data extracted from 23 original studies that reported the effect of water institutions on the performance of the water sector in various regions of the world. The results from the bivariate and multivariate meta-regressions suggest the presence of a publication selection bias that favours a positive impact of water institutions on performance. Also, a genuine positive empirical effect of water institutions on the performance of the water sector is found. In addition, the variations in the primary studies are attributable to differences in the way the primary studies capture water institutions, the dependent variables used to capture performance, and the estimation strategy/methodology, among others. The main novelty of this chapter is its use of meta-analysis to increase the statistical power of this set of literature, which covers different methodologies, geographic and environmental conditions under which water institutions performed compared to single studies. This thesis concludes by underscoring forcefully that farmers need sustainable supplies of water but must also manage the impact of agriculture on water resources to ensure sufficient quantity and quality of water for production, but robust water management institutions are key. In terms of policy recommendations, this thesis offers several of them, including but not limited to the fact that WCPs are interdependent, and therefore, the design of any effective strategy(ies) aimed at increasing their uptake rate must take this interdependence into consideration. It also advocates the promotion and use of monetary incentives to induce farmers to lessen agriculture's impact on water quality. Finally, it recommends that to engender water sector reforms and/or for the further development, facilitation, and strengthening of water institutions, there is the need to incorporate and strengthen the water law and/or the water policy in policy formulation and reforms for successful water resource management and governance.
Item
Open Access
Development of scalable hybrid switching-based software-defined networking using reinforcement learning
(2024) Blose, Max; Akinyemi, Lateef Adesola; Nicolls, Frederick
As the global internet traffic continues to grow exponentially, there is a growing need for cutting-edge switching technologies to manage this growth. One of the most recent innovations is Software Defined Networking (SDN), which refers to the disintegration of the infrastructure layer and the logically centralized control layer. SDN is a cutting-edge networking approach that provides network agility, programming flexibility, and enhanced network performance over traditional switching networks. Even though SDN has some great benefits, there is a need to address and manage scalability challenges to guarantee optimal, scalable, and rapid data traffic switching within Service Provider network infrastructure, including Data Centres environments. These scalability issues are inherent to SDN's logically centralized control layer. Whenever a packet belonging to a new flow has to be transported, OpenFlow switch has to interact with the logically centralized SDN controller through southbound OpenFlow Application Programming Interface between OpenFlow switch and the logically centralized SDN controller. This results to an increase in communication overhead between the two instances. The control layer overhead traffic can impede scalability due to the controller's limited processing memory. There is therefore a strong incentive to enhance the scalability of SDN operations. To address the SDN scalability issues identified by creating a scalable hybrid switching solution using machine learning algorithms. We propose an SDN OpenFlow model switch which collaborate with the traditional switch to represent a scalable framework of Hybrid Routing with Reinforcement Learning (sHRRL). We implement a reinforcement algorithm to randomly explore new routes and discover the most optimal path through the Q-learning algorithm. This primitive and model-free form of reinforcement learning utilizes the Markov Decision Process and the Bellman's equation to reiteratively update Q-values in Q-table for every transition in the network environment state, until Q-function has converged to the best Q-Values. The greedy strategy is employed to guide the reinforcement learning agent in selecting the most suitable Q-values from the Q-Table. To ensure that the machine learning algorithm is able to discover a sufficient amount of possible routes and has a sufficient understanding of the network environment, sufficient training and evaluation episodes should be conducted. The proposed hybrid switching methodology was benchmarked against the standard SDN OpenFlow switch in terms of network performance metrics, including average throughput and packet exchange transmission rates, CPU load, and delay, to compare the two switching approaches. When statistically comparing the test results, it was observed that the number of packets exchanged by the hybrid switch was greater by more than sixty percent compared to the Open Flow switch which saturated first. The average throughput results demonstrate that the hybrid switching routing scheme achieves high throughput results. The first type of switch to reach saturation is the Open Flow switch, as it does not explore all available paths. Consequently, the hybrid switch is more efficient than the Open Flow Switch when it comes to CPU load. The average CPU load for the Open Flow switch is fifteen percent (15%) higher than for the hybrid Switch. Our analysis of the simulation data suggests that the Q-learning-based reinforcement learning framework, sHRRL, enhances the performance of the hybrid switch when compared to the Open Flow switches. We are therefore of the opinion that the hybrid switching model proposed utilizing machine learning algorithms can address the scalability issues in the design of SDN controller networks, particularly in data centre environments where high switching speeds are of paramount importance.
Item
Open Access
An analysis of the performance and interpretability of machine learning classification algorithms to predict long-term share returns on the JSE
(2024) Boakes, Jamie; Moodley, Deshendran
The prediction of long-term share returns is an essential yet complex task in financial analysis and formulating investment strategy. Machine learning is a promising approach for improving the accuracy of these predictions. However, the outputs of machine learning models are not transparent or interpretable, which limits their usability for real-world decision making. There is a lack of research on the use of machine learning algorithms to predict long-term share returns on the Johannesburg Stock Exchange (JSE), with no studies that specifically examine the interpretability of machine learning algorithms. This study investigates the use of machine learning algorithms to predict long-term share returns on the JSE based on fundamental data and analyses the interpretability of the top performing algorithms. Based on a review of the literature, eight machine learning classification algorithms were selected and compared to predict tercile class 12-month share returns using fundamental data, spanning a period of two decades. The XGBoost, Random Forest, and GradBoost algorithms were found to outperform the Support Vector Classifier, Logistic Regression, Decision Tree, Artificial Neural Network, and AdaBoost algorithms. XGBoost and Random Forest were further investigated using SHAP (SHapley Additive exPlanations) global summary plots to identify the most influential input features and to analyse the interpretability of these algorithms. The study found that ensemble-based classification algorithms, i.e. XGBoost, Random Forest and GradBoost, outperformed the other algorithms. Further analysis of the results varied, with some sectors outperforming the overall market. An analysis of the input features identified the most important valuation and profitability ratios that contributed to prediction performance, and thus improves the transparency and interpretability of the models. This research is the first to comprehensively compare and analyse the interpretability of machine learning algorithms to predict long-term share returns on the JSE.
Item
Open Access
The gas content of luminous compact blue galaxies in the COSMOS field
(2024) Arlow, Henco; Pisano, Daniel J; Bershady, Matthew
Luminous compact blue galaxies (LCBGs) are a heterogeneous subset of starburst galaxies. Their number density drops quite significantly as we approach lower redshifts. As a set of galaxies that evolve quickly, they make excellent candidates for studying galactic evolution as a whole. In order to understand how galaxies evolve, we make use of LCBGs to study their gas content as it changes over approximately nine billion years of lookback time. We make use of HI emission line data provided by the full CHILES survey, covering a redshift range of z=0 to z=0.45 within the COSMOS f ield as well as continuum data of the same field provided by the CHILES Continuum Polarization survey. In this thesis we set out to study the properties of LCBGs in these f ields to better understand the nature of these objects as they evolve to the present day. We report on direct detections of HI found in LCBGs in CHILES.Wealsoperform acubelet stacking technique on LCBGs for which we have known spectroscopic redshifts in CHILES. From these stacks we measure average HI masses as well as upper limit values for non-detections to study how it evolves with redshift. We also measure the star formation rates of a set of LCBGs using continuum fluxes in CHILES Con Pol and compare our results to measurements made with data from CHILES's first epoch. Continuum stacking is then performed in several redshift and stellar mass bins to extract average star formation rates. We proceed to fit appropriate functions to these relations in order to quantify the dependence of LCBG sSFRs to their stellar mass and redshift.
Item
Open Access
A complex, high-performance agent-based model used to explore tuberculosis and COVID-19 case-finding interventions
(2024) Low, Marcus; Kuttel, Michelle
Tuberculosis (TB) claimed an estimated 1.5 million lives in 2021 and the COVID-19 pandemic resulted in 14.9 million excess deaths in 2020 and 2021 combined. With both these infectious diseases substantial pathogen transmission takes place before people report to health facilities. Diagnosing more people more quickly and placing them on treatment and/or isolating them is thus critical to achieving epidemiological control. Early diagnosis interventions include contact tracing and isolation, testing of asymptomatic people thought to be at high risk of infection, and in the case of TB, screening using chest X-rays. The impact of several such early diagnosis interventions on case detection have been studied in clinical trials, but the longer-term impact of these interventions on infections (incidence) and deaths (mortality) is not known. There are also unanswered questions as to the impact hypothetical future TB tests, for example allowing for more frequent testing, may have on TB incidence and mortality. We developed an agent-based model (ABM) called ABM Spaces and used it to ask: (i) What is the impact of four different TB case-finding interventions on TB detection rates, incidence and mortality? (ii) What is the impact of test frequency and test sensitivity on tuberculosis incidence? And (iii) What is the impact of contact tracing and isolation and variable test turnaround times on COVID-19 diagnosis and mortality? Such agent-based modelling, in which disease transmission and progression is modelled at the level of discrete individuals, has increasingly been used in recent decades to model infectious disease interventions. Relatively few ABMs in the literature contain substantial social structure (for example associating agents with specific households, workplaces, and school classes). We illustrate that such ABMs with substantial social structure can be developed in a way that is epidemiologically sound and show that this type of ABM is well-suited to the modelling of social interventions such as contact tracing. In the ABM Spaces model we found that testing of people at considerable risk of TB has a greater impact on TB incidence and mortality than mass X-ray screening, that the impact of the two interventions is additive, and that the impact of annual testing of high TB risk individuals is highly sensitive to HIV prevalence. We found that the relationship between test frequency and TB mortality and incidence is non-linear, with an inflection point at around the four-month mark. The COVID-19 version of ABM Spaces confirmed the potential of contact tracing and isolation to reduce incidence and mortality, but the effect was highly sensitive to test turnaround times.