Browsing by Author "Luvuno, Linda"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Climate-based regionalization and inclusion of spectral indices for enhancing transboundary land-use/cover classification using deep learning and machine learning
    (MDPI, 2021) Kavhu, Blessing; Mashimbye, Zama Eric; Luvuno, Linda
    Accurate land use and cover data are essential for effective land-use planning, hydrological modeling, and policy development. Since the Okavango Delta is a transboundary Ramsar site, managing natural resources within the Okavango Basin is undoubtedly a complex issue. It is often difficult to accurately map land use and cover using remote sensing in heterogeneous landscapes. This study investigates the combined value of climate-based regionalization and integration of spectral bands with spectral indices to enhance the accuracy of multi-temporal land use/cover classification using deep learning and machine learning approaches. Two experiments were set up, the first entailing the integration of spectral bands with spectral indices and the second involving the combined integration of spectral indices and climate-based regionalization based on Koppen–Geiger climate zones. Landsat 5 TM and Landsat 8 OLI images, machine learning classifiers (random forest and extreme gradient boosting), and deep learning (neural network and deep neural network) classifiers were used in this study. Supervised classification using a total of 5140 samples was conducted for the years 1996, 2004, 2013, and 2020. Average overall accuracy and Kappa coefficients were used to validate the results. The study found that the integration of spectral bands with indices improves the accuracy of land use/cover classification using machine learning and deep learning. Post-feature selection combinations yield higher accuracies in comparison to combinations of bands and indices. A combined integration of spectral indices with bands and climate-based regionalization did not significantly improve the accuracy of land use/cover classification consistently for all the classifiers (p < 0.05). However, post-feature selection combinations and climate-based regionalization significantly improved the accuracy for all classifiers investigated in this study. Findings of this study will improve the reliability of land use/cover monitoring in complex heterogeneous TDBs.
  • Thumbnail Image
    Item
    Understanding social-ecological regime shifts : the case of woody encroachment in South Africa
    (Stellenbosch : Stellenbosch University, 2019-04) Luvuno, Linda; Biggs, Reinette, 1979-; Esler, Karen J.; Stevens, Nicola; Stellenbosch University. Faculty of Agrisciences. Dept. of Conservation Ecology and Entomology.
    ENGLISH ABSTRACT: Humanity has been very successful in modifying the planet to meet the demands of a rapidly growing human population. As human activities have grown in magnitude, they have become increasingly interlinked with ecosystem dynamics, creating social-ecological systems (SES). Increased human impacts on ecosystems are also leading to an increased occurrence of regime shifts: large, persistent changes in the structure and function of ecosystems and SES that often have substantive impacts on the suite of ecosystem services provided by these systems, and on the well-being of people who live in them. As global changes accelerate, better understanding the drivers, impacts and risks of regime shifts has become a key need. This knowledge has important implications for the formulation of management strategies that aim to either maintain existing desirable regimes, restore previous regimes where a regime shift has occurred, or facilitate transformation to new regimes in the novel planetary conditions we face. A prevalent regime shift in savannas worldwide is woody encroachment. Woody encroachment is a shift from a grassy savanna to a persistently woody savanna, and has direct implications for a variety of ecosystem services such as livestock grazing, and people’s livelihoods that depend on these services. Much of the work on woody encroachment has focused on the direct drivers of the process, such as the role of fire or grazing in inhibiting or promoting encroachment. However, less is understood about how underlying social processes may impact these drivers, how ecological changes may feedback to affect some of these underlying social processes, how to monitor woody encroachment as a regime shift and how encroachment impacts ecosystem services and human well-being. This dissertation consists of four research chapters in journal format. The first is a synthesis of the ecological drivers and the social processes and drivers of woody encroachment based on the published literature, synthesized using causal loop diagrams and a published regime shift analysis framework. The remainder of the papers focus on woody encroachment in the Hlabisa district of South Africa. The second paper used Landsat TM imagery to quantify the extent of woody encroachment from 1990 to 2016 under contrasting land uses, specifically state-owned conservation land and communal land largely used for subsistence agriculture. The third paper builds on paper 2 and used spatial autocorrelation and the sequential t-tests analysis for regime shifts (STARS) to explore whether the changes observed in the remote sensing data conform to the statistical properties of a regime shift. The fourth paper used semi-structured interviews to investigate how different land users in the Hlabisa area (state conservation game reserve, private game reserves and local communities) are impacted by woody encroachment. Paper 1 provides a broader social-ecological understanding of woody encroachment. This review highlighted the link between increased human populations (locally and globally) and woody encroachment, and suggests key management options based on the key feedback loops identified. Paper 2 and 3 highlight the value of multi-temporal remote sensing data to monitor the extent of woody encroachment and collect time series data that could be used in the detection of regime shifts and early warning indicator of these shifts. Paper 2 found that Hlabisa experienced significant increases in tree cover between 1990 and 2016, under both the conservation and communal land uses, suggesting that the changes may be largely driven by global drivers rather than local land use practices. Paper 3 shows that these tree cover changes constituted a regime shift, confirmed through the results of STARS and spatial autocorrelation. This paper also suggests that these approaches offer a method that could be used to monitor woody encroachment regime shifts. Paper 4 reveals that all interviewed land users perceived woody encroachment to be increasing in the area. Community members and private game reserve managers mostly reported negative impacts of woody encroachment, with mixed reports from the state reserve managers. This paper also showed that private reserve managers are the most active in undertaking actions to counter encroachment. This research can inform policy and management practices. The dissertation emphasises the importance of understanding the social and ecological interactions that underlie woody encroachment, including the worldviews of land users and managers. With the looming impacts of global warming, and possible technological advances that can change how people live and view the systems in which they live, it is important for SES managers to adopt a complex adaptive systems approach that considers possible feedbacks, drivers at local to global scales, approaching system thresholds, livelihood impacts, as well as the potential for novel planetary conditions.
  • Thumbnail Image
    Item
    Woody encroachment as a social-ecological regime shift
    (MDPI, 2018-06-28) Luvuno, Linda; Biggs, Reinette, 1979-; Stevens, Nicola; Esler, Karen
    African savannas are increasingly affected by woody encroachment, an increase in the density of woody plants. Woody encroachment often occurs unexpectedly, is difficult to reverse, and has significant economic, cultural and ecological implications. The process of woody encroachment represents a so-called regime shift that results from feedback loops that link vegetation and variables such as fire, grazing and water availability. Much of the work on woody encroachment has focused on the direct drivers of the process, such as the role of fire or grazing in inhibiting or promoting encroachment. However, little work has been done on how ecological changes may provide feedback to affect some of the underlying social processes driving woody encroachment. In this paper, we build on the ecological literature on encroachment to present a qualitative systems analysis of woody encroachment as a social-ecological regime shift. Our analysis highlights the underlying indirect role of human population growth, and we distinguish the key social-ecological processes underlying woody encroachment in arid versus mesic African savannas. The analysis we present helps synthesize the impacts of encroachment, the drivers and feedbacks that play a key role and identify potential social and ecological leverage points to prevent or reverse the woody encroachment process.