Browsing by Author "Hlatshwayo, Sizwe Thamsanqa."
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Informing reforestation practices : quantifying live forest above ground biomass of a randomly mixed natural forest plantation using GIS and remote sensing models.(2017) Hlatshwayo, Sizwe Thamsanqa.; Mutanga, Onisimo.; Lottering, Romano Trent.Restoration of natural forests is viewed as one of the effective and viable approaches for mitigating and adapting to climate change. However, maximising the carbon capture and storage of naturally mixed forest plantations is currently a challenge for forest managers, due to the complex nature of species interaction and environmental controls that inhibit the distribution and growth rates of certain species. Monitoring the amount of carbon captured and stored in natural forest ecosystem is vital in verifying their productivity and detecting areas of concern that could be unproductive. In this study the productivity of the Buffelsdraai reforestation site was monitored using above ground biomass (AGB) of planted trees. While there are traditional approaches for monitoring forest AGB with high accuracy, these approaches are unfavourable because they are timeous and spatially restricted. Fortunately, the inception of remote sensing has provided viable approaches for estimating forest AGB at a synoptic scale and with low cost. The purpose of this study was to apply remote sensing and GIS models to quantify the ecological benefits of the Buffelsdraai reforestation project on AGB productivity. The study investigated the potential of the spatially optimised three band texture combinations in predicting and mapping forest AGB and structural diversity. This research study has potential to contribute to the importance of spatial planning and design of naturally mixed forest plantations to improve their diversity and AGB productivity. The first part of the study focused on mapping the temporal and spatial distribution of forest AGB using spatially optimised three band texture combinations computed from SPOT-6 imagery and random forest regression algorithm. The results indicated that the three band texture combinations were superior in predicting forest AGB compared to raw texture bands and two band texture combinations. The second part of the thesis focussed on assessing the effects of forest structural diversity and topographic variables on forest AGB productivity using GIS and remotely sensed data. The forest structural diversity measures were predicted using three band texture combinations modelled using random forest and stochastic gradient boosting algorithms. The topographic variables were derived using the digital elevation model in ArcMap 10.3. Results indicated that random forest yielded overall higher accuracies in predicting the forest structural diversity measures compared to stochastic gradient boosting. More importantly, the study showed that forest diversity and topographic variables have significant influences on forest AGB variability. Overall the study provided insight into the management of natural forests and to the importance of spatial planning and design of these mixed forests.Item The use of machine learning algorithms to assess the impacts of droughts on commercial forests in KwaZulu-Natal, South Africa.(2020) Buthelezi, Mthokozisi Ndumiso Mzuzuwentokozo.; Lottering, Romano Trent.; Hlatshwayo, Sizwe Thamsanqa.Droughts are a non-selective natural disaster in that their occurrence can be in both high and low precipitation areas. However, this study acknowledged that droughts are more recurrent and a regular feature in arid and semi-arid climates such as that of Southern Africa. Some of these countries rely strongly on commercial forests for their gross domestic product (GDP), especially South Africa and Mozambique which means droughts pose a significant threat to their economy and the society that depends on this economy. The risks associated with droughts have consequently created an increased demand for an efficient method of analysing and investigating droughts and the impacts they impose on forest vegetation. Therefore, this study aimed to examine the effects of droughts on all commercial forests within the province of KwaZulu-Natal (KZN) at a catchment and provincial scale by employing Kernel Support Vector Machine (Kernel –SVM), Rotation Forests (RTF) and Extreme Gradient Boosting (XGBoost) algorithms. These were based on Landsat and MODIS derived vegetation and conditional drought indices. The main aim of this study was achieved by the following objectives: (i) to improve methods for classifying droughts; (ii) to achieve medium spatial resolution drought analysis using Landsat sensors; (iii) to determine the accuracy of machine learning algorithms (MLAs) when employed on remote sensing data and (iv) to improve the usability of conditional drought indices and vegetation indices. The results obtained there-after demonstrated that the objectives of this study were met. With the MLAs performing better when using conditional drought indices compared to vegetation indices, therefore, highlighting drawbacks already associated with vegetation indices. Where at the catchment scale, Kernel – support vector machine (SVM) produced an overall accuracy (OA) of 94.44% when based on conditional drought indices compared to 81.48% when based on vegetation indices. On the same scale, Rotation forests (RTF) produced 96.30% and 81.84% when using conditional drought indices and vegetation indices, respectively. At a provincial scale, RTF produced an OA of 76.6% and 70.7% when using conditional drought indices and vegetation indices respectively. This was compared to extreme gradient boosting (XGBoost) which produced an OA of 81.9% and 69.3% when using conditional drought indices and vegetation indices respectively. These results also indicate that it is possible to analyse droughts at provincial and catchment scale. Although the results presented in this study were promising, more research is still required to improve the applicability of MLAs in drought analysis.