Browsing by Author "Moncrieff, Glenn"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Open Access
    Automated quantification of plant water transport network failure using deep learning
    (2021) Naidoo, Tristan; Britz, Stefan; Moncrieff, Glenn
    Droughts, exacerbated by anthropogenic climate change, threaten plants through hydraulic failure. This hydraulic failure is caused by the formation of embolisms which block water flow in a plant's xylem conduits. By tracking these failures over time, vulnerability curves (VCs) can be created. The creation of these curves is laborious and time consuming. This study seeks to automate the creation of these curves. In particular, it seeks to automate the optical vulnerability (OV) method of determining hydraulic failure. To do this, embolisms need to be segmented across a sequence of images. Three fully convolutional models were considered for this task, namely U-Net, U-Net (ResNet34), and W-Net. The sample consisted of four unique leaves, each with its own sequence of images. Using these leaves, three experiments were conducted. They considered whether a leaf could generalise across samples from the same leaf, across different leaves of the same species, and across different species. The results were assessed on two levels; the first considered the results of the segmentation, and the second considered how well VCs could be constructed. Across the three experiments, the highest test precision-recall AUCs achieved were 81%, 45%, and 40%. W-Net performed the worst across the models, while U-Net and U-Net (ResNet-34) performed similarly to one another. VC reconstruction was assessed using two metrics. The first is Normalised Root Mean Square Error. The second is the difference in Ψ50 values between the true VC and the predicted VC, where Ψ50 is a physiological value of interest. This study found that the shape of the VCs could be reconstructed well if the model was able to recall a portion of embolisms across all images which had embolisms. Moreover, it found that some images may be more important than others due to a non-linear mapping between time and water potential. VC reconstruction was satisfactory, except for the third experiment. This study demonstrates that, in certain scenarios, automation of the OV method is attainable. To support the ubiquitous use and development of the work done in this study, a website was created to document the code base. In addition, this website contains instructions on how to interact with the code base. For more information please visit: https://plant-network-segmentation.readthedocs.io/.
  • Thumbnail Image
    Item
    Open Access
    Monitoring and mapping the critically endangered Clanwilliam cedar using aerial imagery and deep learning
    (2021) Hadebe, Blessings; Britz, Stefan; Moncrieff, Glenn
    The critically endangered Clanwilliam cedar, Widdringtonia wallichii, is an iconic tree species endemic to the Cederberg mountains in the Fynbos Biome. Consistent declines in its populations have been noted across its range primarily due to the impact of fire and climate change. Mapping the occurrences of this species over its range is key to the monitoring of surviving individuals and is important for the management of biodiversity in the region. Recent efforts have focused on the use of freely available Google EarthTM imagery to manually map the species across its global native distribution. This study advances this work by proposing an approach for automating the process of tree detection using deep-learning. The approach involves using sets of high-resolution red, green, blue (RGB) imagery to train artificial neural networks for the task of tree-crown detection. Additional models are trained on colour-infrared imagery, since live vegetation has a red tone on the near-infrared (NIR) spectrum. Preliminary results show that using an intersection-over-union threshold of 0.5 yields an average tree-crown recall of 0.67 with a precision of 0.53, and that the addition of the NIR spectral band does not result in improved performance. The viability of using this approach to regularly update maps of the Clanwilliam Cedar and monitor its population trends in the Cederberg is assessed.
  • Thumbnail Image
    Item
    Open Access
    The origins and maintenance of species boundaries in Jamesbrittenia O. Kuntze (Scrophulariaceae: Manuleae)
    (2007) Moncrieff, Glenn; Verboom, George Anthony
    The genus Jamesbrittenia contains 83 species distributed throughout southern Africa. Many species produce attractive flowers and consequently their horticultural potential is currently being explored. Speciation patterns and reproductive isolation were investigated in order to identify trends that may apply at broader scales. Bayesian phylogenetic analysis was performed using plastid (rps 16 and psbA-trnH) and nuclear (GScp) sequence data. Relative divergence times were calculated using a relaxed clock method. Prezygotic isolation, measured as seed set resulting from interspecific crosses, correlated with divergence time. However, recently diverged, highly sympatric taxa deviated from the overall trend. This provides circumstantial evidence for reinforcement of reproductive barriers. Floral dissimilarity and divergence time were found to be useful in predicting hybridization reported in the wild (p<0.0001). Species pairs susceptible to hybridization were identified on the basis of their floral dissimilarity and divergence time in order to prevent potentially hybridizing species from being brought into contact. The inability to detect the dominant mode of speciation confounded interpretation of the results, as it was not possible to determine if the influence of geographic patterns on the evolution of reproductive isolation was a result of the mode of speciation or post-speciation evolutionary changes.
  • Thumbnail Image
    Item
    Open Access
    Patterns and mechanisms of stem mortality in Acacia nigrescens induced by elephants and fire
    (2007) Moncrieff, Glenn; Midgley, Jeremy J; Kruger, Laurence M
    Increasing elephant populations have been implicated in the decline of woody vegetation throughout Africa. The problem is particularly relevant to the Kruger National Park in South Africa, where elephant populations have almost doubled in the last 10 years. One manner in which elephants utilize trees is by stripping their bark. The role of bark stripping in increasing stem vulnerability to fire and the mechanism through which fire damage is mediated were investigated by experimentally removing bark and burning Acacia nigrescens stems. Field surveys were conducted in order to investigate patterns of bark stripping in relation to mortality patterns of large trees occurring subsequent to natural fires. In the experimental study, an increasing probability of mortality was associated with increasing amount of bark removed when trees were burnt. However, when trees were stripped but not burnt, simulating damage to cambium and phloem, none died in the 4-month period over which the experiment ran. This was taken as evidence that fire-induced xylem damage causes stem mortality. However, fire did kill a greater proportion of the remaining stem cambium around the circumference when bark had been removed. The field surveys indicate that bark stripping by elephants is frequent on large stems (44%) and that larger trees are more heavily impacted. The only variable measured that explained mortality patterns well was the percent of bark removed around the stem circumference up to 3m (p = 0.0076). These results indicate that damage to xylem is important in determining post-fire survival and that bark stripping by elephants increases the vulnerability of stems to fire. This increased vulnerability is a result of both increased damage to cambium and damage to exposed xylem. The high proportion of trees stripped by elephants and the increase in vulnerability to mortality associated with bark stripping suggests that unless elephant population growth is curbed, large Acacia nigrescens trees will eventually be eliminated from this ecosystem.