Research Articles (Agronomy)

Permanent URI for this collection

https://scholar.sun.ac.za/handle/10019.1/519

Browse

Browsing Research Articles (Agronomy) by Subject "Climatic changes"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Deep learning-enabled temperature simulation of a greenhouse tunnel.
    (IWACP, 2023-11) Jogunola, O.; Hull. K. J.; Mabitsela, Mosima Mamoyahabo; Phiri, E. E; Adebisi, B.; Booysen, M. J.
    ABSTRACT: Agriculture is poised to suffer greatly from the effects of climate change. Prediction models, using deep learning, have been developed that can simulate and predict conditions in open field farming to combat the climate variability from climate change. However, deep learning used in precision agriculture, specifically greenhouse tunnels, is under-researched despite also being affected by this variability. Utilising tunnel data collected over 42 days, two hybrid deep learning models were designed. Specifically, a hybrid of convolutional neural network (CNN) and Long Short-Term Memory (LSTM), and a hybrid of CNN and Bidirectional LSTM (BLSTM). The models are designed to forecast the internal temperature of the tunnel to support its management. The cooling wet wall state, solar irradiance, inside and outside temperature of the tunnel are input variables to the developed deep-learning models. Two scenarios are discussed with the results, the first scenario includes all the external variables as input, while the second scenario only considers the internal temperature as input. Results show a performance improvement of 48% and 14% computation time for the CNN-LSTM compared to the CNN-BLSTM model for the two scenarios, respectively. In terms of the measured loss metrics, both models had varied performance and model fitness, with an average mean square error of 0.025 across the models and scenarios.
  • Thumbnail Image
    Item
    Genetic evidence for plural introduction pathways of the invasive weed Paterson’s curse (Echium plantagineum L.) to southern Australia
    (Public Library of Science, 2019-09-19) Zhu, Xiaocheng; Gopurenko, David; Serrano, Miguel; Spencer, Mark A.; Pieterse, Petrus J.; Skoneczny, Dominik; Lepschi, Brendan J.; Reigosa, Manuel J.; Gurr, Geoff M.; Callaway, Ragan M.; Weston, Leslie A.
    Paterson’s curse (Echium plantagineum L. (Boraginaceae)), is an herbaceous annual native to Western Europe and northwest Africa. It has been recorded in Australia since the 1800’s and is now a major weed in pastures and rangelands, but its introduction history is poorly understood. An understanding of its invasion pathway and subsequent genetic structure is critical to the successful introduction of biological control agents and for provision of informed decisions for plant biosecurity efforts. We sampled E. plantagineum in its native (Iberian Peninsula), non-native (UK) and invaded ranges (Australia and South Africa) and analysed three chloroplast gene regions. Considerable genetic diversity was found among E. plantagineum in Australia, suggesting a complex introduction history. Fourteen haplotypes were identified globally, 10 of which were co-present in Australia and South Africa, indicating South Africa as an important source population, likely through contamination of traded goods or livestock. Haplotype 4 was most abundant in Australia (43%), and in historical and contemporary UK populations (80%), but scarce elsewhere (< 17%), suggesting that ornamental and/or other introductions from genetically impoverished UK sources were also important. Collectively, genetic evidence and historical records indicate E. plantagineum in southern Australia exists as an admixture that is likely derived from introduced source populations in both the UK and South Africa.