Browsing by Author "Hawkesford, Malcom J."

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Computer vision methods for the analysis of multimodal and multidimensional data for high-throughput plant phenotyping
    (Cranfield University, 2023-12) Okyere, Frank Gyan; Mohareb, Fady R.; Hawkesford, Malcom J.; Simms, Daniel M.
    Drought and nutrient stresses substantially impact crop productivity, frequently resulting in lower yields and financial losses to farmers. Early detection and tracking of these stresses are significant for improving agricultural yield and achieving the world food challenge goals. Advanced image technologies such as the use of conventional cameras and imaging spectroscopy combined with computer vision methodolgoies are being leveraged for non-invasive plant phenotyping to improve crop productivity, resilience, and sustainability. This thesis seeks to combine these technologies with machine learning algorithms to develop automated phenotyping pipelines to phenotype plants at different growth stages, particularly; for nutrient and drought stress identification and quantification. With this proposal, the onset of plant nutrient and drought stresses could be detected early and at different growth stages of the plants. Three experiments (two in the glasshouse and one in the field) were conducted, and images were acquired using digital RGB and a hyperspectral camera. The first experiment (nutrient stress) was performed in the glasshouse, the second (nutrient stress) on the field and the third (drought stress) in the glasshouse. The glasshouse nutrient experiment was performed on quinoa and cowpea plants made of four treatments: high nitrogen high phosphorus (HNHP), high nitrogen low phosphorus (HNLP), low nitrogen low phosphorus (LNHP) and low nitrogen low phosphorus (LNLP). The field nutrient experiment was performed on wheat plants made of 12 Olsen phosphorus varitions (approximately 3, 6, 9, 12, 15, 18, 21, 25, 30, 40, 50 and 60 ppm). The third experiment is a wheat drought analysis under variable nitrogen at selected plant growth stages. The treatments include: well-watered high- nitrogen (WWHN), well-watered low-nitrogen (WWLN), drought-stress high-nitrogen (DSHN) and drought-stress low-nitrogen (DSLN). Several image processing and machine learning techniques were employed to pre-process, post-process, and analyze plant- specific traits for tracking plant drought and nutrient stresses. Specifically, using digital imaging, a new segmentation algorithm invariant to illumination and complex background scenes was proposed to segment field and glasshouse-based images. Statistical and machine learning methods were employed to identify phenotypic traits sensitive to nutrient (nitrogen and phosphorus) deficiencies. Additionally, plant colour, morphology, and texture features were critically analyzed to assess their response to different stresses in plants. Using a hyperspectral imaging, a hybrid deep learning model was proposed to detect and track plant nitrogen and phosphorus deficiencies. In this case , the spatial and spectral characteristics of plants were analyzed, and deep learning algorithms were combined to understand their response to nutrient and drought stress in plants. Finally, using the spectral characteristics of plants, different conventional machine learning algorithms including Random Forest, Partial Least Square Regression and Support Vector Machines were developed to model the trends and patterns of plants for drought stress detection. The research results show a link between colour and nutrient stress, while texture and colour features were highly responsive to drought stress. The short-wave infrared region of the electromagnetic spectrum was highly responsive to plant phosphorus deficiency, while the blue, red, and near-infrared regions were highly connected to plant nitrogen deficiency. Furthermore, combining a proposed vegetation indices (VIs) from the VNIR regions of the spectrum with already known VIs resulted in the easy identification of plant drought stress compared to using only the known or proposed indices.
  • Thumbnail Image
    ItemOpen Access
    Phenotyping the nutritional status of crops using proximal and remote sensing techniques
    (Cranfield University, 2024-05) Cudjoe, Daniel Kingsley; Mohareb, Fady R.; Waine, Toby W.; Hawkesford, Malcom J.
    Understanding the nutritional needs of crops is crucial for ensuring their health and maximising yield. However, the capability to accurately measure relevant physical characteristics (phenotypes) of important crops in response to complex nutrient stresses is limited. For crop breeders and researchers, the existing capacity to characterise crops with adequate precision, detail and efficiency is hindering significant progress in crop development. In this PhD thesis, the use of advanced sensing techniques to assess the nutritional status of African crops was explored, focusing on three main objectives. First, the use of a handheld proximal sensor was investigated to evaluate the spectral properties of quinoa and cowpea crops grown under different N and P supplies in controlled glasshouse conditions (Chapter 3). By analysing these spectral properties, the aim was to identify spectral indices that could show early signs of N and P stress separately in the plants. These stress indicators were related to the overall performance of the crops. Spectral indices were found that could distinguish between N and P stress at the early growth stage of the crops. However, identifying spectral indices for P stress was limited, particularly in cowpea due to the shorter wavelength range of the handheld device. The results showed significant relationships between the spectral indices and traits related to the morphology, physiology and agronomy of the crops. Second, it was demonstrated that different levels of N impact the drought responses of spring wheat (Chapter 4). By evaluating morpho-physiological changes in the plants under high N and low N conditions, an understanding of how spectral reflectance measured at the leaf level could help distinguish between combined and complex stresses such as drought and nutrient deficiency was investigated. The results showed a greater amplitude of drought response in plants that were supplied with high N compared to low N levels, with interactive effects on many morphological and physiological traits. Out of a group of 39 different SRIs, only the Renormalised Difference Vegetation Index (RDVI) and the Red Difference Vegetation Index (rDVI_790) showed better accuracy in detecting drought stress. The results also revealed that indices sensitive to chlorophyll levels, such as the chlorophyll Index (mNDblue_730), Greenness Index (G) and Lichtenthaler Index (Lic2), as well as red-edge indices like Modified Red-Edge Simple Ratio (MRESR), chlorophyll Index Red-Edge (CIrededge) and Normalised Difference Red-Edge (NDRE), were more accurate in detecting N stress. Lastly, the effectiveness of using spectral information from images collected from a drone and spectral reflectance measured with proximal sensors on the ground were compared for detecting N stress in winter wheat under field conditions (Chapter 5). By comparing these two sensing methods, it was assessed which approach is more accurate, reliable and cost- effective for assessing the N nutritional needs of the crop in real-world agricultural settings. The results indicated that the NDVI measured on the ground at the leaf level could accurately detect the small changes in N levels earlier compared to the drone NDVI and canopy level NDVI and for assessing the agronomic performance of winter wheat. Overall, this PhD research sheds new light on the potential of advanced sensing techniques to improve crop management practices and enhance agricultural productivity by providing timely and accurate information about the nutritional status of the studied crops.