Grassland monitoring for precision management using UAV remote sensing
1/02/2016 - 31/01/2019 (collaboration between KU Leuven and ILVO; Irene Borra-Serrano has a scholarship from ILVO)
Promotors: Prof. Ben Somers (KU Leuven), dr. Peter Lootens (ILVO), Prof. Wouter Saeys (KU Leuven), dr. Koen Mertens (ILVO)
Irene Borra Serrano is a PhD student with a background in remote sensing applied to agriculture and forestry. UAV applications in agriculture are mainly focused on agricultural crops. Grasslands have received less attention despite their economic and ecological importance. There are clear opportunities for the application of this innovative technology to support decision-making of grass breeders and farmers. The potential of this close remote sensing system will be investigated. Frequent flights during the growing season will enable to monitor the growth and determine critical moments in management and the effect of variable treatments (e.g. optimum cutting time, local resowing or variable fertilisation). Visible and hyperspectral sensors will be used to determine the most suitable wavelengths for our purposes. The UAV-imagery will be captured under different weather (lighting) conditions (clear or cloudy skies). In each case, correlations will be established between the information derived from UAV imagery and information obtained using standard methods in breeding and grassland management. Finally procedures to apply this technology to breeding and grassland management will be developed.
Ruben Van De Vijver
Drone based detection and monitoring of potato diseases using hyperspectral and thermal imaging
1/11/2015 - 31/10/2019 (collaboration between KU Leuven and ILVO)
Promotors: Prof. Wouter Saeys (KU Leuven), dr. Koen Mertens (ILVO), Prof. Ben Somers (KU Leuven), dr. Peter Lootens (ILVO)
Ruben Van De Vijver is a PhD student with a specialization in disease detection in potato plants. Potato is one of the main crops in Belgium where economical loss is high due to diseases. Reducing the usage of crop protection products, the environmental sustainability of potato cultivation would be greatly improved. Hyperspectral imaging has been reported to have potential for fast and non-destructive detection of biotic and abiotic stress detection in plants. Drones may turn out to be a game changer as a carrier platform for hyperspectral and thermal sensors. The main objective of this project is therefore to develop a methodology to detect and map potato diseases in an early stage in the field. This will enable local treatment before major economic damage is done. In the project Ruben will focus on stress detection in plants from a close range (proximal sensing). Later differentiation between different diseases will be made. In order to perform proximal sensing a hypercart has been built carrying the hyperspectral, thermal and RGB (Red, Green, Blue) sensors. Later, these sensors will be mounted on a drone (remote platform) for remote sensing.
Hyperspectral detection and determination of troublesome agricultural weeds
1/06/2017 - 31/05/2023 (collaboration between UGent and ILVO)
Promotors: Prof. Jan Pieters (UGent), dr. David Nuyttens (ILVO)
Marlies Lauwers is assistant at the Biosystems engineering department of the faculty of Bioscience engineering, Ghent University. She will apply her experience in and knowledge of remote sensing and image processing to precision farming and in particular to weed management. Weeds can create major problems for farmers. If not properly managed, they reduce yields, cause infestations while toxic weeds might even end up in the food chain. The goal of her research is to detect and identify troublesome weeds with the use of hyperspectral techniques. Research has proven that multi- and hyperspectral sensors are able to distinguish between certain similar species. Site specific weed management leads to economic and environmental benefits as it is strongly linked to the quantity of herbicides that are applied. Weed identification can, in addition, aid in finding the proper management and, if necessary, the most appropriate herbicide type. In a first step, hyperspectral signatures of selected weeds will be collected with a spectrometer and investigated using different classification algorithms. On the one hand, weeds and their associated crops will be sampled with respect to site specific management. On the other hand, co-occurring weeds that are hard to distinguish based on their morphology will be identified and signatures compared. In a next stage, weeds will be detected using a hyperspectral camera.