Main content
Top content
Clara Lößl
PhD student
Coppenrath Innovation Centre
Hamburger Straße 24
LOK 15, Raum 01.16.03A
49084 Osnabrück
Tel.: +49 541 969-6341
Integrated AI analysis of geometric and spectral UAV data using machine learning to derive high-resolution bio-physical and bio-chemical plant properties in agroforestry systems
Agriculture, forestry and the food system play a major role in the global greenhouse gas (GHG) balance. This results in the need for adjustments to agricultural practice to meet the 2030 Climate Action Program while increasing resilience to weather extremes and other impacts of global warming. One approach for reducing GHG emissions and adopting agriculture to climate change are agroforestry systems, which are characterised by the spatial integration of trees (especially fruit, fast
growing or timber trees) and field crops.
The main objective of this PhD project is to develop and investigate suitable methods for monitoring and assessing biodiversity in agroforestry systems by combining high spatial resolution multispectral and LiDAR data from Unmanned Aerial Vehicles (UAV) systems. This should be done by an integrated AI analysis of geometric and spectral UAV data using machine learning to derive high-resolution bio-physical and bio-chemical plant properties in agroforestry systems. These parameters form the basis for a 3D modelling of biomass in arable and tree strips (yield/biomass/carbon monitoring). In addition, multi-temporal data (summer/winter) are combined in order to be able to integrate additional information from different tree conditions (leafy/non-leafy) for biomass modelling.
Finally, the analysis of the interaction of tree strips/landscape elements and arable crops, as well as the mapping of CO2 storage as a function of above-ground biomass and site factors must be of interest.
Project team: Clara Lößl (Ph.D. Student), Dr. Thomas Jarmer (UOS), Dr.-Ing. Ralf Pecenka (ATB)
GIL Tagung 2024
Find the digital version of the conference poster here: GIL 2024 POSTER
