The ISPRS SC Webinar Series
Deep ensembles for global vegetation analysis
Worldwide analyzes and estimates of vegetation parameters such as biomass or vegetation height are essential for modeling climate change and biodiversity. Traditional allometric approaches usually have to be adapted for specific ecosystems and regions. It is therefore very difficult to carry out homogeneous, global modeling with high spatial and temporal resolution and, at the same time, good accuracy. Data-driven approaches, especially modern deep learning methods, promise great potential here. In the lecture, current research results for the global determination of vegetation height will be presented, which are being developed in the EcoVision Lab integrating probabilistic approaches and deep learning (Deep ensembles)
