Nico Lang: Global vegetation monitoring with probabilistic deep learning

Mapping forest structure on a global scale is an important component for understanding the Earth’s carbon cycle and conserving biodiversity. Several new space missions have been developed to support these goals by measuring forest structure to estimate biomass and carbon stocks. To analyze the vast amount of remote sensing data, efficient modelling approaches are needed that are robust to the inherent noise in these data. Data-driven approaches, especially modern deep learning methods, promise great potential for interpreting and combining data from different space missions to estimate vegetation parameters with enhanced spatial and temporal resolution.

This talk will present recent research results for global vegetation height mapping exploiting ESA’s Sentinel-2 optical imagery and NASA’s GEDI full waveform LIDAR. By integrating probabilistic deep learning approaches (i.e. deep ensembles), the predictive uncertainty of the models is quantified, which is crucial for downstream applications that depend on reliable estimates.

Nico is Postdoc at the University of Copenhagen associated with the Pioneer Centre for AI, where he is co-advised by Serge Belongie and Christian Igel. He received his PhD from ETH Zurich, where he was working in the EcoVision Lab that is part of the Photogrammetry and Remote Sensing (PRS) group under the supervision of Prof. Konrad Schindler and Prof. Jan Dirk Wegner. During his master’s degree in Geomatics at ETHZ he discovered his fascination for machine learning and computer vision in the context of geodata sciences.

Following on from work started during his earlier academic visit to Prof. Pietro Perona’s Computational Vision lab at Caltech, he has worked on deep learning approaches to monitor urban trees from street-level images. In his PhD, he developed an approach to compute a high-resolution canopy height model of the entire Earth by fusing optical satellite images with spaceborne LIDAR. His current research interests include quantifying the uncertainty in such estimates and learning from imbalanced data, which are ubiquitous challenges when working with real-world data.