MULTI-MODAL DEEP LEARNING WITH SENTINEL-3 OBSERVATIONS FOR THE DETECTION OF OCEANIC INTERNAL WAVES

Currently, global hydrological models do not benefit from observations of model output variables to reduce and quantify model output uncertainty. For the Mississippi River basin, we explored three approaches for using both streamflow and total water storage anomaly observations to adjust the parameter sets in a global hydrological model. We developed a method for considering the observation uncertainties to quantify the uncertainty of model output and provide recommendations.

The Greenland Ice Sheet represents the second-largest contributor to global sea-level rise. We quantify atmosphere, ice and ocean-based processes related to the mass balance of glaciers in Northeast Greenland, focusing on Greenland’s largest floating ice tongue, the 79N Glacier. We find that together, the different in situ and remote sensing observations and model simulations to reveal a consistent picture of a coupled atmosphere-ice sheet-ocean system, that has entered a phase of major change.

Shrinkage of the Antarctic ice sheet (AIS) leads to sea level rise. Satellite gravimetry measures AIS mass changes. We apply a new method that overcomes two limitations: low spatial resolution and large uncertainties due to the Earth's interior mass changes. To do so, we additionally include data from satellite altimetry and climate and firn modelling, which are evaluated in a globally consistent way with thoroughly characterized errors. The results are in better agreement with independent data.

Ozone is a toxic greenhouse gas with high spatial variability. We present a machine-learning-based ozone-mapping workflow generating a transparent and reliable product. Going beyond standard mapping methods, this work combines explainable machine learning with uncertainty assessment to increase the integrity of the produced map.

With the AQ-Bench dataset, we contribute to shared data usage and machine learning methods in the field of environmental science. The AQ-Bench dataset contains air quality data and metadata from more than 5500 air quality observation stations all over the world. The dataset offers a low-threshold entrance to machine learning on a real-world environmental dataset. AQ-Bench thus provides a blueprint for environmental benchmark datasets.