The Chair of Space Geodesy faces the challenges and profits from the opportunities that come with “big data” in geodesy. We design and implement advanced machine learning techniques to automate the processing of GNSS and VLBI data, resulting in a faster availability and higher quality of geodetic products. Also, machine learning is applied in the large-scale analysis of GNSS time series to detect and investigate geophysical signals, inter alia related to hydrological and seismic events, as well as to severe weather events and ionospheric disturbances. Finally, we improve the predictions of several types of geodetic parameters by machine learning. In particular, we focus on determining future Earth orientation parameters, station coordinates and atmospheric parameters.
ETH researchers led by Professor Benedikt Soja, have succeeded in detecting heavy precipitation events directly with GPS data. The results of their study could significantly improve meteorological monitoring and forecasting.
In their recent publication in Nature Water, D-BAUG researchers Junyang Gou and Professor Benedikt Soja introduced a finely resolved model of terrestrial water storage using a novel deep learning approach. By integrating satellite observations with hydrological models, their method achieves remarkable accuracy even in smaller basins. This model promises significant benefits across various domains, including hydrology, climate science, sustainable water management, and hazard prediction.