Global Navigation Satellite Systems (GNSS) can sense deformations of the Earth’s crust. All components, but in particular the vertical component are affected by mass loading, i.e. external forces resulting from the redistribution and changes in fluid mass. These effects include non-tidal atmospheric loading (NTAL), non-tidal ocean loading (NTOL), and hydrological loading (HYDL). If these loading effects are not compensated in the processing of space geodetic data, the obtained results will be distorted. Thus, physics-based loading models exist that can be applied to correct station positions. This study investigates if machine learning (ML) in combination with environmental variables can replace or augment the existing physics-based models via a data-driven modelling of GNSS displacements. Therefore, vertical displacements of 3553 GNSS stations in Europe are utilized to train and validate XGBoost models. Three different strategies were tested, differing in the preprocessing of the GNSS data, i.e. whether or which physics-based loading models were applied beforehand. A significant improvement was achieved for all strategies ranging from 4.4% to 22.9%. The improvement is calculated based on the root mean squared error (RMSE) reduction of the GNSS residual coordinates w.r.t. a trajectory model, accounting for a linear trend, seasonal signals, and discontinuities in the GNSS coordinate time series. In addition to evaluating the ML models, a thorough feature importance analysis based on SHapley Additive exPlanations (SHAP) is carried out to better understand the driving factors of the model output and to gain insights into what signals could still be found to enhance existing physical models.

Rapid provision of Earth Orientation Parameters (EOPs, here polar motion and dUT1) is indispensable in many geodetic applications and also for spacecraft navigation. There are, however, discrepancies between the rapid EOPs and the final EOPs that have a higher latency, but the highest accuracy. To reduce these discrepancies, we focus on a data-driven approach, present a novel method named ResLearner, and use it in the context of deep ensemble learning. Furthermore, we introduce a geophysically-constrained approach for ResLearner. We show that the most important geophysical information to improve the rapid EOPs is the effective angular momentum functions of atmosphere, ocean, land hydrology, and sea level. In addition, semi-diurnal, diurnal, and long-period tides coupled with prograde and retrograde tidal excitations are important features. The influence of some climatic indices on the prediction accuracy of dUT1 is discussed and El Ni\~{n}o Southern Oscillation is found to be influential. We developed an operational framework, providing the improved EOPs on a daily basis with a prediction window of 63 days to fully cover the latency of final EOPs. We show that under the operational conditions and using the rapid EOPs of the International Earth Rotation and Reference Systems Service (IERS) we achieve improvements as high as 60\%, thus significantly reducing the differences between rapid and final EOPs. Furthermore, we discuss how the new final series IERS 20 C04 is preferred over 14 C04. Finally, we compare against EOP hindcast experiments of European Space Agency, on which ResLearner presents comparable improvements.

Global Navigation Satellite Systems (GNSS) have become a valuable tool for remote sensing, as signals can be used for monitoring soil and snow properties as well as water vapor in the atmosphere. By using L-band carrier frequencies, GNSS acts as an all-weather-operation system. Nevertheless, severe weather can still have an impact on the strength of signals received at a ground station, as we show in this study. We investigate Signal-to-Noise Ratio (SNR) from the Global Positioning System (GPS) during two thunderstorm events, which produced excessive amounts of rain and hail. We make use of a GPS-SNR-based algorithm, developed for the detection of hail particles from volcanic eruptions. Results indicate that the investigated thunderstorm events are visible in SNR observations. Affected satellites show a significant SNR drop during event periods, which are determined by weather radar observations. Thus, results suggest the possibility of detecting severe weather systems using GNSS-SNR observations.

Deep quantum learning is a relatively new concept in which quantum computing algorithms and/or devices are used to enhance the performance of deep learning approaches. Quantum technology originally requires quantum devices, also called quantum computers, which are specially designed computers with hardware parts built upon the concepts of quantum mechanics. Quantum devices are not widely available, but quantum algorithms are increasingly gaining more attention. These algorithms use theoretical considerations of quantum mechanics, including concepts of superposition, entanglement, and interference. Quantum algorithms have shown tremendous speedup and efficiency over traditional methods in many fundamental tasks such as prime factorization and list search. As a result of the power of quantum algorithms, they are used in deep learning approaches to increase their performance. The combined approach, which is normally called deep quantum learning, has shown competitive accuracy with respect to standard deep learning approaches. In order to take advantage of quantum algorithms for sequential data modelling, one needs to combine them with a suitable machine learning model, such as Long Short-Term Memory (LSTM) neural networks. In this study, we introduce quantum LSTM neural networks to time series prediction tasks in geodetic science. We present a special architecture consisting of three layers of LSTM, each having a quantum circuit with two qubits, and a final dense layer with a linear activation function. As an application, we focus on the ultra-short-term prediction of length of day based on geodetic and geophysical time series. We show that these networks can predict length of day better than the state-of-the-art statistical and machine learning methods, especially in the final days of the ten-day prediction window. In a test reflecting conditions of the EOP Prediction Comparison Campaign, the prediction accuracy was 0.024, 0.045, and 0.086 ms for the one-, five-, and ten-day-ahead predictions.