Applying Machine Learning in GNSS Computing Cases: Precise Modelling and Predicting for Geodetic Coordinate Time Series and Vehicle Locations
Wenzong Gao · Queensland University of Technology · 2025
This research investigates the use of machine learning (ML) to address computational and modelling challenges in two key Global Navigation Satellite System (GNSS) applications. In the GNSS coordinate time series analysis, ML methods achieved over a 30% improvement in the positioning accuracy of GNSS station coordinates, reaching millimeter-level prediction precision. In the vehicle navigation scenario, where GNSS is integrated with inertial measurement units, ML techniques enhanced robust location prediction accuracy by fourfold during GNSS signal outages. These results underscore the potential of ML to address GNSS-related challenges, offering significant benefits for both scientific research and practical applications.