GMLD: A TOOL TO INVESTIGATE AND DEMONSTRATE THE USE OF ML IN VARIOUS AREAS OF GNSS DOMAIN

This paper presents relevant results achieved during the NAVISP- EL1-035.02 project funded by the European Space Agency, which aimed to investigate the possible uses of Machine Learning (ML) based techniques for the processing of data in the field of Global Navigation Satellite Systems (GNSSs). For this purpose, we explored different kind of data present in the entire chain of the positioning process and different kind of ML approaches. In particular, this paper presents the system architecture and technologies adopted for developing the GNSS ML Demonstrator (GMLD), as well as the approaches and the results obtained for one of the most promising GNSS implemented applications, which is the prediction of daily maps of the ionosphere. Results show how, based on the historical data and the time correlation of the values, ML methods outperformed benchmark methods for the majority of the applications approached, improving the positioning performance at GNSS user level. Since the GMLD has been designed and implemented providing the general data management and ML capabilities as part of the framework, it can be easily reused to execute further investigation and implement new applications.