How Smartphones can help to estimate ionospheric and tropospheric characteristics based on GNSS raw data

Last Updated: 19/12/2022 12:40     Created at: 15/12/2022 16:29

Final Presentation of NAVISP Project EL1 038 now available:

On Tuesday, December 13, 2022, Rina Consulting presented, together with its consortium partners  Politecnico di Milano,  Intelligentia Srl, and GReD Srl the results of the NAVISP project “CAMALIOT: Application of Machine Learning Technology for GNSS IOT Data Fusion”.

GNSS infrastructure has been growing significantly in recent years, in the space segment as well as on ground. Recent advances in technology have contributed to the deployment of a "de-facto" large GNSS receiver array based on affordable smart devices that are easy to find in the consumer market (dual band smartphones, raw GNSS data recording, new sensors). Millions of these Internet-of-things (IOT) devices feature an increasing number of capabilities and sensors able to collect a variety of measurements and provide improved GNSS performance. Due to the large number of devices, IOT data offer great potential for GNSS science exploitations, with unprecedented spatio-temporal resolution. This includes, for example, Galileo dual-band smartphone receivers and Android support for recording raw GNSS data, which is a major step forward in improving PNT data processing.  

Effective crowdsourcing of GNSS data is flourishing across different scientific disciplines including space weather, water vapour measurement or geo-hazard detection. Crowdsourced GNSS Big Data repositories provide a unique opportunity to apply innovative Machine Learning (ML) techniques to characterise multiple error sources, helping to identify singularities and correlations, particularly across the above GNSS-related disciplines.

The main objective of the activity was therefore to validate the application of ML, Big Data, and data mining techniques to vast data sets derived from various GNSS data sources. 

In this context, an innovative software infrastructure was developed that comprises an ingestion, processing, and analysis service that implements IoT components, as well as ML models, and pipelines. Through an online platform, users have direct access to GNSS science data from various IOT sources and can leverage ML potential for new product development. With a modular design, the platform architecture focuses on usability and flexibility for seamless development and deployment of Big Data and ML pipelines, as well as adaptability to future changes in the rapidly changing world of IOT.

Thus, with support from NAVISP, the project was able to collect and integrate GNSS data from ground based IoT sources as well as from space, going far beyond traditional GNSS data collection networks, and validate the use of these datasets through two use cases to characterize the ionosphere and troposphere. The feasibility of estimating ionospheric and tropospheric products starting from smartphone GNSS raw data was demonstrated with two experimental campaigns in Italy. Both types of products were validated against those derived from geodetic GNSS receivers, and, in the case of the ionospheric Total Electron Content (TEC), against state-of-the-art ionospheric maps. As a result, the project has improved ML data preparation, feature extraction, training and validation of GNSS crowdsourced data from IoT devices. At the end of the project, Rina Consulting and its consortium partners were able to demonstrate that the combination of IoT, Big Data and ML technologies in the GNSS domain can support new services and products for various application areas.

This activity was supported by NAVISP Element 1, which is dedicated to European industry technology innovation in the wide PNT sector.

More detailed information can be found in the slides of the Final Presentation.