ALBERT

Description: The Global Navigation Satellite System (GNSS) is widely acknowledged for its ability to monitor ground deformation and provide guidance to assess associated hazards. However, noise in GNSS time-series can hide or even mask the actual ground deformation signals. Various denoising techniques have been developed to improve the signal-to-noise ratio and detect low amplitude signals. The Discrete Wavelet Transform (DWT) has proven to be one of the most effective techniques. However, the DWT requires extensive time-series data and it is therefore computationally expensive, making it unsuitable for real-time monitoring.In this research, we first assess the feasibility of using deep learning (DL) to perform the equivalent of wavelet analysis on GNSS data. Secondly, we explore the possibility of using DL to predict the future values of a wavelet-denoised GNSS time-series. The proposed method can be described as follows: i) wavelet analysis is applied to GNSS time-series coming from different sites in a permanent network; ii) a DL model is trained using the original time-series as input and the "Wavelet processed" series as target; iii) the trained model is used to perform real-time denoising on newly recorded GNSS data; iv) a separate model is trained to predict future values of the so-denoised GNSS data.We tested our approach on GNSS data collected in the Campi Flegrei area (Naples, Italy), an active volcanic caldera well-known for its ongoing deformation. The preliminary results are promising, as the models show good accuracy in both tasks: simulating past denoised signals and predicting future ones.

Description: Volcano ground deformations needs hardware and software tools of high complexity related to the processing of raw GNSS data, filtering of outliers and spikes and clear visualization of displacements occurring in real time. In this project we developed a web application for high rate real time signals visualization from permanent GNSS remote stations managed by INGV OE (Istituto Nazionale di Geofisica e Vulcanologia, Osservatorio Etneo). Currently the new software tool is able to import GNSS data processed by some of the most important high rate real time software like GeoRTD® (owned by Geodetics), GNSS Spider® (Owned by Leica Geosystems) and RTKlib. The tool is based on the Grafana open source platform and InfluxDB open source database. Various dashboards have been configured to display time series of the North-East-Up coordinates to monitor single stations, to compare signals coming from different data sources and to display the displacement vectors on the map. We also applied a simple alghoritm for the detection of abnormal variations due to impending volcanic activity. This web interface is applied to different active Italian volcanoes as Etna (Sicily), Stromboli (Aeolian Islands) and Phlegrean Fields (Naples). We tested the performance of this software using as a case study the 24th December 2018 dike intrusion on the Etna volcano.