An Artificial Intelligence-based platform for volcanic hazard monitoring

<p>Satellite remote sensing data are suitable to monitor global scale volcanic hazards in an efficient and timely manner. The development of monitoring systems which automatically collect and process satellite data is crucial during a volcanic crisis. The huge amount of multispectral satellite data available requires new approaches capable of processing them automatically and artificial intelligence (AI) addresses these needs. Machine learning, a type of AI in which computers learn from data, is gaining importance in volcanology. The combination of ML algorithms and satellite remote sensing in volcano monitoring has the potential of analyzing global data in near real-time for mapping and monitoring purposes. Here, an AI-based platform<strong> </strong>was developed to monitor in near real-time the volcanic activity from space. AI algorithms are used to retrieve information about the ongoing volcanic activity. Under this perspective, a key role is played by ML since it overcomes the issues related to hard coded/explicit rules by implicitly learning them from historical satellite data. Volcanic eruptions are then fully characterized in terms of their energy release, e.g. volcanic radiative power (VRP), effusive rate, quantification of the erupted products, i.e. volume, spatial extension, volcanic cloud composition. This task is achieved by combining a variety of freely available satellite datasets, i.e. infrared (IR) data with different spatial, temporal and spectral features.&#160; In particular, both a geostationary satellite sensor, i.e. SEVIRI (Spinning Enhanced Visible and InfraRed Imager, on board Meteosat satellites), and several mid-high spatial resolution polar satellite sensors, e.g. MODIS (Moderate Resolution Imaging Spectroradiometer, on board Terra and Aqua satellites), VIIRS (Visible Infrared Imaging Radiometer Suite, on board the Suomi-NPP and NOAA-20 satellites), SLSTR (Sea and Land Surface Temperature Radiometer, on board Sentinel-3A and Sentinel-3B satellites), MSI (MultiSpectral Instrument, on board Sentinel-2), are adopted. We demonstrate the potential of this web-based satellite-data-driven platform<strong> </strong>during the recent eruptive events on Stromboli and Etna.&#160;</p>