Modern seismic networks provide a huge amount of data received in real-time, being impossible the manual identification of relevant events useful to monitor the activity of the volcano. Thus, many volcano observatories are interested in tools to perform an online, automatic analysis of the seismic activity. Machine Learning area provides various of Volcano-Seismic Recognition (VSR) systems designed to classify seismic events in real-time. However, only a few approaches can also detect them in a continuous data streams. Most of those VSR systems are based on the 2-step supervised paradigm: 1. A training database (X-DB) of a given volcano ’X’ is prepared with hundreds of events manually detected and classified according to their physical origin. 2. Statistical models are built analysing this DB, and are later used to automatically identify events in new data recorded at the volcano X. This supervised procedure is the major drawback to achieve a fast deployment of a VSR system for another volcano Y, as the preparation of its own Y-DB takes considerable time, and requires qualified operators and previous recordings, which is difficult for volcanoes without recent activity or which haven’t been monitored. In order to overcome these limitations, the EU-funded project ’VULCAN.ears’ focused on real-time, Volcano-Independent VSR (VI.VSR) approaches. It proposes alternative solutions based on state-of-the-art technologies as universal DBs and models, waveform standardisation and parallel architectures. Recent results obtained by mixing DBs from Popocatépetl, Colima, Deception and Arenal active volcanoes will be presented. We apply VULCAN.ears technologies to evaluate VSR systems on joint DBs built with data of several volcanoes. We also use volcano-independent models to automatically classify events of another volcano, analysing how the recognition accuracy varies as the training DB becomes more complex. All tests are carried out by an easy to use, user-friendly graphical application (geoStudio). All these achievements produce new insights useful to redesign the next-generation, portable and robust VSR systems.

On the 22nd of May 2021, although no alarming precursory unrest had been reported, Nyiragongo volcano erupted and lava flows threatened about 1 million of inhabitants living in the cities of Goma (Democratic Republic of Congo) and Giseny (Rwanda). After January 1977 and January 2002, it was the beginning of the third historically known flank eruption of Nyiragongo volcano and the first ever to be recorded by dense measurements both on the ground and from space. In the following days, seismic and geodetic data as well as fracture mapping revealed the gradual southward propagation of a shallow dike from the Nyiragongo edifice underlying below Goma airport on May 23-24, then Goma and Gisenyi city centers on May 25-26 and finally below the northern part of Lake Kivu on May 27. Southward migration of the associated seismic swarm slowed down between May 27 and June 02. Micro seismicity became more diffuse, progressively activating transverse tectonic structures previously identified in the whole Lake Kivu basin. Here we exploit ground based and remote sensing data as well as inversion and physics-based models to fully characterize the dike sized, the dynamics of dike propagation and its arrest against a structural lineament known as the Nyabihu Fault. This work highlights the shallow origin of the dike, the segmented dike propagation controlled by the interaction with pre-existing fracture networks and the incremental crater collapse associated with drainage which led to the disappearance of the world’s largest long-living lava lake on top of Nyiragongo.