Extensional faults in Southern Calabria (Italy) have been widely studied for their capability to generate high magnitude earthquakes (Mw 7-7.2). An example is the 1783 historical seismic sequence, which caused numerous fatalities near the villages located along the largest fault structures of this region, the Cittanova fault and the Serre fault. In this paper, we estimated the seismic potential of these two faults by a kinematic block modeling approach using GNSS data of both campaign points and permanent stations available within this area. Our results indicate that both faults are accommodating extensional velocity gradient (~ 1 mm/yr), with long-term slip rates (~ 2 mm/yr). A 3D mesh of triangular dislocation elements (TDEs) was used to estimate the spatial variability of the back-slip on fault planes, the corresponding interseismic coupling degree and the resolution capability related to the data spreading. This approach has allowed us to distinguish the fault areas where elastic seismic rupture is more likely to happen from those affected by aseismic creeping behaviour. Using our interseismic coupling results, we estimated a set of possible rupture scenarios in Southern Calabria, as well as calculated the corresponding interseismic moment accumulation rate, comparing it to the coseismic moment release rate achieved by previous studies. Thus, we achieved that, the Southern Calabria domain is accumulating an interseimic moment rate at most equal to 1.09 ×1015 Nm/yr, the equivalent of an earthquake of Mw 4 for each year.

Volcanic eruptions are usually not easily predictable and this poses a significant hazard not only for exposures to the local population but due to possible presence of tephra also for airline traffic. The significant investments of the last years in new monitoring techniques and networks have improved our capabilities to sense volcano health, but the path to automatically recognize signs of potentially hazardous unrest is still long. On the other hand, machine learning is currently living a period of tumultuous growth and it is possible to find its applications practically in all the contexts where there is an overflow of data to be interpreted. Our aim is to exploit the capability of some established algorithms in machine learning to test their reliability in early detecting anomalous signals from the monitoring network before eruption events on Mt. Etna (Italy). In particular, we evaluate the effectiveness of using random forest approaches to learn from the measured signals the complex dynamics of the Etnean volcanic environment without any a-priori information on the data relationships. Such models are then tested against real eruptive cases to assess their performance.