Di Michele, Federica

The present work would like to illustrate a new concept of multiparametric stations to characterize the crustal fluids-tectonic interaction in specific geological contexts. The dynamics of crustal fluids in relation to tectonics is a complex and sometimes intricate issue. Several factors act and mutually influence themselves, so that in each tectonic and geological context they follow a specific behavior, and a comprehensive cause-effect rule is hard to find. Changes in water chemistry and levels and in soil flux regimes (e.g., CO2, CH4, radon) are just a few examples well documented in the literature as being pre-, co- and post-seismic modifications as well as being markers of the local tectonic stress acting in the crust. A regional study combined with a long-lasting multiparametric monitoring is needed to prepare to a seismic sequence in a given place. The field infrastructure was set up starting from the end of 2021, and multiparametric stations have been installed in correspondence of active seismogenic sources initially located in Northern Italy. Data are transmitted in real-time and archived in an ad hoc developed relational database. Monitoring is mainly focused on groundwater parameters (water level, temperature, and electrical conductivity) of aquifers showing distinct degrees of confinement and lithologies. Sites are also equipped of meteorological sensors (pressure, temperature, rain, humidity, wind speed and direction), radon sensors and surface and borehole seismic stations providing accelerometric and velocimetric data. A mud volcano field is also monitored and holds the installation of a permanent CO2 soil flux station. A statistical analysis working flow is also proposed for a preliminary evaluation of the acquired time-series. In particular, a couple of tools to detect, and thus filter, anthropogenic and meteorological effects on a groundwater level series is described. We wish to provide a model of approach to analogous study cases in other potentially seismic areas.

In this paper we present a case study where the Random Forest (RF) Classifier, has been used to estimate the damage to buildings caused by a (possible) future earthquake, starting from the data of past earthquakes. This prelaminar work is based on the Shakedado dataset, which contains information on buildings and ground shaking parameters for the six major earthquakes that occurred in Italy between 1981 and 2012. We perform the following two conceptual experiments E1: Assume that the sequence that hit Emilia has just ended and the data relating to the other major earthquakes happened in the past (L’Aquila, Pollino, and Irpinia) are available, then calculate the level of damage for each building in the Emila dataset. E2: Assume that the sequence that hit Pollino has just ended and the data relating to the other major earthquakes happened in the past (L’Aquila, Emilia) are available, then calculate the level of damage for each building in the Pollino dataset. Both training and test datasets contain only masonry buildings located within 10 km of the main shock of each sequence. The results show the RF algorithm’s ability to discriminate between buildings with light/no damage from those with medium/severe damage, with a good accuracy, especially for E1.