The increase of available seismic data prompts the need for automatic processing procedures to fully exploit them. A good example is aftershock sequences recorded by temporary seismic networks, whose thorough analysis is challenging because of the high seismicity rate and station density. Here, we test the performance of two recent Deep Learning algorithms, the Generalized Phase Detection and Earthquake Transformer, for automatic seismic phases identification. We use data from the December 2019 Mugello basin (Northern Apennines, Italy) swarm, recorded on 13 permanent and nine temporary stations, applying these automatic procedures under different network configurations. As a benchmark, we use a catalog of 279 manually repicked earthquakes reported by the Italian National Seismic Network. Due to the ability of deep learning techniques to identify earthquakes under poor signal‐to‐noise‐ratio (SNR) conditions, we obtain: (a) a factor 3 increase in the number of locations with respect to INGV bulletin and (b) a factor 4 increase when stations from the temporary network are added. Comparison between deep learning and manually picked arrival times shows a mean difference of 0.02–0.04 s and a variance in the range 0.02–0.07 s. The improvement in magnitude completeness is ∼0.5 units. The deep learning algorithms were originally trained using data sets from different regions of the world: our results indicate that these can be successfully applied in our case, without any significant modification. Deep learning algorithms are efficient and accurate tools for data reprocessing in order to better understand the space‐time evolution of earthquake sequences.

The Mugello Basin (North-Eastern Tuscany) is an intermontane basin of the Northern Apennines (Italy) with a well-documented record of seismicity; the two major historical earthquakes occurred in 1542 (Mw = 6.0) and in 1919 (Mw = 6.4). In this study, we integrate different seismic catalogs spanning the 2005–2019 time interval, and complement these data with phase arrival times from a temporary network that specifically operated in the area throughout the 2019–2021 time interval. The subsequent relocation of this data set with a double-difference algorithm allows for accurate analyses of the most relevant seismic sequences which affected the study area in 2008, 2009, 2015–2017, and 2019. These sequences are associated with the activation of adjacent segments of larger NW-striking fault systems, one of which bounds the NE margin of the Mugello Basin (Ronta Fault System). For each seismic sequence, best-fit fault surfaces are derived from orthonormal regression of relocated hypocenters, yielding consistent results with that derived from fault plane solutions. The four sequences mark a significant increase in the seismicity rate with respect to what was recorded in the previous decades. This suggests that, following the 2008 renewal of seismicity, static or dynamic stress changes, or both depending on the case, played a role in advancing the time of failure of the fault segments activated subsequently.

<p>The Northern Apennines is a NW-SE striking fold-and-thrust belt composed of a pile of NE-verging tectonic units that developed during Cenozoic collision between the European plate (Corso–Sardinian block) and the Adria plate. Seismicity and geodetic data indicate that contemporaneous crustal shortening (in the external, Adriatic part) and extension (in the internal, Tyrrhenian side) characterize the current tectonic activity of the Apennines. The region around the Mugello basin (Northern Tuscany) represents one of the most important seismogenic areas of the Northern Apennines. Large historical earthquakes have occurred, such as the M=6.0, 1542 and the M=6.4, 1919 events. Its proximity to densely-urbanized areas and the potential impact of strong earthquakes on the cultural heritage in the nearby (~30km) city of Florence makes a better knowledge of the seismicity in the Mugello basin a target of paramount importance. Unresolved issues regard (i) the exact location and geometry of the fault(s) which produced the 1542 and 1919 earthquakes, (ii) the mechanism driving the abrupt transition from an extensional to compressional stress regime at the internal and external sides of the belt, respectively, and (iii) geometry of and role played by a close-by transfer zone oriented transversely (NE-SW) to the main strike of the belt. To address these problems, in early 2019 we initiated a project aiming at improving the knowledge about the seismo-tectonic setting of the basin and adjoining areas. At first, we integrated all the available seismic catalogs for the area, obtaining more than 12000 earthquakes spanning the 2005-2019 time interval. These data have been used to derive a minimum-misfit, 1-D velocity model to be subsequently used for a travel times inversion 3D tomography. At the same time, we Installed 9 temporary seismic stations, complementing the permanent networks presently operating in the area. This new deployment recorded a Mw=4.5 earthquake that struck the NW margin of the basin on Dec. 9, 2019. The mainshock and the ~200 aftershocks precisely delineate a 5-km-long, NW-striking and SW-dipping fault which extends over the 6-9 km depth interval. The focal mechanism of the mainshock yields consistent results, indicating a normal fault striking N105°E and dipping about 45°. This fault appears to be distinct from that (those) activated during the two last important sequences in the area, which occurred in 2008 and 2009. The earthquake caused unexpected, large accelerations (PGA~0.24g at ~7km epicentral range), provoking damages that resulted in the evacuation of more than 150 residents and economic losses of several millions of euro. Sample horizontal-to-vertical spectral ratios at the most damaged sites report significant amplification within the 1-5 Hz frequency range, likely responsible for the anomalous ground shaking. Given the proximity of the aforementioned fault to that inferred for the 1542 (and, possibly, 1919) earthquake(s), a detailed study of the 2019 seismic sequence is expected to shed new light into the overall dynamics of the basin.</p>