FTFlavia Tavani

Flavia Tavani

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Flavia Tavani has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Deep Learning-based Workflow for the Automated Focal Mechanism Determination in Italy

    by Flavia Tavani, Pietro Artale Harris, Laura Scognamiglio, Men-Andrin Meier

    The determination of earthquake focal mechanisms is crucial for understanding tectonic processes and assessing seismic hazard. While traditional methods based on manual polarity picking have proven effective, they are time-consuming and potentially subject to analyst’s bias, particularly for small to moderate earthquakes. This study presents a machine learning-based approach for automating focal mechanism determination through P-wave polarity prediction. We develop and validate a methodology that combines a Convolutional Neural Network (CNN), based on the work by Ross et al. (2018) with the SKHASH algorithm (Skoumal et al. 2024), focusing on Italian earthquakes with magnitudes between 0 and 4.0, spanning the country's major active tectonic settings. The CNN, trained on a subset of the INSTANCE catalog by Michelini et al. (2021) containing over 450,000 Italian seismic waveforms, achieves 96% accuracy in polarity classification. To ensure the reliability of prediction, we implement stringent probability thresholds and validate our approach using a test dataset of 240,335 waveforms from 15,420 events. We then apply the methodology to 300 earthquakes with existing Time Domain Moment Tensor (TDMT) solutions finding a median Kagan angle (Kagan, 1991) between our FM and the TDMT solutions of 28.7°. This automated approach proves to be effective and may, in the future, offer a reliable means of determining focal mechanisms for lower magnitude events, where moment tensor inversions might not be feasible. This would contribute to a better understanding of regional seismotectonics and enhance seismic monitoring capabilities.

  • Open Access

    Source Characterization via Deep Learning: Integrating Polarity Prediction and Focal Mechanism Estimation

    by Flavia Tavani, Laura Scognamiglio, Pietro Artale Harris, Men-Andrin Meier

    In modern seismology, the rapid and accurate characterization of seismic sources following an earthquake is a fundamental task. Most observatories currently compute moment tensor solutions for events exceeding specific magnitude thresholds to ensure reliability. For instance, the National Institute of Geophysics and Volcanology (INGV) provides routine solutions for moderate to large events (Mw≥3.5) using established methods (Scognamiglio et al., 2009). However, characterizing smaller events remains challenging due to low signal-to-noise ratios and the need of modeling high-frequency waveforms that requires detailed knowledge of the velocity model, which is rarely available.Machine learning (ML) techniques have emerged as powerful tools to address these limitations, particularly in improving the prediction of first-arrival seismic wave polarities. These ML-derived polarities can be effectively integrated into traditional frameworks to compute robust focal mechanisms. In this study, we implement a workflow that bridges deep learning polarity predictions with standard focal mechanism estimation techniques, focusing on the tectonic setting of the Italian Peninsula.Our methodology consists of two primary stages. First, we trained a Convolutional Neural Network (CNN) for polarity prediction using the INSTANCE catalog (Michelini et al., 2021), which provides the high-quality, manually reviewed data essential for supervised learning. Second, we validated the model’s performance by analyzing approximately 4,700 earthquakes that occurred in Italy between January 1 2021, and January 1 2025, with magnitudes below 4.5.To benchmark our results, we selected a subset of earthquakes with existing Time Domain Moment Tensor (TDMT) solutions (Scognamiglio et al., 2006). Using the polarities predicted by the CNN, we computed focal mechanisms using the SKHASH code (Skoumal et al., 2024). The accuracy of these solutions was then evaluated against the TDMT catalog using Kagan angle analysis (Kagan, 1991) to quantify the rotation between double-couple sources.

  • Open Access

    Earthquake modelling via Brownian motions on networks

    by Fausto Colantoni, Mirko D'Ovidio, Flavia Tavani

    We provide a general model for Brownian motions on metric graphs with interactions. In a general setting, for (sticky) Brownian propagations on edges, our model provides a characterization of lifetimes and holding times on vertices in terms of (jumping) Brownian accumulation of energy associated with that vertices. Propagation and accumulation are given by drifted Brownian motions subjected to non-local (also dynamic) boundary conditions. As the continuous (sticky) process approaches a vertex, then the right-continuous process has a restart (resetting), it jumps randomly away from the zero-level of energy. According with this new energy, the continuous process can start (or not) as a new process in a randomly chosen edge. We provide a self-contained presentation with a detailed construction of the model. The model well extends to a higher order of interactions, here we provide a simple case and focus on the analysis of earthquakes. Earthquakes are notoriously difficult to study. They build up over long periods and release energy in seconds. Our goal is to introduce a new model, useful in many contexts and in particular in the difficult attempt to manage seismic risks.

  • Open Access

    SeismicNoiseAnalyzer: A Deep-Learning Tool for Automatic Quality Control of Seismic Stations

    by Alessandro Pignatelli, Paolo Casale, Veronica Vignoli, Flavia Tavani

    SeismicNoiseAnalyzer 1.0 is a software tool designed to automatically assess the quality of seismic stations through the classification of spectral diagrams. By leveraging convolutional neural networks trained on expert-labeled data, the software emulates human visual inspection of probability density function (PDF) plots. It supports both individual image analysis and batch processing from compressed archives, providing detailed reports that summarize station health. Two classification networks are available: a binary model that distinguishes between working and malfunctioning stations and a ternary model that introduces an intermediate “doubtful” category to capture ambiguous cases. The system demonstrates high agreement with expert evaluations and enables efficient instrumentation control across large seismic networks. Its intuitive graphical interface and automated workflow make it a valuable tool for routine monitoring and data validation.


  • Open Access

    Detecting communities and complex network features of the Italian earthquake catalog

    by Flavia Tavani, Ilaria Spassiani

    We represent an earthquake catalog as a complex network, where each node corresponds to a seismic event, and the links between nodes represent their distances in the space-time-energy domain. This approach, commonly known as the nearest-neighbor (NN) method, was introduced by Baiesi and Paczuski in 2004 to analyze the Californian earthquake catalog. Unlike the traditional fixed window-based techniques, which group into a cluster all the events within a predefined space-time domain centered at a selected mainshock, the nearest-neighbor method offers greater flexibility and precision. In fact, the resulting weighted network is able to capture extensive information about the space-time seismicity of a given region.In our study, we use network theory to analyze the Italian earthquake catalog from 2010 to 2020, compiled by the National Institute of Geophysics and Volcanology (INGV). Specifically, we first apply the NN method to derive the seismic Italian structure as a weighted network. Then, we focus our analysis on its topological properties to detect communities, that are groups of nodes more tightly interconnected with each other than with the rest of the network.To achieve this, we use the Louvain and Leiden algorithms: they are based on the maximization of modularity, a metric that quantifies the strength of a network’s division into modules (also referred to as communities or clusters). For implementation, we rely on IT tools new to seismology, but largely used in complex network analysis. Specifically, we use Radatools, an Ada library designed for analyzing complex networks, alongside the NetworkX Python package, which facilitates the creation, manipulation, and study of network structures, dynamics, and functions.This approach enables us to identify communities in the Italian network, and to compare them with clusters derived using traditional window-based techniques commonly employed in the literature, such as the Gardner-Knopoff technique. By investigating these differences and similarities, we aim to provide a robust and comprehensive analysis of the Italian earthquake catalog, leveraging high-performance tools for studying complex seismic networks.


  • Open Access

    Toward a Polarity Focal Mechanism Estimation via Deep Learning for small to moderate Italian earthquakes

    by Flavia Tavani, Pietro Artale Harris, Laura Scognamiglio, Men-Andrin Meier

    One of the main tasks in seismology is the source characterization after an earthquake, in particular the estimate of the orientation of the fault on which an earthquake occurs and the direction of the slip. Currently, most seismological observatories compute moment tensor solutions for earthquakes above a certain magnitude threshold, but, for small to moderate earthquakes (i.e. aftershock sequences), or for large but close in time events, focal mechanism by first arrival polarities are often the only source information available (Sarao et al., 2021).Focal mechanisms are important to better define the activated faults, to help in understanding the seismotectonic process, to improve the predicted ground shakings for early warning, the tsunami alert and the seismic hazard assessment. For these purposes, it becomes essential to produce and disseminate an estimate of the earthquake source parameters even for small events. Recently, machine learning techniques have gained significant attention and usage in various fields, including seismology where these algorithms have emerged as powerful tools in providing new insight into the earthquakes data analysis such as the prediction of the seismic wave's first arrivals polarities which can be used to compute focal mechanisms.We present here a workflow developed to obtain earthquake focal mechanisms starting from the first p-wave polarities estimated through the method proposed by Ross et al (2018).Our procedure consists of two stages: in the first stage, we use a combination of the available INGV web services (Bono et al., 2021) and the ObsPy functions to download the earthquake hypocentral location. We recover the waveforms recorded by the stations in the 0 -120 km distance range, and we create an input file with the appropriate information required for the prediction of the polarities for each waveform. We then use the convolutional neural network (CNN) proposed in Ross et al (2018) to obtain the polarities for each waveform, which can be UP, DOWN, or UNKNOWN. The second stage of the developed procedure aims to use the polarities that have been predicted to determine the focal mechanisms of the selected earthquakes. To do this, we use a modern Python implementation of HASH code (originally proposed in Fortran by Hardebeck et al. 2002, 2003) called SKASH (Skoumal et al. submitted). Finally, we present an application of this procedure to the September 2023, Marradi (Central Italy), seismic sequence that has been characterized by a magnitude Mw 4.9 mainshock followed by over 70 aftershocks in the magnitude range 2 - 3.4. Here, we focused on the estimation of the focal mechanism for events down to M 2.0. The application of the presented workflow permits to gain useful information about the kinematics of the earthquakes in the sequence, obtaining thus a more precise characterization of the activated structures.