EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CFM: a convolutional neural network for first-motion polarity classification of seismic records in volcanic and tectonic areas

Giovanni Messuti, Silvia Scarpetta, Ortensia Amoroso, Ferdinando Napolitano, Mariarosaria Falanga, Paolo Capuano

Frontiers in Earth Science · 20.07.2023 · 11

DOI: 10.3389/feart.2023.1223686 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Earth Science, online erschienen am 20.07.2023. Verfasst von Giovanni Messuti und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

First-motion polarity determination is essential for deriving volcanic and tectonic earthquakes’ focal mechanisms, which provide crucial information about fault structures and stress fields. Manual procedures for polarity determination are time-consuming and prone to human error, leading to inaccurate results. Automated algorithms can overcome these limitations, but accurately identifying first-motion polarity is challenging. In this study, we present the Convolutional First Motion (CFM) neural network, a label-noise robust strategy based on a Convolutional Neural Network, to automatically identify first-motion polarities of seismic records. CFM is trained on a large dataset of more than 140,000 waveforms and achieves a high accuracy of 97.4% and 96.3% on two independent test sets. We also demonstrate CFM’s ability to correct mislabeled waveforms in 92% of cases, even when they belong to the training set. Our findings highlight the effectiveness of deep learning approaches for first-motion polarity determination and suggest the potential for combining CFM with other deep learning techniques in volcano seismology.

Zitieren

APA

Messuti, G., Scarpetta, S., Amoroso, O., Napolitano, F., Falanga, M., & Capuano, P. (2023). CFM: a convolutional neural network for first-motion polarity classification of seismic records in volcanic and tectonic areas. Frontiers in Earth Science, 11. https://doi.org/10.3389/feart.2023.1223686

Vancouver

Messuti G, Scarpetta S, Amoroso O, Napolitano F, Falanga M, Capuano P. CFM: a convolutional neural network for first-motion polarity classification of seismic records in volcanic and tectonic areas. Frontiers in Earth Science. 2023;11. doi:10.3389/feart.2023.1223686

BibTeX
@article{Messuti2023,
  author = {Messuti, Giovanni and Scarpetta, Silvia and Amoroso, Ortensia and Napolitano, Ferdinando and Falanga, Mariarosaria and Capuano, Paolo},
  title = {CFM: a convolutional neural network for first-motion polarity classification of seismic records in volcanic and tectonic areas},
  journal = {Frontiers in Earth Science},
  year = {2023},
  volume = {11},
  doi = {10.3389/feart.2023.1223686}
}
Kostenlos starten →