Skip to main content
Could seismo-volcanic catalogues be improved or created using weakly supervised approaches with pre-trained systems?

Could seismo-volcanic catalogues be improved or created using weakly supervised approaches with pre-trained systems?

This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint.

Add a Comment

You must log in to post a comment.


Comments

There are no comments or no comments have been made public for this article.

Downloads

Download Preprint

Authors

Manuel Marcelino Titos Luzón, María del Carmen Benítez Ortúzar, Luca D'Aria, Milad Kowsari, Jesús M. Ibáñez

Abstract

Real-time monitoring of volcano-seismic signals is complex. Typically, automatic systems are built by learning
from large seismic catalogs, where each instance has a label indicating its source mechanism. However, building complete
catalogs is difficult owing to the high cost of data-labelling. Current machine learning techniques have achieved great success
in constructing predictive monitoring tools; nevertheless, catalog-based learning can introduce bias into the system. Here,
we show that while monitoring systems trained on annotated data from seismic catalogs achieve performance of up to 90%5
in event recognition, other information describing volcanic behavior is not considered or either discarded. We found that
weakly supervised learning approaches have the remarkable capability of simultaneously identifying unannotated seismic
traces in the catalog and correcting misannotated seismic traces. When a system trained on a master dataset and catalog from
Deception Island Volcano (Antarctica) is used as a pseudo-labeller in other volcanic contexts, such as Popocatépetl (Mexico)
and Tajogaite (Canary Islands) volcanoes, within the framework of weakly supervised learning, it can uncover and update10
valuable information related to volcanic dynamics. Our results offer the potential for developing more sophisticated semi-
supervised models to increase the reliability of monitoring tools. For example, the use of more sophisticated pseudo-labelling
techniques involving data from several catalogs could be tested. Ultimately, there is potential to develop universal monitoring
tools able to consider unforeseen temporal changes in monitored signals at any volcano.

DOI

https://doi.org/10.31223/X50N0Z

Subjects

Engineering, Physical Sciences and Mathematics

Keywords

Volcano-seismic signals, Real-time monitoring, Weakly supervised learning, Pseudo-labelling, Seismic catalogs, Event recognition, Automatic monitoring systems, Data annotation, Volcanic dynamics, Cross-volcano generalization, Semi-supervised models, Machine learning.

Dates

Published: 2025-07-04 10:15

Last Updated: 2025-07-04 10:15

License

CC-BY Attribution-NonCommercial 4.0 International

Additional Metadata

Data Availability (Reason not available):
Correspondence and requests for materials should be addressed to corresponding author