Articles | Volume 25, issue 10
https://doi.org/10.5194/nhess-25-3827-2025
https://doi.org/10.5194/nhess-25-3827-2025
Research article
 | 
08 Oct 2025
Research article |  | 08 Oct 2025

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

Manuel Titos, Carmen Benítez, Luca D'Auria, Milad Kowsari, and Jesús Miguel Ibáñez

Data sets

mmtitos/ML-DIGIVOLCAN: ML-DIGIVOLCAN V1.0.0 (v1.0.0) Manuel Marcelino Titos Luzon https://doi.org/10.5281/zenodo.17235276

Download
Short summary
Developing seismo-volcanic monitoring tools is crucial for volcanic observatories. Our study reviews current methods using transfer learning techniques and finds that while these systems identify nearly 90 % of seismic events, they miss other important volcanic data due to the catalog-learning bias. We propose a weakly supervised technique to reduce bias and uncover new volcanic information. This method can improve existing databases and efficiently create new ones using machine learning.
Share
Altmetrics
Final-revised paper
Preprint