Volcanic eruption forecasting using Signal Processing and ML techniques on seismic signals
From 01 / 06 / 2020 to 31 / 05 / 2023
The main objective of this project is to provide reliable tools for the early forecasting of volcanic eruptions by developing an innovative analysis of seismic-volcanic signals using Machine Learning techniques.
FEMALE will establish a new, universally applicable, exportable, simple, and useful methodology for forecasting volcanic eruptions using continuous and labeled seismic-volcanic signals.
This novel methodology, which compares eruptive and non-eruptive cases, is essential for obtaining a reliable statistical basis for forecasting future eruptions.
— Ángel Gerardo Alguacil de la Blanca
— Francisco Javier Carrillo Rosúa
— María Mercedes Vázquez Vílchez
— Sonia Mota Fernández
Responsible
Jesús Miguel Ibáñez Godoy
Goal
To establish a new suite of parameters that characterizes continuous seismic signals (seismograms), avoiding the identification and labelling of isolated events.
Responsible
Jesús Miguel Ibáñez Godoy
Goal
We will create a Parametric Seismic Database for long time series at a set of volcanoes. Therefore, once the best set of features has been defined, FEMALE will transform the original raw seismic data bases into a new parametric seismic database.
Responsible
Jesús Miguel Ibáñez Godoy
Goal
Once the new parametric data base is created for each selected volcano, the creation of the Inventory of Case Studies will be divided into three tasks: Identification of the primary volcanic processes, Determination of the baseline and Extraction of parameters that evolve before each Case Studies.
Responsible
Jesús Miguel Ibáñez Godoy
Goal
FEMALE will extend this study to seismic time series associated with other volcanoes to create a new inventory of case studies that will enable volcanic forecasting and permit comparison with complete seismic catalogues.
Responsible
María del Carmen Benítez Ortúzar
Goal
The use of ML in volcanic seismology allows seismic catalogues of volcanoes to be expanded with more precise information. We are pioneers in this endeavor, and our advances provide reliable tools for this purpose.
Responsibles
María del Carmen Benítez Ortúzar
Jesús Miguel Ibáñez Godoy
Goal
We will compare the results derived in WP 3 and WP 4 with those obtained in WP 5.
Responsibles
María del Carmen Benítez Ortúzar
Jesús Miguel Ibáñez Godoy
Goal
The working team will be led by Professors Ibáñez and Benítez, with the direct collaboration of all the researchers from the Research Team and the Working Group.
If you’d like to learn more about GEOASPAI, feel free to click the link below: