Volcano-Seismic Event Detection and Clustering

This study looks into unsupervised and supervised methods for detecting events in volcano-seismic time series data, segmenting the data, and clustering the segments where there is activity. This two-stage pipeline allows for the analysis of the signals without requiring the type of event to be ident...

Full description

Saved in:
Bibliographic Details
Main Authors: Joe Carthy, Pablo Rey-Devesa, Manuel Titos, Carmen Benitez
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10978850/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849723336872951808
author Joe Carthy
Pablo Rey-Devesa
Manuel Titos
Carmen Benitez
author_facet Joe Carthy
Pablo Rey-Devesa
Manuel Titos
Carmen Benitez
author_sort Joe Carthy
collection DOAJ
description This study looks into unsupervised and supervised methods for detecting events in volcano-seismic time series data, segmenting the data, and clustering the segments where there is activity. This two-stage pipeline allows for the analysis of the signals without requiring the type of event to be identified at the offset and reduces the manpower required to analyze new data. Due to the resource intensive labeling process required to understand volcano-seismic signals it is important to explore unsupervised analysis techniques in this domain. The unsupervised methods are evaluated using supervised metrics including completeness, homogeneity, and V-measure scores. Alongside the unsupervised investigation, the use of intersection-based metrics that offer a clearer performance evaluation of the event segmentation task is motivated and the potential of gradient boosted trees for event detection is tested.
format Article
id doaj-art-d10dbdd323e8424782fce5929cfaabc0
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-d10dbdd323e8424782fce5929cfaabc02025-08-20T03:11:03ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118112761128910.1109/JSTARS.2025.355941210978850Volcano-Seismic Event Detection and ClusteringJoe Carthy0https://orcid.org/0000-0003-1489-3279Pablo Rey-Devesa1https://orcid.org/0000-0002-6254-4930Manuel Titos2Carmen Benitez3https://orcid.org/0000-0002-5407-8335Department of Signal Theory, Telematics and Communications and the Research Centre for Information and Communications Technologies (CITIC), University of Granada, Granada, SpainDepartment of Theoretical Physics and the Cosmos, University of Granada, Granada, SpainDepartment of Signal Theory, Telematics and Communications and the Research Centre for Information and Communications Technologies (CITIC), University of Granada, Granada, SpainDepartment of Signal Theory, Telematics and Communications and the Research Centre for Information and Communications Technologies (CITIC), University of Granada, Granada, SpainThis study looks into unsupervised and supervised methods for detecting events in volcano-seismic time series data, segmenting the data, and clustering the segments where there is activity. This two-stage pipeline allows for the analysis of the signals without requiring the type of event to be identified at the offset and reduces the manpower required to analyze new data. Due to the resource intensive labeling process required to understand volcano-seismic signals it is important to explore unsupervised analysis techniques in this domain. The unsupervised methods are evaluated using supervised metrics including completeness, homogeneity, and V-measure scores. Alongside the unsupervised investigation, the use of intersection-based metrics that offer a clearer performance evaluation of the event segmentation task is motivated and the potential of gradient boosted trees for event detection is tested.https://ieeexplore.ieee.org/document/10978850/Classificationclusteringdeep learningdimension reductiongradient boosted trees
spellingShingle Joe Carthy
Pablo Rey-Devesa
Manuel Titos
Carmen Benitez
Volcano-Seismic Event Detection and Clustering
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Classification
clustering
deep learning
dimension reduction
gradient boosted trees
title Volcano-Seismic Event Detection and Clustering
title_full Volcano-Seismic Event Detection and Clustering
title_fullStr Volcano-Seismic Event Detection and Clustering
title_full_unstemmed Volcano-Seismic Event Detection and Clustering
title_short Volcano-Seismic Event Detection and Clustering
title_sort volcano seismic event detection and clustering
topic Classification
clustering
deep learning
dimension reduction
gradient boosted trees
url https://ieeexplore.ieee.org/document/10978850/
work_keys_str_mv AT joecarthy volcanoseismiceventdetectionandclustering
AT pabloreydevesa volcanoseismiceventdetectionandclustering
AT manueltitos volcanoseismiceventdetectionandclustering
AT carmenbenitez volcanoseismiceventdetectionandclustering