Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning
International audience The continuously growing amount of seismic data collected worldwide is outpacing our abilities for analysis, since to date, such datasets have been analyzed in a human-expert-intensive, supervised fashion. Moreover, analyses that are conducted can be strongly biased by the sta...
Published in: | Nature Communications |
---|---|
Main Authors: | , , , , , |
Other Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
HAL CCSD
2020
|
Subjects: | |
Online Access: | https://hal.univ-grenoble-alpes.fr/hal-03411505 https://hal.univ-grenoble-alpes.fr/hal-03411505v2/document https://hal.univ-grenoble-alpes.fr/hal-03411505v2/file/Preprint.pdf https://doi.org/10.1038/s41467-020-17841-x |
id |
ftinsu:oai:HAL:hal-03411505v2 |
---|---|
record_format |
openpolar |
spelling |
ftinsu:oai:HAL:hal-03411505v2 2024-04-28T08:21:51+00:00 Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning Seydoux, Léonard Balestriero, Randall Poli, Piero Hoop, Maarten De Campillo, Michel Baraniuk, Richard Institut des Sciences de la Terre (ISTerre) Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Savoie Mont Blanc (USMB Université de Savoie Université de Chambéry )-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel-Université Grenoble Alpes (UGA) Electrical and Computer Engineering - Rice University Rice University Houston ANR-19-P3IA-0003,MIAI,MIAI @ Grenoble Alpes(2019) European Project: 789742335,F-IMAGE 2020 https://hal.univ-grenoble-alpes.fr/hal-03411505 https://hal.univ-grenoble-alpes.fr/hal-03411505v2/document https://hal.univ-grenoble-alpes.fr/hal-03411505v2/file/Preprint.pdf https://doi.org/10.1038/s41467-020-17841-x en eng HAL CCSD Nature Publishing Group info:eu-repo/semantics/altIdentifier/doi/10.1038/s41467-020-17841-x info:eu-repo/grantAgreement//789742335/EU/ERC F-IMAGE/F-IMAGE hal-03411505 https://hal.univ-grenoble-alpes.fr/hal-03411505 https://hal.univ-grenoble-alpes.fr/hal-03411505v2/document https://hal.univ-grenoble-alpes.fr/hal-03411505v2/file/Preprint.pdf doi:10.1038/s41467-020-17841-x info:eu-repo/semantics/OpenAccess ISSN: 2041-1723 EISSN: 2041-1723 Nature Communications https://hal.univ-grenoble-alpes.fr/hal-03411505 Nature Communications, 2020, 11 (1), pp.3972. ⟨10.1038/s41467-020-17841-x⟩ [SDU.STU.GP]Sciences of the Universe [physics]/Earth Sciences/Geophysics [physics.geo-ph] [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] info:eu-repo/semantics/article Journal articles 2020 ftinsu https://doi.org/10.1038/s41467-020-17841-x 2024-04-05T00:36:09Z International audience The continuously growing amount of seismic data collected worldwide is outpacing our abilities for analysis, since to date, such datasets have been analyzed in a human-expert-intensive, supervised fashion. Moreover, analyses that are conducted can be strongly biased by the standard models employed by seismologists. In response to both of these challenges, we develop a new unsupervised machine learning framework for detecting and clustering seismic signals in continuous seismic records. Our approach combines a deep scattering network and a Gaussian mixture model to cluster seismic signal segments and detect novel structures. To illustrate the power of the framework, we analyze seismic data acquired during the June 2017 Nuugaatsiaq, Greenland landslide. We demonstrate the blind detection and recovery of the repeating precursory seismicity that was recorded before the main landslide rupture, which suggests that our approach could lead to more informative forecasting of the seismic activity in seismogenic areas. Article in Journal/Newspaper Greenland Nuugaatsiaq Institut national des sciences de l'Univers: HAL-INSU Nature Communications 11 1 |
institution |
Open Polar |
collection |
Institut national des sciences de l'Univers: HAL-INSU |
op_collection_id |
ftinsu |
language |
English |
topic |
[SDU.STU.GP]Sciences of the Universe [physics]/Earth Sciences/Geophysics [physics.geo-ph] [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
spellingShingle |
[SDU.STU.GP]Sciences of the Universe [physics]/Earth Sciences/Geophysics [physics.geo-ph] [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] Seydoux, Léonard Balestriero, Randall Poli, Piero Hoop, Maarten De Campillo, Michel Baraniuk, Richard Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning |
topic_facet |
[SDU.STU.GP]Sciences of the Universe [physics]/Earth Sciences/Geophysics [physics.geo-ph] [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
description |
International audience The continuously growing amount of seismic data collected worldwide is outpacing our abilities for analysis, since to date, such datasets have been analyzed in a human-expert-intensive, supervised fashion. Moreover, analyses that are conducted can be strongly biased by the standard models employed by seismologists. In response to both of these challenges, we develop a new unsupervised machine learning framework for detecting and clustering seismic signals in continuous seismic records. Our approach combines a deep scattering network and a Gaussian mixture model to cluster seismic signal segments and detect novel structures. To illustrate the power of the framework, we analyze seismic data acquired during the June 2017 Nuugaatsiaq, Greenland landslide. We demonstrate the blind detection and recovery of the repeating precursory seismicity that was recorded before the main landslide rupture, which suggests that our approach could lead to more informative forecasting of the seismic activity in seismogenic areas. |
author2 |
Institut des Sciences de la Terre (ISTerre) Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Savoie Mont Blanc (USMB Université de Savoie Université de Chambéry )-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel-Université Grenoble Alpes (UGA) Electrical and Computer Engineering - Rice University Rice University Houston ANR-19-P3IA-0003,MIAI,MIAI @ Grenoble Alpes(2019) European Project: 789742335,F-IMAGE |
format |
Article in Journal/Newspaper |
author |
Seydoux, Léonard Balestriero, Randall Poli, Piero Hoop, Maarten De Campillo, Michel Baraniuk, Richard |
author_facet |
Seydoux, Léonard Balestriero, Randall Poli, Piero Hoop, Maarten De Campillo, Michel Baraniuk, Richard |
author_sort |
Seydoux, Léonard |
title |
Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning |
title_short |
Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning |
title_full |
Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning |
title_fullStr |
Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning |
title_full_unstemmed |
Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning |
title_sort |
clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning |
publisher |
HAL CCSD |
publishDate |
2020 |
url |
https://hal.univ-grenoble-alpes.fr/hal-03411505 https://hal.univ-grenoble-alpes.fr/hal-03411505v2/document https://hal.univ-grenoble-alpes.fr/hal-03411505v2/file/Preprint.pdf https://doi.org/10.1038/s41467-020-17841-x |
genre |
Greenland Nuugaatsiaq |
genre_facet |
Greenland Nuugaatsiaq |
op_source |
ISSN: 2041-1723 EISSN: 2041-1723 Nature Communications https://hal.univ-grenoble-alpes.fr/hal-03411505 Nature Communications, 2020, 11 (1), pp.3972. ⟨10.1038/s41467-020-17841-x⟩ |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1038/s41467-020-17841-x info:eu-repo/grantAgreement//789742335/EU/ERC F-IMAGE/F-IMAGE hal-03411505 https://hal.univ-grenoble-alpes.fr/hal-03411505 https://hal.univ-grenoble-alpes.fr/hal-03411505v2/document https://hal.univ-grenoble-alpes.fr/hal-03411505v2/file/Preprint.pdf doi:10.1038/s41467-020-17841-x |
op_rights |
info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.1038/s41467-020-17841-x |
container_title |
Nature Communications |
container_volume |
11 |
container_issue |
1 |
_version_ |
1797583916437078016 |