Deep Multimodal Learning for Seismoacoustic Fusion to Improve Earthquake‐Explosion Discrimination Within the Korean Peninsula

Abstract Recent geophysical studies have highlighted the potential utility of integrating both seismic and infrasound data to improve source characterization and event discrimination efforts. However, the influence of each of these data types within an integrated framework is not yet well‐understood...

Full description

Saved in:
Bibliographic Details
Main Authors: Miro Ronac Giannone, Stephen Arrowsmith, Junghyun Park, Brian Stump, Chris Hayward, Eric Larson, Il‐Young Che
Format: Article
Language:English
Published: Wiley 2024-07-01
Series:Geophysical Research Letters
Subjects:
Online Access:https://doi.org/10.1029/2024GL109404
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725638013878272
author Miro Ronac Giannone
Stephen Arrowsmith
Junghyun Park
Brian Stump
Chris Hayward
Eric Larson
Il‐Young Che
author_facet Miro Ronac Giannone
Stephen Arrowsmith
Junghyun Park
Brian Stump
Chris Hayward
Eric Larson
Il‐Young Che
author_sort Miro Ronac Giannone
collection DOAJ
description Abstract Recent geophysical studies have highlighted the potential utility of integrating both seismic and infrasound data to improve source characterization and event discrimination efforts. However, the influence of each of these data types within an integrated framework is not yet well‐understood by the geophysical community. To help elucidate the role of each data type within a merged structure, we develop a neural network which fuses seismic and infrasound array data via a gated multimodal unit for earthquake‐explosion discrimination within the Korean Peninsula. Model performance is compared before and after adding the infrasound branch. We find that the seismoacoustic model outperforms the seismic model, with the majority of the improvements stemming from the explosions class. The influence of infrasound is quantified by analyzing gated multimodal activations. Results indicate that the model relies comparatively more on the infrasound branch to correct seismic predictions.
format Article
id doaj-art-7dfb5d45c2e9455f82f5549339fa5c1f
institution DOAJ
issn 0094-8276
1944-8007
language English
publishDate 2024-07-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-7dfb5d45c2e9455f82f5549339fa5c1f2025-08-20T03:10:25ZengWileyGeophysical Research Letters0094-82761944-80072024-07-015114n/an/a10.1029/2024GL109404Deep Multimodal Learning for Seismoacoustic Fusion to Improve Earthquake‐Explosion Discrimination Within the Korean PeninsulaMiro Ronac Giannone0Stephen Arrowsmith1Junghyun Park2Brian Stump3Chris Hayward4Eric Larson5Il‐Young Che6Department of Earth Science Southern Methodist University Dallas TX USADepartment of Earth Science Southern Methodist University Dallas TX USADepartment of Earth Science Southern Methodist University Dallas TX USADepartment of Earth Science Southern Methodist University Dallas TX USADepartment of Earth Science Southern Methodist University Dallas TX USADepartment of Computer Science Southern Methodist University Dallas TX USAKorea Institute of Geoscience and Mineral Resources Daejeon South KoreaAbstract Recent geophysical studies have highlighted the potential utility of integrating both seismic and infrasound data to improve source characterization and event discrimination efforts. However, the influence of each of these data types within an integrated framework is not yet well‐understood by the geophysical community. To help elucidate the role of each data type within a merged structure, we develop a neural network which fuses seismic and infrasound array data via a gated multimodal unit for earthquake‐explosion discrimination within the Korean Peninsula. Model performance is compared before and after adding the infrasound branch. We find that the seismoacoustic model outperforms the seismic model, with the majority of the improvements stemming from the explosions class. The influence of infrasound is quantified by analyzing gated multimodal activations. Results indicate that the model relies comparatively more on the infrasound branch to correct seismic predictions.https://doi.org/10.1029/2024GL109404deep learningseismologyinfrasound
spellingShingle Miro Ronac Giannone
Stephen Arrowsmith
Junghyun Park
Brian Stump
Chris Hayward
Eric Larson
Il‐Young Che
Deep Multimodal Learning for Seismoacoustic Fusion to Improve Earthquake‐Explosion Discrimination Within the Korean Peninsula
Geophysical Research Letters
deep learning
seismology
infrasound
title Deep Multimodal Learning for Seismoacoustic Fusion to Improve Earthquake‐Explosion Discrimination Within the Korean Peninsula
title_full Deep Multimodal Learning for Seismoacoustic Fusion to Improve Earthquake‐Explosion Discrimination Within the Korean Peninsula
title_fullStr Deep Multimodal Learning for Seismoacoustic Fusion to Improve Earthquake‐Explosion Discrimination Within the Korean Peninsula
title_full_unstemmed Deep Multimodal Learning for Seismoacoustic Fusion to Improve Earthquake‐Explosion Discrimination Within the Korean Peninsula
title_short Deep Multimodal Learning for Seismoacoustic Fusion to Improve Earthquake‐Explosion Discrimination Within the Korean Peninsula
title_sort deep multimodal learning for seismoacoustic fusion to improve earthquake explosion discrimination within the korean peninsula
topic deep learning
seismology
infrasound
url https://doi.org/10.1029/2024GL109404
work_keys_str_mv AT miroronacgiannone deepmultimodallearningforseismoacousticfusiontoimproveearthquakeexplosiondiscriminationwithinthekoreanpeninsula
AT stephenarrowsmith deepmultimodallearningforseismoacousticfusiontoimproveearthquakeexplosiondiscriminationwithinthekoreanpeninsula
AT junghyunpark deepmultimodallearningforseismoacousticfusiontoimproveearthquakeexplosiondiscriminationwithinthekoreanpeninsula
AT brianstump deepmultimodallearningforseismoacousticfusiontoimproveearthquakeexplosiondiscriminationwithinthekoreanpeninsula
AT chrishayward deepmultimodallearningforseismoacousticfusiontoimproveearthquakeexplosiondiscriminationwithinthekoreanpeninsula
AT ericlarson deepmultimodallearningforseismoacousticfusiontoimproveearthquakeexplosiondiscriminationwithinthekoreanpeninsula
AT ilyoungche deepmultimodallearningforseismoacousticfusiontoimproveearthquakeexplosiondiscriminationwithinthekoreanpeninsula