Single Layer Recurrent Neural Network for detection of local swarm-like earthquakes—the application
SUMMARY We present results of applying a local event detector based on artificial neural networks (ANNs) to two seismically active regions. The concept of ANNs enables us to recognize earthquake-like signals in seismograms because well-trained neural networks are characterized by the ability to gene...
Published in: | Geophysical Journal International |
---|---|
Main Authors: | , |
Other Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Oxford University Press (OUP)
2019
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1093/gji/ggz321 http://academic.oup.com/gji/advance-article-pdf/doi/10.1093/gji/ggz321/28936440/ggz321.pdf http://academic.oup.com/gji/article-pdf/219/1/672/29149344/ggz321.pdf |
id |
croxfordunivpr:10.1093/gji/ggz321 |
---|---|
record_format |
openpolar |
spelling |
croxfordunivpr:10.1093/gji/ggz321 2023-10-09T21:52:51+02:00 Single Layer Recurrent Neural Network for detection of local swarm-like earthquakes—the application Doubravová, Jana Horálek, Josef Grant Agency of the Czech Republic European Paediatric Orthopaedic Society 2019 http://dx.doi.org/10.1093/gji/ggz321 http://academic.oup.com/gji/advance-article-pdf/doi/10.1093/gji/ggz321/28936440/ggz321.pdf http://academic.oup.com/gji/article-pdf/219/1/672/29149344/ggz321.pdf en eng Oxford University Press (OUP) https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model Geophysical Journal International volume 219, issue 1, page 672-689 ISSN 0956-540X 1365-246X Geochemistry and Petrology Geophysics journal-article 2019 croxfordunivpr https://doi.org/10.1093/gji/ggz321 2023-09-22T11:15:45Z SUMMARY We present results of applying a local event detector based on artificial neural networks (ANNs) to two seismically active regions. The concept of ANNs enables us to recognize earthquake-like signals in seismograms because well-trained neural networks are characterized by the ability to generalize to unseen examples. This means that once the ANN is trained, in our case by few tens to hundreds of examples of local event seismograms, the algorithm can then recognize similar features in unknown records. The detailed description of the single-station detection, design and training of the ANN has been described in our previous paper. Here we show the practical application of our ANN to the same seismoactive region we used for its training, West Bohemia/Vogtland (border area Czechia-Saxony, local seismic network WEBNET), and to different seismogenic area, Reykjanes Peninsula (South-West Iceland, local seismic network REYKJANET). The training process requires carefully prepared data set which is preferably achieved by manual processing. Such data were available for the West Bohemia/Vogtland earthquake-swarm region, so we used them to train the ANN and test its performance. Due to the absence of completely manually processed activity for the Reykjanes Peninsula, we use the trained ANN for swarm-like activity in such a different tectonic setting. The application of a coincidence of the single-station detections helps to reduce significantly the number of undetected events as well as the number of false alarms. Setting up the minimum number of stations which are required to confirm an event detection enables us to choose the balance between minimum magnitude threshold and a number of false alarms. The ANN detection results for the Reykjanes Peninsula are compared to manual readings on the stations of the REYKJANET network, manual processing from Icelandic regional network SIL (the SIL catalogues by the Icelandic Meteorological Office) and two tested automatic location algorithms. The neural network shows ... Article in Journal/Newspaper Iceland Oxford University Press (via Crossref) Reykjanes ENVELOPE(-22.250,-22.250,65.467,65.467) Geophysical Journal International 219 1 672 689 |
institution |
Open Polar |
collection |
Oxford University Press (via Crossref) |
op_collection_id |
croxfordunivpr |
language |
English |
topic |
Geochemistry and Petrology Geophysics |
spellingShingle |
Geochemistry and Petrology Geophysics Doubravová, Jana Horálek, Josef Single Layer Recurrent Neural Network for detection of local swarm-like earthquakes—the application |
topic_facet |
Geochemistry and Petrology Geophysics |
description |
SUMMARY We present results of applying a local event detector based on artificial neural networks (ANNs) to two seismically active regions. The concept of ANNs enables us to recognize earthquake-like signals in seismograms because well-trained neural networks are characterized by the ability to generalize to unseen examples. This means that once the ANN is trained, in our case by few tens to hundreds of examples of local event seismograms, the algorithm can then recognize similar features in unknown records. The detailed description of the single-station detection, design and training of the ANN has been described in our previous paper. Here we show the practical application of our ANN to the same seismoactive region we used for its training, West Bohemia/Vogtland (border area Czechia-Saxony, local seismic network WEBNET), and to different seismogenic area, Reykjanes Peninsula (South-West Iceland, local seismic network REYKJANET). The training process requires carefully prepared data set which is preferably achieved by manual processing. Such data were available for the West Bohemia/Vogtland earthquake-swarm region, so we used them to train the ANN and test its performance. Due to the absence of completely manually processed activity for the Reykjanes Peninsula, we use the trained ANN for swarm-like activity in such a different tectonic setting. The application of a coincidence of the single-station detections helps to reduce significantly the number of undetected events as well as the number of false alarms. Setting up the minimum number of stations which are required to confirm an event detection enables us to choose the balance between minimum magnitude threshold and a number of false alarms. The ANN detection results for the Reykjanes Peninsula are compared to manual readings on the stations of the REYKJANET network, manual processing from Icelandic regional network SIL (the SIL catalogues by the Icelandic Meteorological Office) and two tested automatic location algorithms. The neural network shows ... |
author2 |
Grant Agency of the Czech Republic European Paediatric Orthopaedic Society |
format |
Article in Journal/Newspaper |
author |
Doubravová, Jana Horálek, Josef |
author_facet |
Doubravová, Jana Horálek, Josef |
author_sort |
Doubravová, Jana |
title |
Single Layer Recurrent Neural Network for detection of local swarm-like earthquakes—the application |
title_short |
Single Layer Recurrent Neural Network for detection of local swarm-like earthquakes—the application |
title_full |
Single Layer Recurrent Neural Network for detection of local swarm-like earthquakes—the application |
title_fullStr |
Single Layer Recurrent Neural Network for detection of local swarm-like earthquakes—the application |
title_full_unstemmed |
Single Layer Recurrent Neural Network for detection of local swarm-like earthquakes—the application |
title_sort |
single layer recurrent neural network for detection of local swarm-like earthquakes—the application |
publisher |
Oxford University Press (OUP) |
publishDate |
2019 |
url |
http://dx.doi.org/10.1093/gji/ggz321 http://academic.oup.com/gji/advance-article-pdf/doi/10.1093/gji/ggz321/28936440/ggz321.pdf http://academic.oup.com/gji/article-pdf/219/1/672/29149344/ggz321.pdf |
long_lat |
ENVELOPE(-22.250,-22.250,65.467,65.467) |
geographic |
Reykjanes |
geographic_facet |
Reykjanes |
genre |
Iceland |
genre_facet |
Iceland |
op_source |
Geophysical Journal International volume 219, issue 1, page 672-689 ISSN 0956-540X 1365-246X |
op_rights |
https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model |
op_doi |
https://doi.org/10.1093/gji/ggz321 |
container_title |
Geophysical Journal International |
container_volume |
219 |
container_issue |
1 |
container_start_page |
672 |
op_container_end_page |
689 |
_version_ |
1779316054259924992 |