Event recognition in marine seismological data using Random Forest machine learning classifier
SUMMARY Automatic detection of seismic events in ocean bottom seismometer (OBS) data is difficult due to elevated levels of noise compared to the recordings from land. Popular deep-learning approaches that work well with earthquakes recorded on land perform poorly in a marine setting. Their adaptati...
Published in: | Geophysical Journal International |
---|---|
Main Authors: | , , , |
Other Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Oxford University Press (OUP)
2023
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1093/gji/ggad244 https://academic.oup.com/gji/advance-article-pdf/doi/10.1093/gji/ggad244/50629157/ggad244.pdf https://academic.oup.com/gji/article-pdf/235/1/589/50722598/ggad244.pdf |
id |
croxfordunivpr:10.1093/gji/ggad244 |
---|---|
record_format |
openpolar |
spelling |
croxfordunivpr:10.1093/gji/ggad244 2024-09-15T18:07:04+00:00 Event recognition in marine seismological data using Random Forest machine learning classifier Domel, Przemyslaw Hibert, Clément Schlindwein, Vera Plaza-Faverola, Andreia Tromsø Research Foundation Research Council of Norway 2023 http://dx.doi.org/10.1093/gji/ggad244 https://academic.oup.com/gji/advance-article-pdf/doi/10.1093/gji/ggad244/50629157/ggad244.pdf https://academic.oup.com/gji/article-pdf/235/1/589/50722598/ggad244.pdf en eng Oxford University Press (OUP) https://creativecommons.org/licenses/by/4.0/ Geophysical Journal International volume 235, issue 1, page 589-609 ISSN 0956-540X 1365-246X journal-article 2023 croxfordunivpr https://doi.org/10.1093/gji/ggad244 2024-07-01T04:20:17Z SUMMARY Automatic detection of seismic events in ocean bottom seismometer (OBS) data is difficult due to elevated levels of noise compared to the recordings from land. Popular deep-learning approaches that work well with earthquakes recorded on land perform poorly in a marine setting. Their adaptation to OBS data requires catalogues containing hundreds of thousands of labelled event examples that currently do not exist, especially for signals different than earthquakes. Therefore, the usual routine involves standard amplitude-based detection methods and manual processing to obtain events of interest. We present here the first attempt to utilize a Random Forest supervised machine learning classifier on marine seismological data to automate catalogue screening and event recognition among different signals [i.e. earthquakes, short duration events (SDE) and marine noise sources]. The detection approach uses the short-term average/long-term average method, enhanced by a kurtosis-based picker for a more precise recognition of the onset of events. The subsequent machine learning method uses a previously published set of signal features (waveform-, frequency- and spectrum-based), applied successfully in recognition of different classes of events in land seismological data. Our workflow uses a small subset of manually selected signals for the initial training procedure and we then iteratively evaluate and refine the model using subsequent OBS stations within one single deployment in the eastern Fram Strait, between Greenland and Svalbard. We find that the used set of features is well suited for the discrimination of different classes of events during the training step. During the manual verification of the automatic detection results, we find that the produced catalogue of earthquakes contains a large number of noise examples, but almost all events of interest are properly captured. By providing increasingly larger sets of noise examples we see an improvement in the quality of the obtained catalogues. Our final model ... Article in Journal/Newspaper Fram Strait Greenland Svalbard Oxford University Press Geophysical Journal International 235 1 589 609 |
institution |
Open Polar |
collection |
Oxford University Press |
op_collection_id |
croxfordunivpr |
language |
English |
description |
SUMMARY Automatic detection of seismic events in ocean bottom seismometer (OBS) data is difficult due to elevated levels of noise compared to the recordings from land. Popular deep-learning approaches that work well with earthquakes recorded on land perform poorly in a marine setting. Their adaptation to OBS data requires catalogues containing hundreds of thousands of labelled event examples that currently do not exist, especially for signals different than earthquakes. Therefore, the usual routine involves standard amplitude-based detection methods and manual processing to obtain events of interest. We present here the first attempt to utilize a Random Forest supervised machine learning classifier on marine seismological data to automate catalogue screening and event recognition among different signals [i.e. earthquakes, short duration events (SDE) and marine noise sources]. The detection approach uses the short-term average/long-term average method, enhanced by a kurtosis-based picker for a more precise recognition of the onset of events. The subsequent machine learning method uses a previously published set of signal features (waveform-, frequency- and spectrum-based), applied successfully in recognition of different classes of events in land seismological data. Our workflow uses a small subset of manually selected signals for the initial training procedure and we then iteratively evaluate and refine the model using subsequent OBS stations within one single deployment in the eastern Fram Strait, between Greenland and Svalbard. We find that the used set of features is well suited for the discrimination of different classes of events during the training step. During the manual verification of the automatic detection results, we find that the produced catalogue of earthquakes contains a large number of noise examples, but almost all events of interest are properly captured. By providing increasingly larger sets of noise examples we see an improvement in the quality of the obtained catalogues. Our final model ... |
author2 |
Tromsø Research Foundation Research Council of Norway |
format |
Article in Journal/Newspaper |
author |
Domel, Przemyslaw Hibert, Clément Schlindwein, Vera Plaza-Faverola, Andreia |
spellingShingle |
Domel, Przemyslaw Hibert, Clément Schlindwein, Vera Plaza-Faverola, Andreia Event recognition in marine seismological data using Random Forest machine learning classifier |
author_facet |
Domel, Przemyslaw Hibert, Clément Schlindwein, Vera Plaza-Faverola, Andreia |
author_sort |
Domel, Przemyslaw |
title |
Event recognition in marine seismological data using Random Forest machine learning classifier |
title_short |
Event recognition in marine seismological data using Random Forest machine learning classifier |
title_full |
Event recognition in marine seismological data using Random Forest machine learning classifier |
title_fullStr |
Event recognition in marine seismological data using Random Forest machine learning classifier |
title_full_unstemmed |
Event recognition in marine seismological data using Random Forest machine learning classifier |
title_sort |
event recognition in marine seismological data using random forest machine learning classifier |
publisher |
Oxford University Press (OUP) |
publishDate |
2023 |
url |
http://dx.doi.org/10.1093/gji/ggad244 https://academic.oup.com/gji/advance-article-pdf/doi/10.1093/gji/ggad244/50629157/ggad244.pdf https://academic.oup.com/gji/article-pdf/235/1/589/50722598/ggad244.pdf |
genre |
Fram Strait Greenland Svalbard |
genre_facet |
Fram Strait Greenland Svalbard |
op_source |
Geophysical Journal International volume 235, issue 1, page 589-609 ISSN 0956-540X 1365-246X |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.1093/gji/ggad244 |
container_title |
Geophysical Journal International |
container_volume |
235 |
container_issue |
1 |
container_start_page |
589 |
op_container_end_page |
609 |
_version_ |
1810444446149378048 |