Characterization of seismicity from different glacial bed types: machine learning classification of laboratory stick-slip acoustic emissions
Abstract Subglacial seismicity presents the opportunity to monitor inaccessible glacial beds at the epicentral location and time. Glaciers can be underlain by rock or till, a first order control on bed mechanics. Velocity-weakening, necessary for unstable slip, has been shown for each bed type, but...
Published in: | Annals of Glaciology |
---|---|
Main Authors: | , , , |
Other Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Cambridge University Press (CUP)
2024
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1017/aog.2024.11 https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0260305524000119 |
id |
crcambridgeupr:10.1017/aog.2024.11 |
---|---|
record_format |
openpolar |
spelling |
crcambridgeupr:10.1017/aog.2024.11 2024-06-09T07:38:26+00:00 Characterization of seismicity from different glacial bed types: machine learning classification of laboratory stick-slip acoustic emissions Saltiel, Seth Groebner, Nathan Sawi, Theresa McCarthy, Christine Directorate for Geosciences Division of Polar Programs 2024 http://dx.doi.org/10.1017/aog.2024.11 https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0260305524000119 en eng Cambridge University Press (CUP) http://creativecommons.org/licenses/by/4.0/ Annals of Glaciology page 1-8 ISSN 0260-3055 1727-5644 journal-article 2024 crcambridgeupr https://doi.org/10.1017/aog.2024.11 2024-05-15T13:13:03Z Abstract Subglacial seismicity presents the opportunity to monitor inaccessible glacial beds at the epicentral location and time. Glaciers can be underlain by rock or till, a first order control on bed mechanics. Velocity-weakening, necessary for unstable slip, has been shown for each bed type, but is much stronger and evolves over more than an order of magnitude longer distances for till beds. Utilizing a de-stiffened double direct shear apparatus, we found conditions for instability at freezing temperatures and high slip rates for both bed types. During stick–slip stress-drops, we recorded acoustic emissions with piezoelectric transducers frozen into the ice. The two populations of event waveforms appear visually similar and overlap in their statistical features. We implemented a suite of supervised machine learning algorithms to classify the bed type of recorded waveforms and spectra, with prediction accuracy between 65–80%. The Random Forest Classifier is interpretable, showing the importance of initial oscillation peaks and higher frequency energy. Till beds have generally higher friction and resulting stress-drops, with more impulsive first arrivals and more high frequency content compared to rock emissions, but rock beds can produce many till-like events. Seismic signatures could enhance interpretation of bed conditions and mechanics from subglacial seismicity. Article in Journal/Newspaper Annals of Glaciology Cambridge University Press Annals of Glaciology 1 8 |
institution |
Open Polar |
collection |
Cambridge University Press |
op_collection_id |
crcambridgeupr |
language |
English |
description |
Abstract Subglacial seismicity presents the opportunity to monitor inaccessible glacial beds at the epicentral location and time. Glaciers can be underlain by rock or till, a first order control on bed mechanics. Velocity-weakening, necessary for unstable slip, has been shown for each bed type, but is much stronger and evolves over more than an order of magnitude longer distances for till beds. Utilizing a de-stiffened double direct shear apparatus, we found conditions for instability at freezing temperatures and high slip rates for both bed types. During stick–slip stress-drops, we recorded acoustic emissions with piezoelectric transducers frozen into the ice. The two populations of event waveforms appear visually similar and overlap in their statistical features. We implemented a suite of supervised machine learning algorithms to classify the bed type of recorded waveforms and spectra, with prediction accuracy between 65–80%. The Random Forest Classifier is interpretable, showing the importance of initial oscillation peaks and higher frequency energy. Till beds have generally higher friction and resulting stress-drops, with more impulsive first arrivals and more high frequency content compared to rock emissions, but rock beds can produce many till-like events. Seismic signatures could enhance interpretation of bed conditions and mechanics from subglacial seismicity. |
author2 |
Directorate for Geosciences Division of Polar Programs |
format |
Article in Journal/Newspaper |
author |
Saltiel, Seth Groebner, Nathan Sawi, Theresa McCarthy, Christine |
spellingShingle |
Saltiel, Seth Groebner, Nathan Sawi, Theresa McCarthy, Christine Characterization of seismicity from different glacial bed types: machine learning classification of laboratory stick-slip acoustic emissions |
author_facet |
Saltiel, Seth Groebner, Nathan Sawi, Theresa McCarthy, Christine |
author_sort |
Saltiel, Seth |
title |
Characterization of seismicity from different glacial bed types: machine learning classification of laboratory stick-slip acoustic emissions |
title_short |
Characterization of seismicity from different glacial bed types: machine learning classification of laboratory stick-slip acoustic emissions |
title_full |
Characterization of seismicity from different glacial bed types: machine learning classification of laboratory stick-slip acoustic emissions |
title_fullStr |
Characterization of seismicity from different glacial bed types: machine learning classification of laboratory stick-slip acoustic emissions |
title_full_unstemmed |
Characterization of seismicity from different glacial bed types: machine learning classification of laboratory stick-slip acoustic emissions |
title_sort |
characterization of seismicity from different glacial bed types: machine learning classification of laboratory stick-slip acoustic emissions |
publisher |
Cambridge University Press (CUP) |
publishDate |
2024 |
url |
http://dx.doi.org/10.1017/aog.2024.11 https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0260305524000119 |
genre |
Annals of Glaciology |
genre_facet |
Annals of Glaciology |
op_source |
Annals of Glaciology page 1-8 ISSN 0260-3055 1727-5644 |
op_rights |
http://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.1017/aog.2024.11 |
container_title |
Annals of Glaciology |
container_start_page |
1 |
op_container_end_page |
8 |
_version_ |
1801372953817907200 |