Automatic speech recognition predicts contemporaneous earthquake fault displacement
Abstract Significant progress has been made in probing the state of an earthquake fault by applying machine learning to continuous seismic waveforms. The breakthroughs were originally obtained from laboratory shear experiments and numerical simulations of fault shear, then successfully extended to s...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-55994-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571502412693504 |
|---|---|
| author | Christopher W. Johnson Kun Wang Paul A. Johnson |
| author_facet | Christopher W. Johnson Kun Wang Paul A. Johnson |
| author_sort | Christopher W. Johnson |
| collection | DOAJ |
| description | Abstract Significant progress has been made in probing the state of an earthquake fault by applying machine learning to continuous seismic waveforms. The breakthroughs were originally obtained from laboratory shear experiments and numerical simulations of fault shear, then successfully extended to slow-slipping faults. Here we apply the Wav2Vec-2.0 self-supervised framework for automatic speech recognition to continuous seismic signals emanating from a sequence of moderate magnitude earthquakes during the 2018 caldera collapse at the Kīlauea volcano on the island of Hawai’i. We pre-train the Wav2Vec-2.0 model using caldera seismic waveforms and augment the model architecture to predict contemporaneous surface displacement during the caldera collapse sequence, a proxy for fault displacement. We find the model displacement predictions to be excellent. The model is adapted for near-future prediction information and found hints of prediction capability, but the results are not robust. The results demonstrate that earthquake faults emit seismic signatures in a similar manner to laboratory and numerical simulation faults, and artificial intelligence models developed for encoding audio of speech may have important applications in studying active fault zones. |
| format | Article |
| id | doaj-art-329f6eb25a0d4457af8b20f777a8577b |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-329f6eb25a0d4457af8b20f777a8577b2025-02-02T12:32:41ZengNature PortfolioNature Communications2041-17232025-01-0116111010.1038/s41467-025-55994-9Automatic speech recognition predicts contemporaneous earthquake fault displacementChristopher W. Johnson0Kun Wang1Paul A. Johnson2Los Alamos National Laboratory, EES-17 National Security Earth ScienceLos Alamos National Laboratory, EES-17 National Security Earth ScienceLos Alamos National Laboratory, EES-17 National Security Earth ScienceAbstract Significant progress has been made in probing the state of an earthquake fault by applying machine learning to continuous seismic waveforms. The breakthroughs were originally obtained from laboratory shear experiments and numerical simulations of fault shear, then successfully extended to slow-slipping faults. Here we apply the Wav2Vec-2.0 self-supervised framework for automatic speech recognition to continuous seismic signals emanating from a sequence of moderate magnitude earthquakes during the 2018 caldera collapse at the Kīlauea volcano on the island of Hawai’i. We pre-train the Wav2Vec-2.0 model using caldera seismic waveforms and augment the model architecture to predict contemporaneous surface displacement during the caldera collapse sequence, a proxy for fault displacement. We find the model displacement predictions to be excellent. The model is adapted for near-future prediction information and found hints of prediction capability, but the results are not robust. The results demonstrate that earthquake faults emit seismic signatures in a similar manner to laboratory and numerical simulation faults, and artificial intelligence models developed for encoding audio of speech may have important applications in studying active fault zones.https://doi.org/10.1038/s41467-025-55994-9 |
| spellingShingle | Christopher W. Johnson Kun Wang Paul A. Johnson Automatic speech recognition predicts contemporaneous earthquake fault displacement Nature Communications |
| title | Automatic speech recognition predicts contemporaneous earthquake fault displacement |
| title_full | Automatic speech recognition predicts contemporaneous earthquake fault displacement |
| title_fullStr | Automatic speech recognition predicts contemporaneous earthquake fault displacement |
| title_full_unstemmed | Automatic speech recognition predicts contemporaneous earthquake fault displacement |
| title_short | Automatic speech recognition predicts contemporaneous earthquake fault displacement |
| title_sort | automatic speech recognition predicts contemporaneous earthquake fault displacement |
| url | https://doi.org/10.1038/s41467-025-55994-9 |
| work_keys_str_mv | AT christopherwjohnson automaticspeechrecognitionpredictscontemporaneousearthquakefaultdisplacement AT kunwang automaticspeechrecognitionpredictscontemporaneousearthquakefaultdisplacement AT paulajohnson automaticspeechrecognitionpredictscontemporaneousearthquakefaultdisplacement |