Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning
Abstract Distributed Acoustic Sensing (DAS) is an emerging technology for earthquake monitoring and subsurface imaging. However, its distinct characteristics, such as unknown ground coupling and high noise level, pose challenges to signal processing. Existing machine learning models optimized for co...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-12-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-43355-3 |
| _version_ | 1827581543381467136 |
|---|---|
| author | Weiqiang Zhu Ettore Biondi Jiaxuan Li Jiuxun Yin Zachary E. Ross Zhongwen Zhan |
| author_facet | Weiqiang Zhu Ettore Biondi Jiaxuan Li Jiuxun Yin Zachary E. Ross Zhongwen Zhan |
| author_sort | Weiqiang Zhu |
| collection | DOAJ |
| description | Abstract Distributed Acoustic Sensing (DAS) is an emerging technology for earthquake monitoring and subsurface imaging. However, its distinct characteristics, such as unknown ground coupling and high noise level, pose challenges to signal processing. Existing machine learning models optimized for conventional seismic data struggle with DAS data due to its ultra-dense spatial sampling and limited manual labels. We introduce a semi-supervised learning approach to address the phase-picking task of DAS data. We use the pre-trained PhaseNet model to generate noisy labels of P/S arrivals in DAS data and apply the Gaussian mixture model phase association (GaMMA) method to refine these noisy labels and build training datasets. We develop PhaseNet-DAS, a deep learning model designed to process 2D spatio-temporal DAS data to achieve accurate phase picking and efficient earthquake detection. Our study demonstrates a method to develop deep learning models for DAS data, unlocking the potential of integrating DAS in enhancing earthquake monitoring. |
| first_indexed | 2024-03-08T22:37:41Z |
| format | Article |
| id | doaj.art-b19c350dfdff416384cbd3fee81a2db3 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-08T22:37:41Z |
| publishDate | 2023-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-b19c350dfdff416384cbd3fee81a2db32023-12-17T12:21:43ZengNature PortfolioNature Communications2041-17232023-12-0114111110.1038/s41467-023-43355-3Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learningWeiqiang Zhu0Ettore Biondi1Jiaxuan Li2Jiuxun Yin3Zachary E. Ross4Zhongwen Zhan5Seismological Laboratory, Division of Geological and Planetary Sciences, California Institute of TechnologySeismological Laboratory, Division of Geological and Planetary Sciences, California Institute of TechnologySeismological Laboratory, Division of Geological and Planetary Sciences, California Institute of TechnologySeismological Laboratory, Division of Geological and Planetary Sciences, California Institute of TechnologySeismological Laboratory, Division of Geological and Planetary Sciences, California Institute of TechnologySeismological Laboratory, Division of Geological and Planetary Sciences, California Institute of TechnologyAbstract Distributed Acoustic Sensing (DAS) is an emerging technology for earthquake monitoring and subsurface imaging. However, its distinct characteristics, such as unknown ground coupling and high noise level, pose challenges to signal processing. Existing machine learning models optimized for conventional seismic data struggle with DAS data due to its ultra-dense spatial sampling and limited manual labels. We introduce a semi-supervised learning approach to address the phase-picking task of DAS data. We use the pre-trained PhaseNet model to generate noisy labels of P/S arrivals in DAS data and apply the Gaussian mixture model phase association (GaMMA) method to refine these noisy labels and build training datasets. We develop PhaseNet-DAS, a deep learning model designed to process 2D spatio-temporal DAS data to achieve accurate phase picking and efficient earthquake detection. Our study demonstrates a method to develop deep learning models for DAS data, unlocking the potential of integrating DAS in enhancing earthquake monitoring.https://doi.org/10.1038/s41467-023-43355-3 |
| spellingShingle | Weiqiang Zhu Ettore Biondi Jiaxuan Li Jiuxun Yin Zachary E. Ross Zhongwen Zhan Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning Nature Communications |
| title | Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning |
| title_full | Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning |
| title_fullStr | Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning |
| title_full_unstemmed | Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning |
| title_short | Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning |
| title_sort | seismic arrival time picking on distributed acoustic sensing data using semi supervised learning |
| url | https://doi.org/10.1038/s41467-023-43355-3 |
| work_keys_str_mv | AT weiqiangzhu seismicarrivaltimepickingondistributedacousticsensingdatausingsemisupervisedlearning AT ettorebiondi seismicarrivaltimepickingondistributedacousticsensingdatausingsemisupervisedlearning AT jiaxuanli seismicarrivaltimepickingondistributedacousticsensingdatausingsemisupervisedlearning AT jiuxunyin seismicarrivaltimepickingondistributedacousticsensingdatausingsemisupervisedlearning AT zacharyeross seismicarrivaltimepickingondistributedacousticsensingdatausingsemisupervisedlearning AT zhongwenzhan seismicarrivaltimepickingondistributedacousticsensingdatausingsemisupervisedlearning |