Bi-directional Pre-trained Network for Single-station Seismic Waveform Analysis
The application of machine learning, particularly deep learning methods, is becoming increasingly widespread in seismology, achieving near-human accuracy in tasks such as phase detection and event classification. However, most neural network models in seismology currently focus on single tasks. Base...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editorial Office of Computerized Tomography Theory and Application
2025-01-01
|
| Series: | CT Lilun yu yingyong yanjiu |
| Subjects: | |
| Online Access: | https://www.cttacn.org.cn/cn/article/doi/10.15953/j.ctta.2024.162 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592356004593664 |
|---|---|
| author | Yuqi CAI Ziye YU Weitao WANG Yanru AN Lu LI |
| author_facet | Yuqi CAI Ziye YU Weitao WANG Yanru AN Lu LI |
| author_sort | Yuqi CAI |
| collection | DOAJ |
| description | The application of machine learning, particularly deep learning methods, is becoming increasingly widespread in seismology, achieving near-human accuracy in tasks such as phase detection and event classification. However, most neural network models in seismology currently focus on single tasks. Based on the CSNCD dataset released by the China Earthquake Networks Center, we have developed a bi-directional neural network pre-trained model for single-station data analysis. This model uses three-component seismic waveform data as input and employs convolutional neural networks and bi-directional Transformer models for feature extraction and processing. It not only performs routine tasks such as Pg, Sg, Pn and Sn phase detection, P-wave first-motion direction determination, and event type classification but can also be adapted to other seismic waveform data analysis tasks through transfer learning. |
| format | Article |
| id | doaj-art-6c0999c8874646d2a8faa3c2cf70e96a |
| institution | Kabale University |
| issn | 1004-4140 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Editorial Office of Computerized Tomography Theory and Application |
| record_format | Article |
| series | CT Lilun yu yingyong yanjiu |
| spelling | doaj-art-6c0999c8874646d2a8faa3c2cf70e96a2025-01-21T09:14:43ZengEditorial Office of Computerized Tomography Theory and ApplicationCT Lilun yu yingyong yanjiu1004-41402025-01-0134111111610.15953/j.ctta.2024.1622024-162Bi-directional Pre-trained Network for Single-station Seismic Waveform AnalysisYuqi CAI0Ziye YU1Weitao WANG2Yanru AN3Lu LI4Institute of Geophysics, China Earthquake Administration, Beijing 100081, ChinaInstitute of Geophysics, China Earthquake Administration, Beijing 100081, ChinaInstitute of Geophysics, China Earthquake Administration, Beijing 100081, ChinaChina Earthquake Networks Center, Beijing 100045, ChinaInstitute of Geophysics, China Earthquake Administration, Beijing 100081, ChinaThe application of machine learning, particularly deep learning methods, is becoming increasingly widespread in seismology, achieving near-human accuracy in tasks such as phase detection and event classification. However, most neural network models in seismology currently focus on single tasks. Based on the CSNCD dataset released by the China Earthquake Networks Center, we have developed a bi-directional neural network pre-trained model for single-station data analysis. This model uses three-component seismic waveform data as input and employs convolutional neural networks and bi-directional Transformer models for feature extraction and processing. It not only performs routine tasks such as Pg, Sg, Pn and Sn phase detection, P-wave first-motion direction determination, and event type classification but can also be adapted to other seismic waveform data analysis tasks through transfer learning.https://www.cttacn.org.cn/cn/article/doi/10.15953/j.ctta.2024.162deep learningphase detectionfirst-motion polarityevent classificationpre-trained model |
| spellingShingle | Yuqi CAI Ziye YU Weitao WANG Yanru AN Lu LI Bi-directional Pre-trained Network for Single-station Seismic Waveform Analysis CT Lilun yu yingyong yanjiu deep learning phase detection first-motion polarity event classification pre-trained model |
| title | Bi-directional Pre-trained Network for Single-station Seismic Waveform Analysis |
| title_full | Bi-directional Pre-trained Network for Single-station Seismic Waveform Analysis |
| title_fullStr | Bi-directional Pre-trained Network for Single-station Seismic Waveform Analysis |
| title_full_unstemmed | Bi-directional Pre-trained Network for Single-station Seismic Waveform Analysis |
| title_short | Bi-directional Pre-trained Network for Single-station Seismic Waveform Analysis |
| title_sort | bi directional pre trained network for single station seismic waveform analysis |
| topic | deep learning phase detection first-motion polarity event classification pre-trained model |
| url | https://www.cttacn.org.cn/cn/article/doi/10.15953/j.ctta.2024.162 |
| work_keys_str_mv | AT yuqicai bidirectionalpretrainednetworkforsinglestationseismicwaveformanalysis AT ziyeyu bidirectionalpretrainednetworkforsinglestationseismicwaveformanalysis AT weitaowang bidirectionalpretrainednetworkforsinglestationseismicwaveformanalysis AT yanruan bidirectionalpretrainednetworkforsinglestationseismicwaveformanalysis AT luli bidirectionalpretrainednetworkforsinglestationseismicwaveformanalysis |