Seismic phase recognition model with low SNR based on U-net

Aiming at the problem of low recognition accuracy and high missed detection rate of seismic phase recognition of low signal-to-noise ratio seismic signals, a new seismic phase recognition model UBAN (U-net-Bidirectional Gated Recurrent Unit-Attention Network) is designed based on U-net neural networ...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianxian Cai, Zhongjie Sun, Mengying Zhang, Fenfen Yan, Li Wang, Ling Li
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Geomatics, Natural Hazards & Risk
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/19475705.2025.2481992
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850205347179921408
author Jianxian Cai
Zhongjie Sun
Mengying Zhang
Fenfen Yan
Li Wang
Ling Li
author_facet Jianxian Cai
Zhongjie Sun
Mengying Zhang
Fenfen Yan
Li Wang
Ling Li
author_sort Jianxian Cai
collection DOAJ
description Aiming at the problem of low recognition accuracy and high missed detection rate of seismic phase recognition of low signal-to-noise ratio seismic signals, a new seismic phase recognition model UBAN (U-net-Bidirectional Gated Recurrent Unit-Attention Network) is designed based on U-net neural network framework, combined with Bi-GRU bidirectional gated recurrent unit and Attention attention mechanism. In this model, Bi-GRU bidirectional gated recurrent unit and Attention attention mechanism are added between the U-net coding layer and the decoding layer. Bi-GRU is suitable for processing long time series signals,and attention mechanism is used to pay attention to the time series characteristics of seismic phases, ignoring the advantages of useless features such as noise and peaks, improving the network ‘s ability to perceive the arrival time characteristics and improving the recognition accuracy. The seismic data of Stanford University are used to train and test the designed UBAN phase recognition model. The experimental results show that the UBAN phase recognition model shows good performance in the phase recognition of low signal-to-noise ratio seismic signals, which provides a new idea for the research of low signal-to-noise ratio seismic signal phase recognition method.
format Article
id doaj-art-c5ff67eceb7b4556be1db91c0e6780ec
institution OA Journals
issn 1947-5705
1947-5713
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Geomatics, Natural Hazards & Risk
spelling doaj-art-c5ff67eceb7b4556be1db91c0e6780ec2025-08-20T02:11:08ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132025-12-0116110.1080/19475705.2025.2481992Seismic phase recognition model with low SNR based on U-netJianxian Cai0Zhongjie Sun1Mengying Zhang2Fenfen Yan3Li Wang4Ling Li5Institute of Disaster Prevention, Sanhe, Hebei, ChinaInstitute of Disaster Prevention, Sanhe, Hebei, ChinaInstitute of Disaster Prevention, Sanhe, Hebei, ChinaInstitute of Disaster Prevention, Sanhe, Hebei, ChinaInstitute of Disaster Prevention, Sanhe, Hebei, ChinaInstitute of Disaster Prevention, Sanhe, Hebei, ChinaAiming at the problem of low recognition accuracy and high missed detection rate of seismic phase recognition of low signal-to-noise ratio seismic signals, a new seismic phase recognition model UBAN (U-net-Bidirectional Gated Recurrent Unit-Attention Network) is designed based on U-net neural network framework, combined with Bi-GRU bidirectional gated recurrent unit and Attention attention mechanism. In this model, Bi-GRU bidirectional gated recurrent unit and Attention attention mechanism are added between the U-net coding layer and the decoding layer. Bi-GRU is suitable for processing long time series signals,and attention mechanism is used to pay attention to the time series characteristics of seismic phases, ignoring the advantages of useless features such as noise and peaks, improving the network ‘s ability to perceive the arrival time characteristics and improving the recognition accuracy. The seismic data of Stanford University are used to train and test the designed UBAN phase recognition model. The experimental results show that the UBAN phase recognition model shows good performance in the phase recognition of low signal-to-noise ratio seismic signals, which provides a new idea for the research of low signal-to-noise ratio seismic signal phase recognition method.https://www.tandfonline.com/doi/10.1080/19475705.2025.2481992Seismic phase recognitionU-net (U-shaped neural network)Bi-GRU (bidirectional-gated recurrent unit)attention mechanismseismic phase with low SNR
spellingShingle Jianxian Cai
Zhongjie Sun
Mengying Zhang
Fenfen Yan
Li Wang
Ling Li
Seismic phase recognition model with low SNR based on U-net
Geomatics, Natural Hazards & Risk
Seismic phase recognition
U-net (U-shaped neural network)
Bi-GRU (bidirectional-gated recurrent unit)
attention mechanism
seismic phase with low SNR
title Seismic phase recognition model with low SNR based on U-net
title_full Seismic phase recognition model with low SNR based on U-net
title_fullStr Seismic phase recognition model with low SNR based on U-net
title_full_unstemmed Seismic phase recognition model with low SNR based on U-net
title_short Seismic phase recognition model with low SNR based on U-net
title_sort seismic phase recognition model with low snr based on u net
topic Seismic phase recognition
U-net (U-shaped neural network)
Bi-GRU (bidirectional-gated recurrent unit)
attention mechanism
seismic phase with low SNR
url https://www.tandfonline.com/doi/10.1080/19475705.2025.2481992
work_keys_str_mv AT jianxiancai seismicphaserecognitionmodelwithlowsnrbasedonunet
AT zhongjiesun seismicphaserecognitionmodelwithlowsnrbasedonunet
AT mengyingzhang seismicphaserecognitionmodelwithlowsnrbasedonunet
AT fenfenyan seismicphaserecognitionmodelwithlowsnrbasedonunet
AT liwang seismicphaserecognitionmodelwithlowsnrbasedonunet
AT lingli seismicphaserecognitionmodelwithlowsnrbasedonunet