PSSegNet: Segmenting the P- and S-Phases in Microseismic Signals through Deep Learning
Microseismic P- and S-phase segmentation is an influential step that limits the accuracy of event location, parameter inversion, and mechanism analysis. Therefore, an improved Unet named PSSegNet is proposed to intelligently segment the P- and S-phases. The designed masks are used as the outputs of...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/1/130 |
| _version_ | 1797358480155213824 |
|---|---|
| author | Zhengxiang He Xingliang Xu Dijun Rao Pingan Peng Jiaheng Wang Suchuan Tian |
| author_facet | Zhengxiang He Xingliang Xu Dijun Rao Pingan Peng Jiaheng Wang Suchuan Tian |
| author_sort | Zhengxiang He |
| collection | DOAJ |
| description | Microseismic P- and S-phase segmentation is an influential step that limits the accuracy of event location, parameter inversion, and mechanism analysis. Therefore, an improved Unet named PSSegNet is proposed to intelligently segment the P- and S-phases. The designed masks are used as the outputs of PSSegNet, which is used to obtain the time–frequency features of the P- and S-phases. As a result, the MSE (mean square error) between the predicted mask and the actual labeled mask is concentrated below 2.5, and the AE (accumulated error) of the reconstructed P/S-phase based on the predicted mask is concentrated below 1.0 × 10<sup>−3</sup>. Arrival picking results show that the overall error of the entire test set is less than 50 ms and most of the errors are less than 20 ms. Data with SNR (signal to noise ratio) < 2, 2 ≤ SNR < 3, PSR (P-phase to S-phase ratio) < 1, or 1 ≤ PSR < 2 in the dataset were selected for arrival picking and their errors were counted. The statistical results show that PSSegNet is robust at low SNR and PSR. The P- and S-phase segmentation based on PSSegNet has excellent potential for use in various applications and can effectively reduce the difficulty of obtaining the P/S-phase arrivals. |
| first_indexed | 2024-03-08T15:02:40Z |
| format | Article |
| id | doaj.art-a64d7c8929ea423582f28930008a9c40 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-08T15:02:40Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-a64d7c8929ea423582f28930008a9c402024-01-10T15:03:42ZengMDPI AGMathematics2227-73902023-12-0112113010.3390/math12010130PSSegNet: Segmenting the P- and S-Phases in Microseismic Signals through Deep LearningZhengxiang He0Xingliang Xu1Dijun Rao2Pingan Peng3Jiaheng Wang4Suchuan Tian5State Key Laboratory for Fine Exploration and Intelligent Development of Coal Resources, China University of Mining and Technology, Xuzhou 221116, ChinaState Key Laboratory for Fine Exploration and Intelligent Development of Coal Resources, China University of Mining and Technology, Xuzhou 221116, ChinaZijin Mining Group Co., Ltd., Longyan 364200, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410083, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410083, ChinaState Key Laboratory for Fine Exploration and Intelligent Development of Coal Resources, China University of Mining and Technology, Xuzhou 221116, ChinaMicroseismic P- and S-phase segmentation is an influential step that limits the accuracy of event location, parameter inversion, and mechanism analysis. Therefore, an improved Unet named PSSegNet is proposed to intelligently segment the P- and S-phases. The designed masks are used as the outputs of PSSegNet, which is used to obtain the time–frequency features of the P- and S-phases. As a result, the MSE (mean square error) between the predicted mask and the actual labeled mask is concentrated below 2.5, and the AE (accumulated error) of the reconstructed P/S-phase based on the predicted mask is concentrated below 1.0 × 10<sup>−3</sup>. Arrival picking results show that the overall error of the entire test set is less than 50 ms and most of the errors are less than 20 ms. Data with SNR (signal to noise ratio) < 2, 2 ≤ SNR < 3, PSR (P-phase to S-phase ratio) < 1, or 1 ≤ PSR < 2 in the dataset were selected for arrival picking and their errors were counted. The statistical results show that PSSegNet is robust at low SNR and PSR. The P- and S-phase segmentation based on PSSegNet has excellent potential for use in various applications and can effectively reduce the difficulty of obtaining the P/S-phase arrivals.https://www.mdpi.com/2227-7390/12/1/130microseismicdeep learningsegmentationP- and S-phasesignal processing |
| spellingShingle | Zhengxiang He Xingliang Xu Dijun Rao Pingan Peng Jiaheng Wang Suchuan Tian PSSegNet: Segmenting the P- and S-Phases in Microseismic Signals through Deep Learning Mathematics microseismic deep learning segmentation P- and S-phase signal processing |
| title | PSSegNet: Segmenting the P- and S-Phases in Microseismic Signals through Deep Learning |
| title_full | PSSegNet: Segmenting the P- and S-Phases in Microseismic Signals through Deep Learning |
| title_fullStr | PSSegNet: Segmenting the P- and S-Phases in Microseismic Signals through Deep Learning |
| title_full_unstemmed | PSSegNet: Segmenting the P- and S-Phases in Microseismic Signals through Deep Learning |
| title_short | PSSegNet: Segmenting the P- and S-Phases in Microseismic Signals through Deep Learning |
| title_sort | pssegnet segmenting the p and s phases in microseismic signals through deep learning |
| topic | microseismic deep learning segmentation P- and S-phase signal processing |
| url | https://www.mdpi.com/2227-7390/12/1/130 |
| work_keys_str_mv | AT zhengxianghe pssegnetsegmentingthepandsphasesinmicroseismicsignalsthroughdeeplearning AT xingliangxu pssegnetsegmentingthepandsphasesinmicroseismicsignalsthroughdeeplearning AT dijunrao pssegnetsegmentingthepandsphasesinmicroseismicsignalsthroughdeeplearning AT pinganpeng pssegnetsegmentingthepandsphasesinmicroseismicsignalsthroughdeeplearning AT jiahengwang pssegnetsegmentingthepandsphasesinmicroseismicsignalsthroughdeeplearning AT suchuantian pssegnetsegmentingthepandsphasesinmicroseismicsignalsthroughdeeplearning |