DiTingMotion: A deep-learning first-motion-polarity classifier and its application to focal mechanism inversion

Frontiers in Earth Science

Earth Science

Miao Zhang¹  Yun Yang²  Lin Tang³  Zhuowei Xiao⁴  Shi Chen⁵  Ming Zhao⁶ 

[1] Department of Earth and Environmental Sciences, Dalhousie University, Halifax, NS, Canada;Earthquake Monitoring Centre, Jiangsu Earthquake Administration, Nanjing, China;Earthquake Monitoring Centre, Sichuan Earthquake Administration, Chengdu, China;Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing, China;Institute of Geophysics, China Earthquake Administration, Beijing, China;Beijing Baijiatuan Earth Sciences National Observation and Research Station, Beijing, China;Institute of Geophysics, China Earthquake Administration, Beijing, China;Beijing Baijiatuan Earth Sciences National Observation and Research Station, Beijing, China;Department of Earth and Environmental Sciences, Dalhousie University, Halifax, NS, Canada;

关键词: first motion polarity;    focal mechanism;    deep learning;    machine learning;    DiTing;    HASH;    Ridgecrest;   

DOI  :  10.3389/feart.2023.1103914

 received in 2022-11-21, accepted in 2023-02-27,  发布年份 2023

来源: Frontiers

【 摘 要 】

Accurate P-wave first-motion-polarity (FMP) information can contribute to solving earthquake focal mechanisms, especially for small earthquakes, to which waveform-based methods are generally inapplicable due to the computationally expensive high-frequency waveform simulations and inaccurate velocity models. In this paper, we propose a deep-learning-based method for the automatic determination of the FMPs, named “DiTingMotion”. DiTingMotion was trained with the P-wave FMP labels from the “DiTing” and SCSN-FMP datasets, and it achieved ∼97.8% accuracy on both datasets. The model maintains ∼83% accuracy on data labeled as “Emergent”, of which the FMP labels are challenging to identify for seismic analysts. Integrated with HASH, we developed a workflow for automated focal mechanism inversion using the FMPs identified by DiTingMotion and applied it to the 2019 M 6.4 Ridgecrest earthquake sequence for performance evaluation. In this case, DiTingMotion yields comparable focal mechanism results to that using manually determined FMPs by SCSN on the same data. The results proved that the DiTingMotion has a good generalization ability and broad application prospect in rapid earthquake focal mechanism inversion.

【 授权许可】

Unknown   
Copyright © 2023 Zhao, Xiao, Zhang, Yang, Tang and Chen.