1.Key Lab of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin Heilongjiang 150080, China
2.Key Laboratory of Earthquake Disaster, Mitigation of Emergency Management, Harbin Heilongjiang 150080, China
To address the issues of weak anti-interference capability and low picking accuracy in traditional automatic picking methods of P-wave first-arrival, a real-time automatic picking method of P-wave first-arrival based on Extreme Gradient Boosting Trees (XGBoost) is proposed. First, 4 characteristic parameters that were conducive to distinguishing seismic signals from background noise were selected as the model's input to reduce complexity of the model. Subsequently, an XGBoost model for automatic picking of P-wave first-arrival was constructed, trained, and tested. Finally, the model's effectiveness was validated by comparing it with commonly used real-time identification methods of P-wave first-arrival in current earthquake early warning systems. The results indicated that the proposed method achieved a picking sample proportion of 93.3% within an error range of ±0.5 s, outperforming both the Energy Periodic Dual Parameter Picking (EDP-Picker) method and the Short-Term Average/Long-Term Average (STA/LTA) ratio method, the picking sample proportion of which was 91.9% and 83.6%, respectively. When the error exceeded ±0.5 s, the proportion of early-triggered and lag-triggered samples of the XGBoost method was 4.27% and 5.26%, respectively, while the corresponding proportion of EDP-Picker was 5.03% and 6.50%, respectively, and that of STA/LTA was 5.39% and 1.71%, respectively. Compared with 2 traditional methods, the overall performance of XGBoost method was significantly enhanced, along with superior identification accuracy and stronger anti-interference capability, meeting picking demands with greater stability in complex scenarios.
LUJianqi, LIShanyou, XIEZhinan, et al. Real-Time Evolutionary Earthquake Location Method and Its Uncertainty Analysis [J]. Journal of Natural Disasters, 2021, 30 (3): 52-62. in Chinese
WANGZifa, LIAOJi’an, WANGYanwei, et al. A Fast Magnitude Estimation Method Based on Deep Convolutional Neural Networks [J]. Chinese Journal of Geophysics, 2023, 66 (1): 272-288. in Chinese
YANGChangwei, ZHANGKaiwen, WUDongsheng, et al. Fast Magnitude Estimation Method for High-Speed Railway Earthquake Early Warning System Based on P-Wave 2 s Power Information [J]. Journal of the China Railway Society, 2024, 46 (7): 167-173. in Chinese
WANGZijun, ZHAOBoming. Rapid and Accurate Prediction Method for Magnitude in Earthquake Early Warning for High Speed Railway [J]. China Railway Science, 2017, 38 (2): 127-132. in Chinese
SONGJindong, ZHUJingbao, LIUYanqiong, et al. On-Site Earthquake Early Warning Method for High-Speed Railway Based on Support Vector Machine Prediction Models [J]. China Railway Science, 2022, 43 (5): 177-187. in Chinese
[11]
ROSSZ E, MEIERM, HAUKSSONE. P Wave Arrival Picking and First-Motion Polarity Determination with Deep Learning [J]. Journal of Geophysical Research: Solid Earth, 2018, 123 (6): 5120-5129.
[12]
ANANTK S, DOWLAF U. Wavelet Transform Methods for Phase Identification in Three-Component Seismograms [J]. Bulletin of the Seismological Society of America, 1997, 87 (6): 1598-1612.
[13]
HILDYARDM W, NIPPRESSS E, RIETBROCKA. Event Detection and Phase Picking Using a Time-Domain Estimate of Predominate Period Tpd [J]. Bulletin of the Seismological Society of America, 2008, 98 (6): 3025-3032.
[14]
ROSSZ E, YUEY, MEIERM A, et al. PhaseLink: a Deep Learning Approach to Seismic Phase Association [J]. Journal of Geophysical Research: Solid Earth, 2019, 124 (1): 856-869.
[15]
ZHUW, BEROZAG C. PhaseNet: a Deep-Neural-Network-Based Seismic Arrival-Time Picking Method [J]. Geophysical Journal International, 2019, 216 (1): 261-273.
LIJian, WANGXiaoming, ZHANGYinghai, et al. Research on Seismic Phase Picking Method Based on Deep Convolutional Neural Network [J]. Chinese Journal of Geophysics, 2020, 63 (4): 1591-1606. in Chinese
[18]
ALLENR. Automatic Phase Pickers: Their Present Use and Future Prospects [J]. Bulletin of the Seismological Society of America, 1982, 72 (6B): S225-S242.
MAQiang, JINXing, LIShanyou, et al. Automatic P-Arrival Detection for Earthquake Early Warning [J]. Chinese Journal of Geophysics, 2013, 56 (7): 2313-2321. in Chinese
[21]
SARAGIOTISC D, HADJILEONTIADISL J, PANASS M. PAI-S/K: a Robust Automatic Seismic P Phase Arrival Identification Scheme [J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40 (6): 1395-1404.
[22]
GALIANA-MERINOJ J, ROSA-HERRANZJ L, PAROLAIS. Seismic P Phase Picking Using a Kurtosis-Based Criterion in the Stationary Wavelet Domain [J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46 (11): 3815-3826.
[23]
LUJ Q, LIS Y, XIEZ N, et al. Energy-and Predominant-Period-Dependent P-Wave Onset Picker (EDP-Picker) [J]. Seismological Research Letters, 2020, 91 (4): 2355-2367.
[24]
CHENT Q, GUESTRINC. XGBoost: a Scalable Tree Boosting System [C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California, USA: ACM, 2016: 785-794.
WANGHaoyu, FUGuoyong, LILi, et al. A Spatial Precipitation Distribution Prediction Model for Chinese Regions Based on Xgboost + GWR Algorithm [J]. Water Resources and Power, 2021, 39 (12): 7-11. in Chinese