摘要
在实时地震监测中,地震P波(primary wave)的初动拾取任务具有至关重要的作用,其有助于地震应急响应的及时实施.虽然此前在该领域已开展了大量的研究,但是如何从地震分布密集并且充满噪声的监测波形中有效地识别出P波仍然是一个具有挑战性的任务.例如对于大地震的余震监测,实践中使用的普遍方法仍依赖于专家辅助标注.本文针对地震实时监测任务,基于集成学习策略,提出一个全新的技术框架——EL-Picker,实现从连续地震波形中自主拾取P波的初动到时.具体而言,EL-Picker包含3个模块,即触发器、分类器和精化器.其中,分类器模块借鉴集成学习策略,实现对多个个体学习器的整合,提升整体模型性能.基于汶川Ms8.0地震的余震数据集进行的大量实验,我们发现EL-Picker不仅较好地实现P波初动拾取效果,并且多诊断出120%被人工遗漏的地震P波.同时,实验结果也启发我们探索如何针对不同的地震站台选取个性化的个体学习器构建分类器模块.此外,我们进一步地讨论了被人工遗漏的地震波形的规律特点,用于指导人工地震标注.这些发现清晰地验证了EL-Picker框架的鲁棒性、时效性、灵活性以及稳定性.
Identifying the arrival times of seismic P-phases plays a significant role in real-time seismic monitoring,which provides critical guidance for emergency response activities.While considerable research has been conducted on this topic,efficiently capturing the arrival times of seismic P-phases hidden within intensively distributed and noisy seismic waves,such as those generated by the aftershocks of destructive earthquakes,remains a real challenge since most common existing methods in seismology rely on laborious expert supervision.To this end,in this paper,we present a machine learning-enhanced framework based on ensemble learning strategy,EL-Picker,for the automatic identification of seismic P-phase arrivals on continuous and massive waveforms.More specifically,EL-Picker consists of three modules,namely,Trigger,Classifier,and Refiner,and an ensemble learning strategy is exploited to integrate several machine learning classifiers.An evaluation of the aftershocks following the Ms 8.0 Wenchuan earthquake demonstrates that EL-Picker can not only achieve the best identification performance but also identify 120%more seismic P-phase arrivals as complementary data.Meanwhile,experimental results also reveal both the applicability of different machine learning models for waveforms collected from different seismic stations and the regularities of seismic P-phase arrivals that might be neglected during the manual inspection.These findings clearly validate the effectiveness,efficiency,flexibility,and stability of EL-Picker.
作者
申大忠
张琦
徐童
祝恒书
赵雯佳
殷子凯
周培伦
房立华
陈恩红
熊辉
Dazhong SHEN;Qi ZHANG;Tong XU;Hengshu ZHU;Wenjia ZHAO;Zikai YIN;Peilun ZHOU;Lihua FANG;Enhong CHEN;Hui XIONG(School of Computer Science and Technology,University of Science and Technology of China,Hefei 230022,China;Baidu Online Network Technology(Beijing)Co.,Ltd.,Beijing 100085,China;Institute of Geology,China Earthquake Administration,Beijing 100029,China;Institute of Geophysics,China Earthquake Administration,Beijing 100081,China;Rutgers,the State University of New Jersey,Newark NJ 07102,USA)
出处
《中国科学：信息科学》
CSCD
北大核心
2021年第6期912-926,共15页
Scientia Sinica(Informationis)
基金
国家重点研发计划(批准号:2018YFB1002600)
国家自然科学基金(批准号:91746301,71531001,61703386,U1605251)资助项目。
关键词
P波拾取
机器学习
集成学习
汶川余震
实时地震监测
P-phase picker
machine learning
ensemble learning
Wenchuan aftershocks
real-time seismic monitoring
