PhaseNet: a deep-neural-network-based seismic arrival-time picking method
PhaseNet: a deep-neural-network-based seismic arrival-time picking method
复制标题
DOI：
10.1093/gji/ggy423
复制
发表时间：
2019-01-01
影响因子：
2.8
通讯作者：
Beroza, Gregory C.
中科院分区：
文献类型：
--
作者：
Zhu, Weiqiang;Beroza, Gregory C.
随着地震传感器的数量的增长，分析师手动和全面选择地震阶段变得越来越困难，但是这种努力对地震监测至关重要。尽管自动拾取了多年的改进，但很难与经验丰富的分析师的表现相匹配。一个更微妙的问题是，不同的地震分析师可能以不同的方式选择阶段，这可能会将偏见引入地震位置。我们提出了一种名为“ phasenet”的基于深神经网络的到达时间采摘方法，该方法选择了P和S波的到达时间。深度神经网络最近在功能学习方面取得了迅速的进步，并且通过足够的培训，在许多应用中都取得了超人的表现。 Phasenet使用三成分的地震波形作为输入，并生成P到达，S到达和噪声作为输出的概率分布。我们设计的含量使概率分布中的峰值为P和S波提供了准确的到达时间。 Phasenet受到了来自北加州地震数据中心分析师标签的P和S到达时间提供的巨大可用数据集的培训。我们使用的数据集包含超过30年地震记录中提取的700 000多个波形样本。我们证明，当应用于已知地震的波形时，Phasenet的拾取精度和召回率比现有方法高得多，这有可能大幅度地增加S波观测值的数量，而不是当前可用的观测值。这将既可以改进位置和改进的剪切波速度模型。
As the number of seismic sensors grows, it is becoming increasingly difficult for analysts to pick seismic phases manually and comprehensively, yet such efforts are fundamental to earthquake monitoring. Despite years of improvements in automatic phase picking, it is difficult to match the performance of experienced analysts. A more subtle issue is that different seismic analysts may pick phases differently, which can introduce bias into earthquake locations. We present a deep-neural-network-based arrival-time picking method called "PhaseNet" that picks the arrival times of both P and S waves. Deep neural networks have recently made rapid progress in feature learning, and with sufficient training, have achieved super-human performance in many applications. PhaseNet uses three-component seismic waveforms as input and generates probability distributions of P arrivals, S arrivals and noise as output. We engineer PhaseNet such that peaks in the probability distributions provide accurate arrival times for both P and S waves. PhaseNet is trained on the prodigious available data set provided by analyst-labelled P and S arrival times from the Northern California Earthquake Data Center. The data set we use contains more than 700 000 waveform samples extracted from over 30 yr of earthquake recordings. We demonstrate that PhaseNet achieves much higher picking accuracy and recall rate than existing methods when applied to the waveforms of known earthquakes, which has the potential to increase the number of S-wave observations dramatically over what is currently available. This will enable both improved locations and improved shear wave velocity models.