Accurate identification and picking of P- and S-wave arrivals is important in earthquake and exploration seismology. Often, existing algorithms are lacking in automation, multiphase classification and picking, as well as performance accuracy. We have developed a new fully automated four-step workflow for efficient classification and picking of P- and S-wave arrival times on microseismic data sets. First, time intervals with possible arrivals on waveform recordings are identified using the fuzzy c-means clustering algorithm. Second, these intervals are classified as corresponding to P-, S-, or unidentified waves using the polarization attributes of the waveforms contained within. Third, the P-, S-, and unidentified-waves arrival times are picked using the Akaike information criterion picker on the corresponding intervals. Fourth, unidentified waves are classified as P or S based on the arrivals moveouts. The application of the workflow on synthetic and real microseismic data sets indicates that it yields accurate arrival picks for high and low signal-to-noise ratio waveforms.

中文翻译：

---

基于无监督机器学习分类和内容信息分析的自动地震相位拾取

准确识别和拾取 P 波和 S 波到达在地震和勘探地震学中很重要。通常，现有算法缺乏自动化、多阶段分类和拣选以及性能准确性。我们开发了一种全新的全自动四步工作流程，用于对微震数据集的 P 波和 S 波到达时间进行有效分类和挑选。首先，使用模糊c识别可能到达波形记录的时间间隔-means 聚类算法。其次，使用包含在其中的波形的极化属性，这些间隔被分类为对应于 P-、S- 或未识别的波。第三，使用 Akaike 信息准则选择器在相应的间隔上选择 P 波、S 波和未识别波到达时间。第四，根据到达时差将未识别的波分类为 P 或 S。该工作流在合成和真实微震数据集上的应用表明，它可以为高和低信噪比波形产生准确的到达拾取。