资源环境科技发展态势分析平台

Pr^{11 †}Now at Los Alamos National Laboratory
oper classification of non‐tectonic seismic signals is critical for detecting microearthquakes and developing an improved understanding of ongoing weak ground motions. We use unsupervised machine learning to label 5 classes of non‐stationary seismic noise common in continuous waveforms. Temporal and spectral features describing the data are clustered to identify separable types of emergent and impulsive waveforms. The trained clustering model is used to classify every 1 second of continuous seismic records from a dense seismic array with 10‐30 m station spacing. We show dominate noise signals can be highly localized and vary on length scales of 100’s meters. The methodology demonstrates the complexity of weak ground motions and improves the standard of analyzing seismic waveforms with a low signal‐to‐noise ratio. Application of this technique will improve the ability to detect genuine microseismic events in noisy environments where seismic sensors record earthquake‐like signals originating from non‐tectonic sources.