Identifying Different Classes of Seismic Noise Signals Using Unsupervised Learning

Abstract

Proper classification of nontectonic seismic signals is critical for detecting microearthquakes and developing an improved understanding of ongoing weak ground motions. We use unsupervised machine learning to label five classes of nonstationary 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 s of continuous seismic records from a dense seismic array with 10–30 m station spacing. We show that dominate noise signals can be highly localized and vary on length scales of hundreds of 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 nontectonic sources.

Learning the Low Frequency Earthquake Activity on the Central San Andreas Fault

“…This produces 150 features per sensor and 750 features per 1 h time interval (3 channels ∗ 5 filters ∗ 10 statistics ∗ 5 sensors = 750 features). The original set of features were selected from previous analysis (C. W. Johnson et al., 2020; Rouet‐Leduc et al., 2018) and reduced to these 10 after model testing. Any missing waveforms are represented as a vector of 150 not‐a‐number values.…”

Graph-partitioning based convolutional neural network for earthquake detection using a seismic array

“…It is thus necessary to develop an appropriate classification method for noise signals before applying the supervised learning. Such idea would be implemented in combination with an unsupervised learning (Johnson et al, 2020).…”

Relation Extraction for Coal Mine Safety Information Using Recurrent Neural Networks with Bidirectional Minimal Gated Unit

“…Then, use the largest pooling operation to get the most significant feature representation. max( ) = dF (16) Among them, d is the overall characteristics of the text after pooling. Since the feature dimension after pooling is fixed, the problem of different lengths of text sentences can be solved.…”

“…The semi-supervised learning approches have a poor portability and is not suitable for coal mine safety data, since the accuracy of information extraction depends on the quality of the initial relation seed [15]. The unsupervised learning approches need to analyze and post-process the extraction results, and the clustering threshold cannot be determined in advance [16]. The open extraction approaches map relation instances to texts by means of external knowledge bases such as DBPedia, OpenCyc and YAGO [17].…”