Data-Driven Signal–Noise Classification for Microseismic Data Using Machine Learning

It is necessary to monitor, acquire, preprocess, and classify microseismic data understand active faults or other causes of earthquakes, thereby facilitating the preparation early-warning earthquake systems. Accordingly, this study proposes application machine learning for signal–noise classification from Pohang, South Korea. For first time, unique were obtained monitoring system borehole station PHBS8 located in Yongcheon-ri, Pohang region, while hydraulic stimulation was being conducted. The collected properly preprocessed utilized as training test supervised unsupervised methods: random forest, convolutional neural network, K-medoids clustering with fast Fourier transform. methods showed 100% 97.4% accuracy data, respectively. method 97.0% accuracy. Consequently, results validated that automation based on proposed applications can acquired real time.