Integrated Detection and Classification of Low-Frequency Earthquakes Using a PhaseNet-Based Deep Learning Framework
Abstract
Abstract This study develops a deep learning–based framework for detecting and classifying low-frequency earthquakes (LFEs) and ordinary earthquakes using continuous seismic waveform data. We extend the PhaseNet architecture to a five-class model that predicts probabilities for P and S phases of both ordinary earthquakes and LFEs, as well as noise. The model is trained using waveforms associated with manually determined hypocenters from the Japan Meteorological Agency (JMA) unified catalog for 2014–2022. The trained model is then applied to continuous waveform data for automatic phase picking, phase association, and event location. To evaluate the likelihood that each detected event is an LFE, we further introduce a quantitative index, called LFE-likeness (LIKE), based on the median LP and LS probability scores at the stations used for event location, where LP and LS correspond to LFE P- and S-phase probabilities, respectively. This approach enables detection and classification of seismic events within a unified framework. Application to seismic activity in northern Yamaguchi Prefecture from February to April 2025 shows that the proposed method detects more than twice as many events as the JMA catalog, including many small events not previously identified. The proposed framework provides a robust and scalable approach for integrated seismic monitoring, improving the detection of weak events and offering new insights into fluid-related seismic processes in the deep crust.
Read the paper
Related studies
- Current state and future directions for deep learning based automatic seismic fault interpretation: A systematic review
- Physics of Partially Saturated Porous Media: Residual Saturation and Seismic-Wave Propagation
- Modern Imaging Using Seismic Reflection Data
- Effects of marine seismic surveys on free-ranging fauna: a systematic literature review
- A review of the recent seismic activity in the southern part of egypt (upper egypt)
- A review of research on mechanism of seismic attenuation and energy compensation
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.