Transfer Learning-Based Seismic Phase Detection Algorithm for Distributed Acoustic Sensing Microseismic Data

• Published in: IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-12
• Main Authors: Choi, Yonggyu, Seol, Soon Jee, Byun, Joongmoo
• Format: Article
• Language: English
• Subjects: Acoustic imagery; Algorithms; Boreholes; Data acquisition; Data models; Datasets; Distributed acoustic sensing (DAS); Earthquakes; event detection; Machine learning; machine learning (ML); microseismic; Microseisms; Monitoring; P waves; Phase detection; Phase measurement; phase picking; S waves; Seismic activity; Seismic data; Seismic measurements; Signal to noise ratio; Supervised learning; Training; Training data; Transfer learning; transfer learning (TL); Transformers
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2024.3469268

Seismic event and phase detection are fundamental techniques for analyzing earthquake events and microseismic data. Recently, machine learning (ML) methods have been used to enhance the speed and precision of these processes. However, the application of ML to microseismic data acquired with distributed acoustic sensing (DAS) systems is challenging because there are insufficient labeled data for training. To address this issue, we propose a novel seismic phase detection algorithm based on transfer learning (TL) that is applicable to DAS microseismic data. This study modified an ML model that detects the phases of P- and S-waves of earthquake data for TL application. The generalized phase detection (GPD) model was trained using the Stanford earthquake dataset (STEAD) of globally acquired seismic data. TL begins with the weights of this trained model, and the TL model is fine-tuned using the small amount of labeled borehole DAS microseismic data available from the Utah FORGE dataset; two events that occurred in the initial DAS recording are labeled and used as training data for TL. The proposed method exhibited superior phase detection, even for S-waves, when tested on other microseismic events. The proposed method also had better general phase detection performance than a conventional supervised learning method using only DAS microseismic data.