Bidirectional recurrent neural networks for seismic event detection

Abstract

Real time, accurate passive seismic event detection is a critical safety measure across a range of monitoring applications from reservoir stability to carbon storage to volcanic tremor detection. The most common detection procedure remains the Short-Term-Average to Long-Term-Average (STA/LTA) trigger despite its common pitfalls of requiring a signal-to-noise ratio greater than one and being highly sensitive to the trigger parameters. Whilst numerous alternatives have been proposed, they often are tailored to a specific monitoring setting and therefore cannot be globally applied, or they are too computationally expensive therefore cannot be run real time. This work introduces a deep learning approach to event detection that is an alternative to the STA/LTA trigger. A bi-directional, long-short-term memory, neural network is trained solely on synthetic traces. Evaluated on synthetic and field data, the neural network approach significantly outperforms the STA/LTA trigger both on the number of correctly detected arrivals as well as on reducing the number of falsely detected events. Its real time applicability is proven with 600 traces processed in real time on a single processing unit.Recently, Machine Learning (ML) methodologies, in particular Deep Learning (DL), has seen a resurgence across all fields of seismology, and wider geoscience applications. The majority of applications have focused on the adaptation of computer vision approaches for aiding seismic interpretation. For example, salt body detection [8], fault detection [9], and horizon detection [10]. However, other studies have considered how ML methodologies can be utilised for seismic event detection. [11] proposed the combination of convolutional Neural Networks (NN) with k-means clustering for detection of seismic arrivals, whilst [12] presents one of the earliest studies that considered using NNs for event detection on broadband seismometers. Novelly, they combined three different back-propagation NNs that