Bidirectional recurrent neural networks for seismic event detection
This work provides a more accurate and efficient real-time seismic event detection method for safety-critical monitoring applications, improving upon the limitations of existing techniques.
This paper addresses the problem of real-time, accurate passive seismic event detection, which is crucial for monitoring applications like reservoir stability and volcanic tremor. The authors propose a deep learning approach using a bi-directional LSTM neural network trained on synthetic traces. This method significantly outperforms the traditional STA/LTA trigger in both correctly detected arrivals and reducing false positives, processing 600 traces in real-time on a single processing unit.
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.