Performance Review of a Real-Time Machine Learning Based Seismic Catalog Generator in Production
A. Reynen, S. Karimi, D. Baturan and B. Witten
Event name: 81st EAGE Conference and Exhibition 2019
Session: Micro and Passive Seismic I
Publication date: 03 June 2019
Info: Extended abstract, PDF ( 656.18Kb )
Price: € 20
As machine learning algorithms can be prone to overfitting, the ability to them generalize for use in a real-time system for seismic event detection and location is critical. In this study, we focus on the temporal stability of a real-time automatic seismic catalog generator algorithm (Feature Weighted Beamforming, FWB) which has been applied on over 15 networks over a one year period in a production environment. We present detailed results from an induced seismic monitoring array over the Duvernay Formation (Duvernay Subscriber Array, DSA), as well as some higher level statistics on other seismic networks. The initial results from DSA in comparison to standard STA/LTA picking and associations show that FWB reduced the number of false positives by 75% without loss of sensitivity, it also reduced the average difference in the event location between automatic and manually picked solutions by 82%. Similar to DSA, for all networks which included a large variety of training data FWB demonstrated consistent detection of all real seismic events compared to a sensitive STA/LTA pick associator regarding system sensitivity and location accuracy. New clusters of seismic activity not seen during training are also correctly detected and located.