Full text loading...
-
Event Detection and Phase Picking Based on Deep Convolutional Neural Networks
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 80th EAGE Conference and Exhibition 2018, Jun 2018, Volume 2018, p.1 - 5
Abstract
Summary
Manual picking of seismic events on continuous waveforms faces a challenge from the increasing volume of data recorded on modern seismic arrays with many receivers. Traditional automatic picking methods use knowledge about manual picks to design a statistical model that should generalize to unseen data. We propose to use convolutional neural networks (CNN) trained on the seismic waveform to learn such a model directly from labeled manual picks. Processing of field data from the Wenchuan earthquake shows the proposed method is accurate in finding arrival times and determining their phases. Due to its efficiency, this process can be developed for real-time processing.
© EAGE Publications BV