Localizing microseismic events on field data using a U-Net-based convolutional neural network trained on synthetic data

Abstract

Hydraulic fracturing (HF) plays an important role when it comes to the extraction of resources in unconventional reservoirs. The microseismic activity arising during HF operations needs to be monitored to improve productivity and to make decisions about mitigation measures. Recently, deep-learning methods have been investigated to localize earthquakes given field-data waveforms as input. For optimal results, these methods require large field data sets that cover the entire region of interest. In practice, such data sets often are scarce. To overcome this shortcoming, we have initially used a (large) synthetic data set with full waveforms to train a U-Net that reconstructs the source location as a 3D Gaussian distribution. As a field data set for our study, we use data recorded during HF operations in Texas. Synthetic waveforms are modeled using a velocity model from the site that is also used for a conventional diffraction-stacking (DS) approach. To increase the U-Nets’ ability to localize seismic events, we augment the synthetic data with different techniques, including the addition of field noise. We select the best performing U-Net using 22 events that have previously been identified to be confidently localized by DS and apply that U-Net to all 1245 events. We compare our predicted locations to DS and the DS locations refined by a relative location (DSRL) method. The U-Net-based locations are better constrained in depth compared to DS and the mean hypocenter difference with respect to DSRL locations is 163 m. This indicates potential for the use of synthetic data to complement or replace field data for training. Furthermore, after training, the method returns the source locations in near real time given the full waveforms, alleviating the need to pick arrival times.