oa A Deep Learning Approach for Microseismic Detection with Downhole DAS

Distributed Acoustic Sensing (DAS) enables efficient seismic data acquisition for permanent and passive micro-seismic monitoring, especially using permanent downhole installations. However, acquiring large amounts of data pushes against the limits of existing computational systems and algorithms, especially for continuous passive seismic monitoring applications. Thus, more than ever, novel methods to analyse big data are required. In this abstract, we investigate using a supervised deep learning neural network to detect and locate microseismic events due to CO2 injection. The challenges of using synthetic data to train the neural network were identified and addressed to fill the gap in the context of a microseismic application. The methodology was demonstrated on synthetic data and tested on data from the Otway CO2 injection site. More tests were performed to confirm the observed effects of including time shifts in the training data. Those enlightening results pave the way for a more extensive study and potential applications to more field data.