The confluence of our ability to handle big data, significant increases in instrumentation density and quality, and rapid advances in machine learning (ML) algorithms have placed Earth Sciences at the threshold of dramatic progress. ML techniques have been attracting increased attention within the seismic community, and, in particular, in microseismic monitoring where they are now being considered a game-changer due to their real-time processing potential. In our review of the recent developments in microseismic monitoring and characterisation, we find a strong trend in utilising ML methods for enhancing the passive seismic data quality, detecting microseismic events, and locating their hypocenters. Moreover, they are being adopted for advanced event characterisation of induced seismicity, such as source mechanism determination, cluster analysis and forecasting, as well as seismic velocity inversion. These advancements, based on ML, include by-products often ignored in classical methods, like uncertainty analysis and data statistics. In our assessment of future trends in ML utilisation, we also see a strong push toward its application on distributed acoustic sensing (DAS) data and real-time monitoring to handle the large amount of data acquired in these cases.

Retrieving accurate microseismic source locations induced by hydraulic-fracturing operations is an important step to gain insights into the hydraulically stimulated reservoir volume. Recently, deep neural networks have been proposed that directly recover source locations from the seismic waveforms. The optimal performance of the proposed deep neural networks usually requires large training sets. The need for a large training set can be circumvented if a previously trained deep neural network can be used to start the training process with its weights instead of randomly initialized weights. These weights can then be fine-tuned using a smaller training set, which is also known as transfer learning. In this work, we implement a transfer learning workflow to update the weights of a deep neural network that was initially trained on a large synthetic dataset to localize microseismic events. We present two methods of processing, namely one post-monitoring mode and one continuous mode where the processing takes place during the monitoring period. We apply the methods to field data from a hydraulic fracturing site in Texas, USA. In the first scenario, a subset of the field data from the entire monitoring period is used to update the weights of the deep neural network, which is then applied to the remaining data resulting in mean and median distances of 227 and 182 m, respectively, compared to the results of a good localization method. In the second scenario, the deep neural network is updated daily with previously detected and located events and applied to the events detected the following day. Since the observed data used for training generally do not cover a wide range of source locations, we enrich the training set with synthetic data. The addition of synthetics for transfer learning ensures that the updated deep neural network provides accurate source locations for events with locations far from locations used during transfer learning. Transfer learning combining synthetic and real data performs significantly better (more consistent) locations than transfer learning without synthetics.