Refine
Has Fulltext
- no (2) (remove)
Document Type
- Article (2) (remove)
Language
- English (2)
Is part of the Bibliography
- yes (2)
Keywords
Institute
The moment magnitude (M-w) 5.5 earthquake that struck South Korea in November 2017 was one of the largest and most damaging events in that country over the past century. Its proximity to an enhanced geothermal system site, where high-pressure hydraulic injection had been performed during the previous 2 years, raises the possibility that this earthquake was anthropogenic. We have combined seismological and geodetic analyses to characterize the mainshock and its largest aftershocks, constrain the geometry of this seismic sequence, and shed light on its causal factors. According to our analysis, it seems plausible that the occurrence of this earthquake was influenced by the aforementioned industrial activities. Finally, we found that the earthquake transferred static stress to larger nearby faults, potentially increasing the seismic hazard in the area.
Despite advanced seismological techniques, automatic source characterization for microseismic earthquakes remains difficult and challenging since current inversion and modelling of high-frequency signals are complex and time consuming. For real-time applications such as induced seismicity monitoring, the application of standard methods is often not fast enough for true complete real-time information on seismic sources. In this paper, we present an alternative approach based on recent advances in deep learning for rapid source-parameter estimation of microseismic earthquakes. The seismic inversion is represented in compact form by two convolutional neural networks, with individual feature extraction, and a fully connected neural network, for feature aggregation, to simultaneously obtain full moment tensor and spatial location of microseismic sources. Specifically, a multibranch neural network algorithm is trained to encapsulate the information about the relationship between seismic waveforms and underlying point-source mechanisms and locations. The learning-based model allows rapid inversion (within a fraction of second) once input data are available. A key advantage of the algorithm is that it can be trained using synthetic seismic data only, so it is directly applicable to scenarios where there are insufficient real data for training. Moreover, we find that the method is robust with respect to perturbations such as observational noise and data incompleteness (missing stations). We apply the new approach on synthesized and example recorded small magnitude (M <= 1.6) earthquakes at the Hellisheioi geothermal field in the Hengill area, Iceland. For the examined events, the model achieves excellent performance and shows very good agreement with the inverted solutions determined through standard methodology. In this study, we seek to demonstrate that this approach is viable for microseismicity real-time estimation of source parameters and can be integrated into advanced decision-support tools for controlling induced seismicity.