Deep compressed seismic learning for fast location and moment tensor inferences with natural and induced seismicity

Abstract

Fast detection and characterization of seismic sources is crucial for decision-making and warning systems that monitor natural and induced seismicity. However, besides the laying out of ever denser monitoring networks of seismic instruments, the incorporation of new sensor technologies such as Distributed Acoustic Sensing (DAS) further challenges our processing capabilities to deliver short turnaround answers from seismic monitoring. In response, this work describes a methodology for the learning of the seismological parameters: location and moment tensor from compressed seismic records. In this method, data dimensionality is reduced by applying a general encoding protocol derived from the principles of compressive sensing. The data in compressed form is then fed directly to a convolutional neural network that outputs fast predictions of the seismic source parameters. Thus, the proposed methodology can not only expedite data transmission from the field to the processing center, but also remove the decompression overhead that would be required for the application of traditional processing methods. An autoencoder is also explored as an equivalent alternative to perform the same job. We observe that the CS-based compression requires only a fraction of the computing power, time, data and expertise required to design and train an autoencoder to perform the same task. Implementation of the CS-method with a continuous flow of data together with generalization of the principles to other applications such as classification are also discussed.

Strain-based forward modeling and inversion of seismic moment tensors using distributed acoustic sensing (DAS) observations

“…In simulated data produced by ray tracing, the characteristics of S-waves measured by a single fiber provide additional constraints on the position of the source, whereas the polarity reversals in P-and S-waves help constrain the fault plans (Baird et al, 2020). In data produced by a one-component sensor in a laboratory experiment, machine learning and waveform fitting MT solutions showed discrepancies mainly localized in the azimuthal direction (Vera Rodriguez and Myklebust, 2022), which cannot be resolved with only one fiber. Most of these studies focused on the information that could be extracted from a single fiber.…”