22 Mar 2021

22 Mar 2021

Review status: this preprint is currently under review for the journal SE.

Accelerating Bayesian microseismic event location with deep learning

Alessio Spurio Mancini1,2, Davide Piras1, Ana Margarida Godinho Ferreira3, Michael Paul Hobson2, and Benjamin Joachimi1 Alessio Spurio Mancini et al.
  • 1Department of Physics and Astronomy, University College London, Gower Street, London, WC1E 6BT, UK
  • 2Astrophysics Group, Cavendish Laboratory, J. J. Thomson Avenue, Cambridge, CB3 0HE, UK
  • 3Department of Earth Sciences, Faculty of Mathematical Physical Sciences, University College London, WC1E 6BT, United Kingdom

Abstract. We present a series of new open source deep learning algorithms to accelerate Bayesian full waveform point source inversion of microseismic events. Inferring the joint posterior probability distribution of moment tensor components and source location is key for rigorous uncertainty quantification. However, the inference process requires forward modelling of micro-seismic traces for each set of parameters explored by the sampling algorithm, which makes the inference very computationally intensive. In this paper we focus on accelerating this process by training deep learning models to learn the mapping between source location and seismic traces, for a given 3D heterogeneous velocity model, and a fixed isotropic moment tensor for the sources. These trained emulators replace the expensive solution of the elastic wave equation in the inference process.

We compare our results with a previous study that used emulators based on Gaussian Processes to invert microseismic events. For fairness of comparison, we train our emulators on the same microseismic traces and using the same geophysical setting. We show that all of our models provide more accurate predictions and ∼100 times faster predictions than the method based on Gaussian Processes, and a O(105) speed-up factor over a pseudo-spectral method for waveform generation. For example, a 2-s long synthetic trace can be generated in ∼10 ms on a common laptop processor, instead of ∼1 hr using a pseudo-spectral method on a high-profile Graphics Processing Units card. We also show that our inference results are in excellent agreement with those obtained from traditional location methods based on travel time estimates. The speed, accuracy and scalability of our open source deep learning models pave the way for extensions of these emulators to generic source mechanisms and application to joint Bayesian inversion of moment tensor components and source location using full waveforms.

Alessio Spurio Mancini et al.

Status: open (until 13 May 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Alessio Spurio Mancini et al.

Data sets

3D velocity model Alessio Spurio Mancini, Davide Piras, Ana M. G. Ferreira, Michael P. Hobson, and Benjamin Joachimi

Model code and software

Deep generative models implementation Alessio Spurio Mancini, Davide Piras, Ana M. G. Ferreira, Michael P. Hobson, and Benjamin Joachimi

Alessio Spurio Mancini et al.


Total article views: 274 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
234 35 5 274 3 2
  • HTML: 234
  • PDF: 35
  • XML: 5
  • Total: 274
  • BibTeX: 3
  • EndNote: 2
Views and downloads (calculated since 22 Mar 2021)
Cumulative views and downloads (calculated since 22 Mar 2021)

Viewed (geographical distribution)

Total article views: 267 (including HTML, PDF, and XML) Thereof 267 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 11 Apr 2021
Short summary
The localisation of an earthquake is affected by many uncertainties. To correctly propagate these uncertainties into an estimate of the earthquake coordinates and their associated errors, many simulations of seismic waves are needed. This operation is computationally very intensive, hindering the feasibility of this approach. In this paper, we present a series of deep learning methods to produce accurate seismic traces in a fraction of the time needed with standard methods.