Towards fast machine-learning-assisted Bayesian posterior inference of microseismic event location and source mechanism

Abstract

Bayesian inference applied to microseismic activity monitoring allows the accurate location of microseismic events from recorded seismograms and the estimation of the associated uncertainties. However, the forward modelling of these microseismic events, which is necessary to perform Bayesian source inversion, can be prohibitively expensive in terms of computational resources. A viable solution is to train a surrogate model based on machine learning techniques, to emulate the forward model and thus accelerate Bayesian inference. In this paper, we substantially enhance previous work, which considered only sources with isotropic moment tensors. We train a machine learning algorithm on the power spectrum of the recorded pressure wave and show that the trained emulator allows complete and fast event locations for $\text{any}$ source mechanism. Moreover, we show that our approach is computationally inexpensive, as it can be run in less than 1 hour on a commercial laptop, while yielding accurate results using less than $10^4$ training seismograms. We additionally demonstrate how the trained emulators can be used to identify the source mechanism through the estimation of the Bayesian evidence. Finally, we demonstrate that our approach is robust to real noise as measured in field data. This work lays the foundations for efficient, accurate future joint determinations of event location and moment tensor, and associated uncertainties, which are ultimately key for accurately characterising human-induced and natural earthquakes, and for enhanced quantitative seismic hazard assessments.

arXiv comment17+4 pages, 13+3 figures, 2 tables. Matches version published in GJI, including extra tests with realistic noise and network configuration. Code available at https://github.com/alessiospuriomancini/seismoML/tree/main/Piras_2022

References in corpus (21)

• Adam: A Method for Stochastic Optimization
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Array Programming with NumPy
• MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
• X-ray spectral modelling of the AGN obscuring region in the CDFS: Bayesian model selection and catalogue
• P-wave arrival picking and first-motion polarity determination with deep learning
• EikoNet: Solving the Eikonal equation with Deep Neural Networks
• COSMOPOWER: emulating cosmological power spectra for accelerated Bayesian inference from next-generation surveys
• Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology
• Deep learning for seismic phase detection and picking in the aftershock zone of 2008 Mw7.9 Wenchuan earthquake
• Solving the wave equation with physics-informed deep learning
• PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method
• When Gaussian Process Meets Big Data: A Review of Scalable GPs
• Bayesian Evidence and Model Selection
• Fast cosmological parameter estimation using neural networks
• Accelerating Asymptotically Exact MCMC for Computationally Intensive Models via Local Approximations
• Comparison of sampling techniques for Bayesian parameter estimation
• {\sc CosmoNet}: fast cosmological parameter estimation in non-flat models using neural networks
• MCMC-Based Inference in the Era of Big Data: A Fundamental Analysis of the Convergence Complexity of High-Dimensional Chains
• Accelerating Bayesian microseismic event location with deep learning
• Fast GPU-Based Seismogram Simulation from Microseismic Events in Marine Environments Using Heterogeneous Velocity Models

Cited by in corpus (2)

• Accelerating Bayesian microseismic event location with deep learning
• Full-waveform earthquake source inversion using simulation-based inference