# Towards fast machine-learning-assisted Bayesian posterior inference of realistic microseismic events. (arXiv:2101.04724v1 [physics.geo-ph])

Bayesian inference applied to microseismic activity monitoring allows for
principled estimation of the coordinates of microseismic events from recorded
seismograms, and their associated uncertainties. However, forward modelling of
these microseismic events, 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 improve on previous work, which considered only sources with
isotropic moment tensor. We train a machine learning algorithm on the power
spectrum of the recorded pressure wave and show that the trained emulator
allows for the complete and fast retrieval of the event coordinates for
$textit{any}$ 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. This work lays the foundations for the efficient localisation and
characterisation of any recorded seismogram, thus helping to quantify human
impact on seismic activity and mitigate seismic hazard.