Comparison of LSTM autoencoder based deep learning enabled Bayesian inference using two time series reconstruction approaches

TL;DR

This paper integrates LSTM autoencoders with Bayesian inference to estimate injection rates from surface displacement data, comparing two reconstruction approaches for improved accuracy in coupled flow and geomechanics modeling.

Contribution

It introduces a novel framework combining deep learning and Bayesian inference for robust parameter estimation in geomechanical problems, utilizing LSTM autoencoders for time series reconstruction.

Findings

LSTM autoencoders effectively reconstruct displacement time series.

The framework provides robust estimates of injection rates.

Comparison of two reconstruction approaches highlights their strengths.

Abstract

In this work, we use a combination of Bayesian inference, Markov chain Monte Carlo and deep learning in the form of LSTM autoencoders to build and test a framework to provide robust estimates of injection rate from ground surface data in coupled flow and geomechanics problems. We use LSTM autoencoders to reconstruct the displacement time series for grid points on the top surface of a faulting due to water injection problem. We then deploy this LSTM autoencoder based model instead of the high fidelity model in the Bayesian inference framework to estimate injection rate from displacement input.