Comparison of LSTM autoencoder based deep learning enabled Bayesian inference using two time series reconstruction approaches
This work addresses a domain-specific problem in geomechanics for water injection monitoring, but it is incremental as it compares two reconstruction approaches within an existing framework.
The authors tackled the problem of estimating injection rates from ground surface displacement data in coupled flow and geomechanics by developing a framework that uses LSTM autoencoders to reconstruct time series and replace high-fidelity models in Bayesian inference, resulting in robust estimates.
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.