A Variational Auto-Encoder for Reservoir Monitoring

TL;DR

This paper introduces a semi-conditional variational auto-encoder that reconstructs pressure fields and classifies leakage rates in CO2 storage reservoirs, aiding monitoring and ensuring storage integrity.

Contribution

The paper presents a novel deep learning model specifically designed for simultaneous pressure field reconstruction and leakage classification in reservoir monitoring.

Findings

Effective reconstruction of pressure fields demonstrated on synthetic data.

Accurate classification of leakage rates achieved with uncertainty estimates.

Model shows promise for real-time reservoir monitoring applications.

Abstract

Carbon dioxide Capture and Storage (CCS) is an important strategy in mitigating anthropogenic CO$_2$ emissions. In order for CCS to be successful, large quantities of CO$_2$ must be stored and the storage site conformance must be monitored. Here we present a deep learning method to reconstruct pressure fields and classify the flux out of the storage formation based on the pressure data from Above Zone Monitoring Interval (AZMI) wells. The deep learning method is a version of a semi conditional variational auto-encoder tailored to solve two tasks: reconstruction of an incremental pressure field and leakage rate classification. The method, predictions and associated uncertainty estimates are illustrated on the synthetic data from a high-fidelity heterogeneous 2D numerical reservoir model, which was used to simulate subsurface CO$_2$ movement and pressure changes in the AZMI due to a CO$_2$ leakage.