Monitoring the CO₂ plume evolution is essential for ensuring geologic storage security and integrity. Traditional numerical simulation-based data assimilation workflow is computationally expensive, and this is further complicated by the fact that geologic uncertainty must be incorporated for robust performance prediction. Therefore, reservoir simulation and model calibration accounting for geologic uncertainty are not amenable to real time monitoring of the CO₂ plume evolution for large-scale applications. We propose a deep learning-based approach which enables near real time CO₂ plume visualization and rapid data assimilation incorporating multiple geological realizations for predicting future CO₂ plume evolution and area of review (AOR) determination.

The proposed deep learning-based data assimilation framework considers geological uncertainty utilizing multiple plausible models for training data generation. Rather than utilizing all available geologic realizations, a representative subset is sampled using dissimilarity measures in flow patterns computed via multidimensional scaling (MDS) and streamline time-of-flight. The approach substantially reduces training data generation cost while preserving the uncertainty inherent in the original ensemble of geomodels. The CO₂ plume evolution is represented using ‘onset time’ images, depicting the calendar time when the CO₂ saturation exceeds a prespecified threshold value at a given location. The use of a single CO₂ onset time image instead of multiple CO₂ saturation snapshots across different timesteps significantly reduces the dimensionality of the problem, making the deep learning model robust and scalable for large-scale field applications. A variational autoencoder encodes the onset time images into latent variables, which are predicted by another neural networks using the available monitoring data. The power and efficacy of the proposed method are demonstrated through application to a largescale field case, the Illinois Basin-Decatur Carbon Sequestration Project.

The available monitoring data consists of bottom-hole pressure at the injector, distributed pressure data and CO₂ saturation log data at the monitoring well. Out of 200 geostatistical realizations, 10 representative models are selected by the MDS while preserving diversity of the geologic model. Additional calibration parameters including transmissibility and pore volume multipliers are applied to the selected realizations for generating a comprehensive training dataset. The trained ML model is then employed for reservoir model calibration, significantly accelerating the calibration process and enabling real time CO₂ plume imaging from the monitoring data. The trained deep learning model achieves history matching of both pressure and saturation responses in seconds. The calibrated models are then used for forecasting future CO₂ plume migration and the AOR assessment.

The deep learning-based data assimilation approach enables near real time monitoring and verification of field-scale CO₂ sequestration projects while accounting for geologic uncertainty. Utilizing the trained deep learning model, reservoir model calibration and prediction of CO₂ plume evolution is performed within seconds, orders of magnitude faster compared to traditional history matching.