Deep learning accelerated inverse modeling and forecasting for large-scale geologic CO₂ sequestration

Traditional physics-simulation based approaches for inverse modeling and forecasting in geologic CO₂ sequestration (GCS) are very time consuming. For example, a single inverse modeling may take a few weeks for a large-scale CO₂ storage model without leveraging any high-performance computing. To speed up this process, we developed a novel approach that employs machine learning methods to integrate monitoring data into subsurface forecasts more rapidly than current physics-based inverse modeling workflows allow. These updated forecasts with the updated models from the inverse modeling process will be used to provide site operators with decision support by generating real-time performance metrics of CO₂ storage (e.g., CO₂ plume and pressure area of review). First, we developed a deep learning (DL) model to predict the pressure/saturation evolution in large-scale storage reservoirs. A feature coarsening technique was applied to extract the most representative information and perform the training and prediction at the coarse scale, and to further recover the resolution at the fine scale by 2D piecewise cubic interpolation. The accuracy of the feature coarsening-based DL model is validated with a reservoir model built upon a Clastic Shelf storage site. Thereafter, the feature coarsening-based DL model was utilized as forward model in the inverse modeling process where a classical data assimilation approach, ES-MDA-GEO, was applied. The efficiency and effectiveness of the proposed DL-assisted workflow for large-scale inverse modeling and forecasting was demonstrated with the Clastic Shelf storage model.