Accelerated training of deep learning surrogate models for surface displacement and flow, with application to MCMC-based history matching of CO2 storage operations
Deep learning surrogate modeling shows great promise for subsurface flow applications, but the training demands can be substantial. Here we introduce a new surrogate modeling framework to predict CO2 saturation, pressure and surface displacement for use in the history matching of carbon storage operations. The new treatment allows us to use a relatively small number of expensive coupled flow-geomechanics simulation runs (required to predict surface displacement) in combination with a large number of much less expensive flow- only simulations. The flow-only runs use an effective rock compressibility determined from the geomechanical parameters, which is shown to provide solutions that closely approximate the pressure and saturation fields for the coupled problem. This overall approach enables significantly faster training. A recurrent residual U- Net architecture is applied for the saturation and pressure surrogate models, while a new, specially designed residual U-Net model is introduced to predict surface displacement. The surface displacement surrogate accepts, as inputs, geomodel quantities along with saturation and pressure surrogate predictions. Median relative error for a diverse test set is less than 4% for all variables. The surrogate models are incorporated into a hierarchical Markov chain Monte Carlo history matching workflow (this workflow would be infeasible with high-fidelity simulation). Surrogate error is included using a new treatment involving the full model error covariance matrix. A high degree of prior uncertainty, with geomodels characterized by uncertain geological scenario parameters (metaparameters) and associated realizations, is considered. History matching results for a synthetic true model are generated using in-situ monitoring-well data only, surface displacement data only, and both data types. The enhanced uncertainty reduction achieved with both data types is quantified. Posterior saturation and surface displacement fields are shown to correspond well with the true solution. The impact of properly treating surrogate model error, and the performance of the workflow for another, more challenging true model, are presented in Supplemental Information.