The project is the the extension of a previous project on the adaptive coupling of full-scale and vertical-equilibrium models for two-phase immiscible flow in porous media.
The main novelties are 1) the set-up of a full implicit scheme to overcome the limitations of the current segregated approach; 2) the use of machine learning techniques to speedup some scale-bridging computations and 3) the use of Bayesian framework to attempt uncertainty quantification. The project looks sound and timely. The availability of a robust full-implicit framework for this type of adaptive technique represents a forward step with respect to the current state of the art.
The goal of this project is a fully-implicit hybrid model with local dynamic model adaptivity employing machine-learned scale-bridging relations for the description of gas-storage scenarios. The hybrid multi-scale model couples a full-dimensional fine-scale model with a vertical-equilibrium coarse-scale model.