Uncertainty quantification of two-phase flow in porous media via coupled-TgNN surrogate model

  title={Uncertainty quantification of two-phase flow in porous media via coupled-TgNN surrogate model},
  author={Jun Yu Li and Dongxiao Zhang and Tianhao He and Qiang Zheng},
Uncertainty quantification (UQ) of subsurface two-phase flow usually requires numerous executions of forward simulations under varying conditions. In this work, a novel coupled theory-guided neural network (TgNN) based surrogate model is built to facilitate computation efficiency under the premise of satisfactory accuracy. The core notion of this proposed method is to bridge two separate blocks on top of an overall network. They underlie the TgNN model in a coupled form, which reflects the… 



Interpretation of well-block pressures in numerical reservoir simulation with nonsquare grid blocks and anisotropic permeability

An interpretation is given of well-block pressure for the case of nonsquare grid blocks. Based on numerical solutions for the single-phase five-spot problem, using various sizes of grids, a

Surrogate modeling for porous flow using deep neural networks

Fast evaluation of pressure and saturation predictions with a deep learning surrogate flow model

An Efficient Spatial-Temporal Convolution Recurrent Neural Network Surrogate Model for History Matching

A new deep-learning-based surrogate modeling framework, image-to-sequence regression, which can directly predict the production data from the high-dimensional spatial parameters, and improve the efficiency of history matching is introduced.

Prediction of Field Saturations Using a Fully Convolutional Network Surrogate

The input of multiple influencing factors is considered to make the surrogate model more consistent with the physical laws, which has achieved good results in the prediction of output fields in the authors' experiments.