Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow

TL;DR

This paper introduces a deep learning surrogate model for 3D subsurface flow that accurately predicts dynamic flow states and integrates with geological parameterization techniques to improve data assimilation in complex geological systems.

Contribution

It develops a 3D recurrent residual U-Net for flow modeling and combines it with CNN-PCA for geological parameterization, enhancing data assimilation in subsurface flow analysis.

Findings

The surrogate model accurately predicts flow dynamics and well responses.

The combined approach effectively performs data assimilation in complex geological settings.

The methodology improves the efficiency of subsurface flow simulations.

Abstract

Data assimilation in subsurface flow systems is challenging due to the large number of flow simulations often required, and by the need to preserve geological realism in the calibrated (posterior) models. In this work we present a deep-learning-based surrogate model for two-phase flow in 3D subsurface formations. This surrogate model, a 3D recurrent residual U-Net (referred to as recurrent R-U-Net), consists of 3D convolutional and recurrent (convLSTM) neural networks, designed to capture the spatial-temporal information associated with dynamic subsurface flow systems. A CNN-PCA procedure (convolutional neural network post-processing of principal component analysis) for parameterizing complex 3D geomodels is also described. This approach represents a simplified version of a recently developed supervised-learning-based CNN-PCA framework. The recurrent R-U-Net is trained on the simulated dynamic 3D saturation and pressure fields for a set of random `channelized' geomodels (generated using 3D CNN-PCA). Detailed flow predictions demonstrate that the recurrent R-U-Net surrogate model provides accurate results for dynamic states and well responses for new geological realizations, along with accurate flow statistics for an ensemble of new geomodels. The 3D recurrent R-U-Net and CNN-PCA procedures are then used in combination for a challenging data assimilation problem involving a channelized system. Two different algorithms, namely rejection sampling and an ensemble-based method, are successfully applied. The overall methodology described in this paper may enable the assessment and refinement of data assimilation procedures for a range of realistic and challenging subsurface flow problems.