U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flow

TL;DR

U-FNO is a novel neural network architecture based on Fourier neural operators, designed to efficiently and accurately simulate complex multiphase flows in porous media, outperforming existing models in speed and data efficiency.

Contribution

The paper introduces U-FNO, an extension of Fourier neural operators, tailored for multiphase flow problems, achieving higher accuracy and data efficiency than existing CNN benchmarks.

Findings

U-FNO outperforms CNN in accuracy for gas saturation and pressure predictions.

U-FNO requires only one-third of the training data compared to CNN.

U-FNO enables faster simulations of CO2 injection in heterogeneous reservoirs.

Abstract

Numerical simulation of multiphase flow in porous media is essential for many geoscience applications. Machine learning models trained with numerical simulation data can provide a faster alternative to traditional simulators. Here we present U-FNO, a novel neural network architecture for solving multiphase flow problems with superior accuracy, speed, and data efficiency. U-FNO is designed based on the newly proposed Fourier neural operator (FNO), which has shown excellent performance in single-phase flows. We extend the FNO-based architecture to a highly complex CO2-water multiphase problem with wide ranges of permeability and porosity heterogeneity, anisotropy, reservoir conditions, injection configurations, flow rates, and multiphase flow properties. The U-FNO architecture is more accurate in gas saturation and pressure buildup predictions than the original FNO and a state-of-the-art convolutional neural network (CNN) benchmark. Meanwhile, it has superior data utilization efficiency, requiring only a third of the training data to achieve the equivalent accuracy as CNN. U-FNO provides superior performance in highly heterogeneous geological formations and critically important applications such as gas saturation and pressure buildup "fronts" determination. The trained model can serve as a general-purpose alternative to routine numerical simulations of 2D-radial CO2 injection problems with significant speed-ups than traditional simulators.