Feature-Modulated UFNO for Improved Prediction of Multiphase Flow in Porous Media

TL;DR

This paper introduces UFNO-FiLM, an improved neural network architecture that enhances multiphase flow prediction accuracy by decoupling scalar inputs and applying spatially weighted loss functions, outperforming previous models.

Contribution

We propose UFNO-FiLM, which incorporates FiLM layers and spatially weighted loss to better handle scalar inputs and focus learning on critical regions, advancing multiphase flow modeling.

Findings

21% reduction in gas saturation MAE compared to UFNO

Effective decoupling of scalar inputs improves model efficiency

Spatially weighted loss enhances accuracy in important regions

Abstract

The UNet-enhanced Fourier Neural Operator (UFNO) extends the Fourier Neural Operator (FNO) by incorporating a parallel UNet pathway, enabling the retention of both high- and low-frequency components. While UFNO improves predictive accuracy over FNO, it inefficiently treats scalar inputs (e.g., temperature, injection rate) as spatially distributed fields by duplicating their values across the domain. This forces the model to process redundant constant signals within the frequency domain. Additionally, its standard loss function does not account for spatial variations in error sensitivity, limiting performance in regions of high physical importance. We introduce UFNO-FiLM, an enhanced architecture that incorporates two key innovations. First, we decouple scalar inputs from spatial features using a Feature-wise Linear Modulation (FiLM) layer, allowing the model to modulate spatial feature maps without introducing constant signals into the Fourier transform. Second, we employ a spatially weighted loss function that prioritizes learning in critical regions. Our experiments on subsurface multiphase flow demonstrate a 21\% reduction in gas saturation Mean Absolute Error (MAE) compared to UFNO, highlighting the effectiveness of our approach in improving predictive accuracy.