FFINO: Factorized Fourier Improved Neural Operator for Modeling Multiphase Flow in Underground Hydrogen Storage

2025-06-19

AI Summary

To address the challenge of rapid modeling for hydrogen plume migration and pressure field evolution in underground hydrogen storage (UHS), this paper proposes the Factorized Fourier Neural Operator (FFINO). Methodologically, it introduces experimentally calibrated relative permeability curves as uncertain parameters into the neural operator framework and designs a factorized Fourier architecture to integrate multi-scale physical features. Compared with FMIONet, FFINO reduces parameter count by 38.1%, shortens training time by 17.6%, and lowers GPU memory consumption by 12%; it improves hydrogen plume prediction accuracy by 9.8% and achieves inference speed 7,850× faster than conventional numerical simulation. This work establishes a new paradigm for real-time, high-fidelity, low-overhead, and field-deployable multiphase flow simulation in UHS.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Hardware-aware ML
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Underground hydrogen storage (UHS) is a promising energy storage option for the current energy transition to a low-carbon economy. Fast modeling of hydrogen plume migration and pressure field evolution is crucial for UHS field management. In this study, we propose a new neural operator architecture, FFINO, as a fast surrogate model for multiphase flow problems in UHS. We parameterize experimental relative permeability curves reported in the literature and include them as key uncertainty parameters in the FFINO model. We also compare the FFINO model with the state-of-the-art FMIONet model through a comprehensive combination of metrics. Our new FFINO model has 38.1% fewer trainable parameters, 17.6% less training time, and 12% less GPU memory cost compared to FMIONet. The FFINO model also achieves a 9.8% accuracy improvement in predicting hydrogen plume in focused areas, and 18% higher RMSE in predicting pressure buildup. The inference time of the trained FFINO model is 7850 times faster than a numerical simulator, which makes it a competent substitute for numerical simulations of UHS problems with superior time efficiency.

Problem

• Fast modeling of hydrogen plume migration in UHS
• Predicting pressure field evolution for UHS management
• Improving accuracy and efficiency in multiphase flow simulation

Innovation

• Factorized Fourier neural operator for multiphase flow
• Parameterized relative permeability curves as uncertainty
• Reduced parameters and training time versus FMIONet