SURGIN: SURrogate-guided Generative INversion for subsurface multiphase flow with quantified uncertainty

2025-09-16

AI Summary

Real-time data assimilation and uncertainty quantification for subsurface multiphase flow in heterogeneous geological formations remain challenging, particularly when assimilating unseen monitoring data without retraining. Method: This paper proposes a zero-shot generative inversion framework that integrates an unconditional score-based generative model (SGM) with a differentiable surrogate model (U-FNO). The SGM learns geological priors via self-supervised training, while the U-FNO provides high-fidelity, differentiable flow response predictions; their coupling enables gradient-guided Bayesian posterior sampling. Contribution/Results: The framework unifies function-space inversion and uncertainty quantification, eliminating the need for task-specific retraining. It significantly improves accuracy and reliability in inferring geological parameters and forecasting spatiotemporal flow dynamics. Comprehensive evaluation across diverse sparse observation configurations demonstrates robustness and strong generalization capability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• 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: Applied ML and AI for Web-based mobile applications

Abstract

We present a direct inverse modeling method named SURGIN, a SURrogate-guided Generative INversion framework tailed for subsurface multiphase flow data assimilation. Unlike existing inversion methods that require adaptation for each new observational configuration, SURGIN features a zero-shot conditional generation capability, enabling real-time assimilation of unseen monitoring data without task-specific retraining. Specifically, SURGIN synergistically integrates a U-Net enhanced Fourier Neural Operator (U-FNO) surrogate with a score-based generative model (SGM), framing the conditional generation as a surrogate prediction-guidance process in a Bayesian perspective. Instead of directly learning the conditional generation of geological parameters, an unconditional SGM is first pretrained in a self-supervised manner to capture the geological prior, after which posterior sampling is performed by leveraging a differentiable U-FNO surrogate to enable efficient forward evaluations conditioned on unseen observations. Extensive numerical experiments demonstrate SURGIN's capability to decently infer heterogeneous geological fields and predict spatiotemporal flow dynamics with quantified uncertainty across diverse measurement settings. By unifying generative learning with surrogate-guided Bayesian inference, SURGIN establishes a new paradigm for inverse modeling and uncertainty quantification in parametric functional spaces.

Problem

• Inferring heterogeneous geological fields from subsurface flow data
• Predicting spatiotemporal flow dynamics with quantified uncertainty
• Enabling real-time data assimilation without task-specific retraining

Innovation

• Zero-shot conditional generation without retraining
• Integrates U-Net enhanced Fourier Neural Operator surrogate
• Leverages score-based generative model for Bayesian inference