🤖 AI Summary
To address the high computational cost and limited long-term predictive capability of geochemical modules in reactive transport simulations within porous media, this work focuses on cation exchange—a canonical adsorption equilibrium process—and systematically identifies, for the first time, the fundamental failure mechanism of purely data-driven surrogate models during temporal rollout: error accumulation. We propose a synergistic correction framework integrating physics-informed constraints with customized data generation. Specifically, we develop a lightweight neural network surrogate, enforce physical consistency via a dedicated loss function, and jointly incorporate rollout-error correction and reaction-kinetics-guided data augmentation. In multi-step rollout predictions, the proposed method reduces prediction error by two orders of magnitude, markedly enhancing both accuracy and stability for long-term forecasting. This approach establishes a robust paradigm for embeddable, high-fidelity machine learning–physics hybrid modeling.
📝 Abstract
Reactive transport in porous media plays a pivotal role in subsurface reservoir processes, influencing fluid properties and geochemical characteristics. However, coupling fluid flow and transport with geochemical reactions is computationally intensive, requiring geochemical calculations at each grid cell and each time step within a discretized simulation domain. Although recent advancements have integrated machine learning techniques as surrogates for geochemical simulations, ensuring computational efficiency and accuracy remains a challenge. This work investigates machine learning models as replacements for a geochemical module in a simulation of reactive transport in porous media. As a proof of concept, we test this approach on a well-documented cation exchange problem. While the surrogate models excel in isolated predictions, they fall short in rollout predictions over successive time steps. By introducing modifications, including physics-based constraints and tailored dataset generation strategies, we show that machine learning surrogates can achieve accurate rollout predictions. Our findings emphasize that even for a simple sorption equilibrium reaction (cation exchange problem), machine learning surrogates alone fail in predicting over successive time-steps. Incorporating simple physics-based modifications enables us to overcome this limitation. A detailed analysis of the limitations and potential mitigation strategies is presented in this work.