arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.04375physics.geo-ph
收藏

使用扩散模型生成裂缝中的多相流体构型

Generating Multiphase Fluid Configurations in Fractures using Diffusion Models

Jaehong Chung, Agnese Marcato, Eric J. Guiltinan, Tapan Mukerji, Yen Ting Lin, Javier E. Santos

AI总结:

本文提出将扩散模型与基于物理的模拟耦合,用生成样本初始化裂缝多相流体模拟,并以弛豫时间验证和早停,实现最高8.2倍加速且保持物理稳健性。

摘要:

孔隙尺度模拟能够准确描述地下流体的输运性质。这些模拟增强了我们对各类应用的理解,例如评估氢气储存效率和预测地下储层中的 CO$_2$ 封存过程。然而,由于其介观尺度特性,这类模拟在计算上代价高昂。此外,其稳态解不能保证唯一,因此必须使用不同初始条件进行多次运行,以确保充分的样本覆盖。这些因素使获得具有代表性且可靠的预测这一任务变得复杂。为克服高计算成本障碍,我们提出一种将生成式扩散模型与基于物理的建模相耦合的混合方法。在训练生成模型后,我们合成样本,并将其用作基于物理模拟的初始条件。我们测量模拟(达到稳态解)的弛豫时间,将其作为验证指标和早停准则。数值实验表明,与常用初始化方法相比,该混合方法最高可实现 8.2 倍加速。这一发现提供了有力的初步支持,表明所提出的基于扩散模型的混合方案有潜力显著缩短数值模拟收敛所需时间,同时不损害物理稳健性。

英文摘要:

Pore-scale simulations accurately describe transport properties of fluids in the subsurface. These simulations enhance our understanding of applications such as assessing hydrogen storage efficiency and forecasting CO$_2$ sequestration processes in underground reservoirs. Nevertheless, they are computationally expensive due to their mesoscopic nature. In addition, their stationary solutions are not guaranteed to be unique, so multiple runs with different initial conditions must be performed to ensure sufficient sample coverage. These factors complicate the task of obtaining representative and reliable forecasts. To overcome the high computational cost hurdle, we propose a hybrid method that couples generative diffusion models and physics-based modeling. Upon training a generative model, we synthesize samples that serve as the initial conditions for physics-based simulations. We measure the relaxation time (to stationary solutions) of the simulations, which serves as a validation metric and early-stopping criterion. Our numerical experiments revealed that the hybrid method exhibits a speed-up of up to 8.2 times compared to commonly used initialization methods. This finding offers compelling initial support that the proposed diffusion model-based hybrid scheme has potentials to significantly decrease the time required for convergence of numerical simulations without compromising the physical robustness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑