Physics-informed convolutional neural networks for fluid flow through porous media

arXiv:2605.20250 · 2026-05-21 공개 · arXiv · PDF

model-generalization porous-media fluid-flow convolutional-encoder-decoder loss-function-design lattice-boltzmann tortuosity-index initial-conditions

Abstract

Accurate simulation of fluid flow in porous media is challenging due to complex pore-space geometries and the computational cost of solving the Navier-Stokes equations. This difficulty is particularly important when repeated simulations are required, as standard numerical solvers may converge slowly in intricate porous domains. We present a neural-network-based framework for predicting pore-scale velocity fields directly from sample geometry. The method uses a convolutional encoder-decoder architecture with skip connections to preserve spatial detail while extracting multi-scale features. Physical consistency is encouraged through a custom loss function combining velocity reconstruction with incompressibility, no-flow conditions inside solids, periodicity constraints, and agreement with the global tortuosity index. We analyze the influence of the corresponding loss weights and quantify the contribution of individual loss components to prediction accuracy. Several CNN backbones are evaluated to identify architectures providing accurate and robust predictions. The generalization ability of the trained model is tested on samples outside the training distribution, including changes in obstacle geometry, boundary conditions, porosity, and realistic porous structures. Finally, we demonstrate a practical use of the predicted velocity fields as initial conditions for Lattice-Boltzmann simulations. This warm-start strategy accelerates solver convergence, reducing the number of iterations in over 90% of tested cases.

한국어 요약

📋 한 줄 요약

**[과학 ML / 다공성 매체 시뮬레이션]** 물리 일관 손실을 결합한 CNN 인코더-디코더로 다공성 매체의 pore-scale 속도장을 예측하고, Lattice-Boltzmann 솔버 warm-start로 90% 이상 케이스에서 수렴 가속을 시연.

🎯 핵심 기여도

💡 핵심 아이디어

물리 시뮬레이션을 신경망으로 "완전 대체"하기보다, 빠른 신경망 예측을 전통 솔버의 좋은 초기값으로 사용하는 하이브리드 전략이 사실상 가장 견고하고 일반화 가능한 선택지가 될 수 있다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: PINN 류 단독 풀이 한계를 인정하고 전통 솔버와의 협업을 통해 실용성을 확보한 모범 사례. **한계**: 학습 데이터 외 도메인(다상 유동·반응성 매체)으로의 확장과 손실 가중치 자동화는 후속 과제.

🚀 실용적 활용