CoFINN: Conservation Flux Informed Neural Networks for Physics Problems Governed by Conservation Laws
Quick Answer
CoFINN is a physics-informed deep learning framework that enhances aerodynamic force prediction in compressible flow fields, achieving up to 34% reduction in drag error at extreme angles of attack.
Quick Take
CoFINN is a physics-informed deep learning framework that enhances aerodynamic force prediction in compressible flow fields, achieving up to 34% reduction in drag error at extreme angles of attack. By integrating finite-volume conservation physics directly into training, it significantly improves physical consistency while maintaining CNN computational efficiency. The framework is applicable to various conservation-law-governed systems.
Key Points
- CoFINN reduces drag prediction error by up to 34% at extreme angles of attack.
- The framework uses finite-volume conservation physics for improved training consistency.
- It maintains computational efficiency while enhancing physical accuracy in predictions.
- Evaluated on transonic flow around airfoils at M=0.7, Re=6 * 10^6.
- Architecture-agnostic, extensible to broader classes of physical systems governed by conservation laws.
Paper Resources
📖 Reader Mode
~2 min readAbstract:We present CoFINN (Conservation Flux Informed Neural Networks), a physics-informed deep learning framework for predicting compressible flow fields governed by conservation laws. Unlike conventional data-driven convolutional neural networks (CNNs), which optimize only pixel-wise similarity metrics, CoFINN embeds finite-volume conservation physics directly into the training process. Unlike classical physics-informed methods which enforce differential-equation residuals at collocation points through automatic differentiation, CoFINN adopts a finite-volume perspective consistent with modern CFD methodology. CoFINN interprets CNN output fields as structured computational grids, where each pixel represents a finite-volume cell, and enforces conservation consistency through sophisticated numerical flux calculations. The framework is evaluated on transonic flow prediction around airfoils at (M=0.7, Re=6 * 10^6), including challenging conditions involving shock waves and high angles of attack. Results show that CoFINN improves aerodynamic force prediction accuracy, reducing drag prediction error by up to 34% at extreme angles of attack and by approximately 15% on average across the test set. Improvements are particularly significant in limited-data regimes, demonstrating that the conservation-based loss acts as an effective physical regularizer. The proposed approach maintains the computational efficiency advantages of CNN surrogates while significantly improving physical consistency and conservation behavior. The framework is architecture-agnostic and extensible to broader classes of conservation-law-governed physical systems.
| Comments: | 28 pages, 7 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Fluid Dynamics (physics.flu-dyn) |
| Cite as: | arXiv:2607.06587 [cs.CV] |
| (or arXiv:2607.06587v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.06587 arXiv-issued DOI via DataCite |
Submission history
From: Adnan Harun Dogan [view email]
[v1]
Sun, 5 Jul 2026 15:21:12 UTC (2,769 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.