VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics Prediction

TL;DR

VICON introduces a vision transformer-based approach for efficient multi-physics fluid dynamics prediction, significantly improving accuracy and robustness over state-of-the-art methods in realistic, variable-timestep scenarios.

Contribution

The paper presents VICON, a novel vision transformer-based architecture that enhances ICONs for dense 2D data, enabling faster, more accurate, and more robust fluid dynamics predictions across varying conditions.

Findings

VICON reduces rollout error by up to 44.7% compared to baselines.

VICON requires significantly less inference time, up to 72.5% of baseline times.

VICON maintains high performance even with irregular sampling and dropped frames.

Abstract

In-Context Operator Networks (ICONs) have demonstrated the ability to learn operators across diverse partial differential equations using few-shot, in-context learning. However, existing ICONs process each spatial point as an individual token, severely limiting computational efficiency when handling dense data in higher spatial dimensions. We propose Vision In-Context Operator Networks (VICON), which integrates vision transformer architectures to efficiently process 2D data through patch-wise operations while preserving ICON's adaptability to multiphysics systems and varying timesteps. Evaluated across three fluid dynamics benchmarks, VICON significantly outperforms state-of-the-art baselines: DPOT and MPP, reducing the averaged last-step rollout error by 37.9% compared to DPOT and 44.7% compared to MPP, while requiring only 72.5% and 34.8% of their respective inference times. VICON naturally supports flexible rollout strategies with varying timestep strides, enabling immediate deployment in imperfect measurement systems where sampling frequencies may differ or frames might be dropped - common challenges in real-world settings - without requiring retraining or interpolation. In these realistic scenarios, VICON exhibits remarkable robustness, experiencing only 24.41% relative performance degradation compared to 71.37%-74.49% degradation in baseline methods, demonstrating its versatility for deploying in realistic applications. Our scripts for processing datasets and code are publicly available at https://github.com/Eydcao/VICON.