Search papers, labs, and topics across Lattice.
This study provides the first systematic evidence of hallucination in AI models applied to fluid dynamics, specifically in the context of viscous fingering, a problem characterized by hydrodynamically unstable transport. The researchers identify that AI-generated solutions can appear visually plausible but are physically unrealistic, leading to violations of conservation laws due to the spectral bias of the models at high flow rates. To address this, they introduce DeepFingers, a novel framework that combines the Fourier Neural Operator with a Deep Operator Network, enabling accurate predictions of spatiotemporal dynamics while maintaining essential mixing metrics.
AI models can generate visually convincing yet physically implausible fluid dynamics solutions, revealing a critical flaw in their design.
We report the first systematic evidence of hallucination in AI models of fluid dynamics, demonstrated in the canonical problem of hydrodynamically unstable transport known as viscous fingering. AI-based modeling of flow with instabilities remains challenging because rapidly evolving, multiscale fingering patterns are difficult to resolve accurately. We identify solutions that appear visually realistic yet are physically implausible, analogous to hallucinations in large language models. These hallucinations manifest as spurious fluid interfaces and reverse diffusion that violate conservation laws. We show that their origin lies in the spectral bias of AI models, which becomes dominant at high flow rates and viscosity contrasts. Guided by this insight, we introduce DeepFingers, a new framework for AI-driven fluid dynamics that enforces balanced learning across the full spectrum of spatial modes by combining the Fourier Neural Operator with a Deep Operator Network to predict the spatiotemporal evolution of viscous fingers. By conditioning on both time and viscosity contrast, DeepFingers learns mappings between successive concentration fields across regimes. The framework accurately captures tip splitting, finger merging, and channel formation while preserving global metrics of mixing. The results open a new research direction to investigate fundamental limitations in AI models of physical systems.
