One Scale at a Time: Scale-Autoregressive Modeling for Fluid Flow Distributions

2026-04-13

AI Summary

This work addresses the high computational cost of traditional PDE solvers and the error accumulation in long-term predictions of learning-based time-stepping models for unsteady fluid flow simulation. To this end, the authors propose Scale Autoregressive Modeling (SAR), a multi-scale graph neural network framework operating on unstructured meshes. SAR introduces a novel scale autoregressive mechanism that performs coarse-to-fine conditional sampling: it first generates a low-resolution flow field and then progressively refines high-resolution details conditioned on coarser outputs, focusing computational effort where uncertainty is greatest—at coarse scales. Evaluated on multiple unsteady flow benchmarks, SAR substantially outperforms state-of-the-art diffusion models and Transolver, achieving 2–7× speedup while reducing distributional errors, improving single-sample accuracy, and enabling efficient and accurate estimation of statistical quantities such as turbulent kinetic energy.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Analyzing unsteady fluid flows often requires access to the full distribution of possible temporal states, yet conventional PDE solvers are computationally prohibitive and learned time-stepping surrogates quickly accumulate error over long rollouts. Generative models avoid compounding error by sampling states independently, but diffusion and flow-matching methods, while accurate, are limited by the cost of many evaluations over the entire mesh. We introduce scale-autoregressive modeling (SAR) for sampling flows on unstructured meshes hierarchically from coarse to fine: it first generates a low-resolution field, then refines it by progressively sampling higher resolutions conditioned on coarser predictions. This coarse-to-fine factorization improves efficiency by concentrating computation at coarser scales, where uncertainty is greatest, while requiring fewer steps at finer scales. Across unsteady-flow benchmarks of varying complexity, SAR attains substantially lower distributional error and higher per-sample accuracy than state-of-the-art diffusion models based on multi-scale GNNs, while matching or surpassing a flow-matching Transolver (a linear-time transformer) yet running 2-7x faster than this depending on the task. Overall, SAR provides a practical tool for fast and accurate estimation of statistical flow quantities (e.g., turbulent kinetic energy and two-point correlations) in real-world settings.

Problem

• fluid flow
• distribution modeling
• generative modeling
• unsteady flow
• computational efficiency

Innovation

• scale-autoregressive modeling
• hierarchical generation
• unstructured mesh
• fluid flow distribution
• generative modeling