FlowForge: A Staged Local Rollout Engine for Flow-Field Prediction

TL;DR

FlowForge is a staged local rollout engine for flow-field prediction that improves robustness, latency, and accuracy by focusing on local spatial updates rather than global predictions.

Contribution

It introduces a novel staged local update schedule and compile-execute design that aligns inference with physical localities in flow prediction models.

Findings

FlowForge matches or exceeds baseline accuracy in flow prediction.

It demonstrates improved robustness to noise and missing data.

FlowForge maintains stable multi-step predictions with reduced latency.

Abstract

Deep learning surrogates for CFD flow-field prediction often rely on large, complex models, which can be slow and fragile when data are noisy or incomplete. We introduce FlowForge, a staged local rollout engine that predicts future flow fields by compiling a locality-preserving update schedule and executing it with a shared lightweight local predictor. Rather than producing the next frame in a single global pass, FlowForge rewrites spatial sites stage by stage so that each update conditions only on bounded local context exposed by earlier stages. This compile-execute design aligns inference with short-range physical dependence, keeps latency predictable, and limits error amplification from global mixing. Across PDEBench, CFDBench, and BubbleML, FlowForge matches or improves upon strong baselines in pointwise accuracy, delivers consistently better robustness to noise and missing observations, and maintains stable multi-step rollout behavior while reducing per-step latency.