The Best of Both Worlds: Hybridizing Neural Operators and Solvers for Stable Long-Horizon Inference

TL;DR

This paper introduces ANCHOR, a hybrid inference framework combining neural operators and classical solvers with adaptive error monitoring, enabling stable long-horizon predictions for nonlinear PDEs efficiently and reliably.

Contribution

The paper presents ANCHOR, a novel online, adaptive correction method that couples neural operators with numerical solvers using residual-based error estimation for stable long-term PDE inference.

Findings

ANCHOR effectively bounds error growth in long-horizon PDE predictions.

It stabilizes neural operator rollouts and improves robustness.

ANCHOR is more efficient than high-fidelity solvers while maintaining accuracy.

Abstract

Numerical simulation of time-dependent partial differential equations (PDEs) is central to scientific and engineering applications, but high-fidelity solvers are often prohibitively expensive for long-horizon or time-critical settings. Neural operator (NO) surrogates offer fast inference across parametric and functional inputs; however, most autoregressive NO frameworks remain vulnerable to compounding errors, and ensemble-averaged metrics provide limited guarantees for individual inference trajectories. In practice, error accumulation can become unacceptable beyond the training horizon, and existing methods lack mechanisms for online monitoring or correction. To address this gap, we propose ANCHOR (Adaptive Numerical Correction for High-fidelity Operator Rollouts), an online, instance-aware hybrid inference framework for stable long-horizon prediction of nonlinear, time-dependent PDEs. ANCHOR treats a pretrained NO as the primary inference engine and adaptively couples it with a classical numerical solver using a physics-informed, residual-based error estimator. Inspired by adaptive time-stepping in numerical analysis, ANCHOR monitors an exponential moving average (EMA) of the normalized PDE residual to detect accumulating error and trigger corrective solver interventions without requiring access to ground-truth solutions. We show that the EMA-based estimator correlates strongly with the true relative L2 error, enabling data-free, instance-aware error control during inference. Evaluations on four canonical PDEs: 1D and 2D Burgers', 2D Allen-Cahn, and 3D heat conduction, demonstrate that ANCHOR reliably bounds long-horizon error growth, stabilizes extrapolative rollouts, and significantly improves robustness over standalone neural operators, while remaining substantially more efficient than high-fidelity numerical solvers.