Flux-form spatiotemporal neural operators for coarse-grained dynamics of multiscale PDEs

arXiv:2608.18148v1 Announce Type: cross Abstract: We study data-driven prediction of coarse-grained dynamics in multiscale PDE systems. Adopting a closure-free operator-learning viewpoint, we apply a linear coarse-graining map and learn a surrogate evolution operator for the resolved field directly from filtered high-fidelity trajectories. Motivated by the Mori-Zwanzig formalism, we propose a spatiotemporal neural operator mapping a resolved history slab on Omegaimes[-T_{in},0] to a resolved future slab on Omegaimes[0,T_{out}]. Spatial mixing uses Fourier convolution, while temporal mixing uses a causal kernel operator with position-attention weights on time lags. This causal temporal operator encodes finite-memory effects in the resolved dynamics while preserving the directionality of the history-to-future map. To improve rollout robustness and suppress nonconservative artifacts, we embed a flux-form inductive bias by parameterizing the windowed update in explicit divergence form. We also provide a data-driven guideline for selecting the memory length T_{in} via the decorrelation time of a closure-injection diagnostic computed from filtered trajectories. We validate on the coarse-grained viscous Burgers' equation, the Kuramoto-Sivashinsky equation, and two-dimensional turbulent flows, obtaining stable autoregressive rollouts with improved long-horizon accuracy and statistical fidelity.

Related

• Prescribed-Basis Coefficient-to-Coefficient Neural Operator for Partial Differential Equations
• A Multi-Resolution Finite-Volume Inspired Deep Learning Framework for Spatiotemporal Dynamics Prediction
• Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems
• Data-Efficient Neural Operator Training via Physics-Based Active Learning

Source: arXiv cs.LG | 2026-08-20