Learning Physical Operators using Neural Operators

TL;DR

This paper presents a physics-informed neural operator framework that decomposes PDEs into learnable components, enabling better generalisation, continuous-time predictions, and interpretability for fluid dynamics problems.

Contribution

It introduces a modular neural operator architecture with operator splitting, improving generalisation and interpretability in solving PDEs.

Findings

Achieves better convergence on Navier--Stokes equations.

Generalises effectively to unseen physics.

Enables temporal extrapolation beyond training data.

Abstract

Neural operators have emerged as promising surrogate models for solving partial differential equations (PDEs), but struggle to generalise beyond training distributions and are often constrained to a fixed temporal discretisation. This work introduces a physics-informed training framework that addresses these limitations by decomposing PDEs using operator splitting methods, training separate neural operators to learn individual non-linear physical operators while approximating linear operators with fixed finite-difference convolutions. This modular mixture-of-experts architecture enables generalisation to novel physical regimes by explicitly encoding the underlying operator structure. We formulate the modelling task as a neural ordinary differential equation (ODE) where these learned operators constitute the right-hand side, enabling continuous-in-time predictions through standard ODE solvers and implicitly enforcing PDE constraints. Demonstrated on incompressible and compressible Navier--Stokes equations, our approach achieves better convergence and superior performance when generalising to unseen physics. The method remains parameter-efficient, enabling temporal extrapolation beyond training horizons, and provides interpretable components whose behaviour can be verified against known physics.