Flow-Matched Neural Operators for Continuous PDE Dynamics

Flow-Matched Neural Operators for Continuous PDE Dynamics

From AI Extreme Weather and Climate by Zhi Li

December 9, 2025 · 12 min · Season 1 · Episode 12

About this episode

The episode discusses the Continuous Flow Operator, a novel neural framework for learning continuous-time dynamics of Partial Differential Equations.

The episode describes the Continuous Flow Operator (CFO) , a novel neural framework for learning the continuous-time dynamics of Partial Differential Equations (PDEs) , aimed at overcoming limitations found in conventional models like autoregressive schemes and Neural Ordinary Differential Equations (ODEs). CFO's key innovation is the use of a flow matching objective to directly learn the right-hand side of the PDE dynamics, utilizing the analytic velocity derived from spline-based interpolants fit to trajectory data. This approach uniquely allows for training on irregular and subsampled time grids while enabling arbitrary temporal resolution during inference through standard ODE integration. Across four benchmarks (Lorenz, 1D Burgers, 2D diffusion-reaction, and 2D shallow water equations), the quintic CFO variant demonstrates superior long-horizon stability and significant data efficiency, often outperforming autoregressive baselines trained on complete datasets even when trained on only 25% of irregularly sampled data .

Topics covered

  • neural operators
  • partial differential equations
  • machine learning
  • data efficiency

Keywords

  • Continuous Flow Operator
  • flow matching objective
  • spline-based interpolants
  • irregular time grids
  • long-horizon stability

Mentioned in this episode

Products: the Continuous Flow Operator (CFO), CFO

More episodes of AI Extreme Weather and Climate

Explore listener stats, chart rankings, contacts and more on the AI Extreme Weather and Climate podcast page.