Skip to content

Conditional Latent Dynamics Network (CLDNet)

Home / Concepts / Conditional Latent Dynamics Network (CLDNet)

Conditional Latent Dynamics Network (CLDNet)

Auto-generated stub. Edit this file to add more details.

A neural ODE-based surrogate for hydrodynamic simulation that uses coordinate-based decoding to enable grid-independent, high-resolution flood forecasting.

Why It Matters

The architecture innovatively decouples spatial grid requirements from hydrodynamic surrogate modeling, a significant shift for physics-informed machine learning on irregular domains.

Evidence

a low-dimensional latent neural ODE driven by rainfall, paired with a coordinate-based decoder conditioned on static terrain

Metadata & Links