Courant: a State-Adaptive Perceiver-Based Neural Surrogate with Local Support and Interpretable Field Decomposition
About
We introduce "Courant", a Perceiver-based encoder-processor-decoder surrogate model that has latent features exhibiting adaptive specialization and local support in the physical space, enabling functionality akin to an adaptive hp-refinement scheme, an attribute that is highly desirable in traditional numerical solvers and scientific machine learning broadly. The proposed architecture combines a shared random Fourier feature coordinate embedding, state-adapted latent queries, and a light-weight decoder. Courant is trained end-to-end with steady or transient simulation data and only a standard L_2 prediction loss in the physical space, achieving competitive accuracy on benchmarks. We demonstrate that Courant's inductive biases yield latents that are interpretable by design: they develop multiscale geometric specialization in the simulation domain and track coherent structures in the time-dependent case, acting analogously to time-evolving spatial basis functions and allowing for decoding a compact, geometry-anchored, partition-of-unity-like decomposition of the simulated field.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Neural Surrogate Modeling | Airfoil | NMAE1.4 | 5 | |
| Neural Surrogate Modeling | Pipe | NMAE1.4 | 5 | |
| Neural Surrogate Modeling | Diff-Sorp | NMAE3.8 | 5 | |
| Neural Surrogate Modeling | NS-3D | NMAE1.7 | 5 | |
| Unsteady flow simulation on unstructured meshes | 2D Cylinder-Obstructed Flow | NMAE1.7 | 5 | |
| Neural Surrogate Modeling | Darcy | NMAE5.7 | 5 | |
| Steady-state flow simulation on unstructured meshes | 3D Branched Pipe Flow (Br.Pipe) | NMAE9.6 | 4 | |
| Steady-state flow simulation on unstructured meshes | 3D Centrifugal Pump (Ctr.Pump) | NMAE1.7 | 3 | |
| Steady-state physical simulation on unstructured meshes | Elasticity (Elast.) | NMAE0.0021 | 3 |