DiffusionPDE: Generative PDE-Solving Under Partial Observation
About
We introduce a general framework for solving partial differential equations (PDEs) using generative diffusion models. In particular, we focus on the scenarios where we do not have the full knowledge of the scene necessary to apply classical solvers. Most existing forward or inverse PDE approaches perform poorly when the observations on the data or the underlying coefficients are incomplete, which is a common assumption for real-world measurements. In this work, we propose DiffusionPDE that can simultaneously fill in the missing information and solve a PDE by modeling the joint distribution of the solution and coefficient spaces. We show that the learned generative priors lead to a versatile framework for accurately solving a wide range of PDEs under partial observation, significantly outperforming the state-of-the-art methods for both forward and inverse directions.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| PDE solving | Poisson | Time (s)802 | 55 | |
| Continuum Field Reconstruction (Rollout) | 2D Navier-Stokes nu=1e-3 | MSE1.339 | 54 | |
| Forward PDE solving | Helmholtz | Relative Error0.088 | 26 | |
| Solving PDE | Burgers | Relative Error8.61 | 24 | |
| Inverse Problem | Poisson | PDE Residual178.5 | 21 | |
| Continuum Field Reconstruction (Rollout) | 2D Navier-Stokes nu=1e-5 | MSE1.302 | 18 | |
| Continuum Field Reconstruction | Shallow-Water (In-t) | MSE2.734 | 18 | |
| Continuum Field Reconstruction | Shallow-Water (Out-t) | MSE3.617 | 18 | |
| Continuum Field Reconstruction | Shallow-Water Avg | MSE3.175 | 18 | |
| Continuum Field Reconstruction | NSν1e-5 Avg | MSE1.094 | 18 |