Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MAgNet: Mesh Agnostic Neural PDE Solver

About

The computational complexity of classical numerical methods for solving Partial Differential Equations (PDE) scales significantly as the resolution increases. As an important example, climate predictions require fine spatio-temporal resolutions to resolve all turbulent scales in the fluid simulations. This makes the task of accurately resolving these scales computationally out of reach even with modern supercomputers. As a result, current numerical modelers solve PDEs on grids that are too coarse (3km to 200km on each side), which hinders the accuracy and usefulness of the predictions. In this paper, we leverage the recent advances in Implicit Neural Representations (INR) to design a novel architecture that predicts the spatially continuous solution of a PDE given a spatial position query. By augmenting coordinate-based architectures with Graph Neural Networks (GNN), we enable zero-shot generalization to new non-uniform meshes and long-term predictions up to 250 frames ahead that are physically consistent. Our Mesh Agnostic Neural PDE Solver (MAgNet) is able to make accurate predictions across a variety of PDE simulation datasets and compares favorably with existing baselines. Moreover, MAgNet generalizes well to different meshes and resolutions up to four times those trained on.

Oussama Boussif, Dan Assouline, Loubna Benabbou, Yoshua Bengio• 2022

Related benchmarks

TaskDatasetResultRank
Zero-shot super-resolutionE1 (test)
MAE0.107
48
Neural Super-Resolution for Mesh-Based SimulationsDataset-1
RMSE0.0979
27
Neural Super-Resolution for Mesh-Based SimulationsDataset 2
RMSE0.1305
27
Neural Super-Resolution for Mesh-Based SimulationsDataset 3
RMSE0.0754
27
Showing 4 of 4 rows

Other info

Code

Follow for update