| Popis: |
Deep models have recently emerged as a promising tool to solve partial differential equations (PDEs), known as neural PDE solvers. While neural solvers trained from either simulation data or physics-informed loss can solve PDEs reasonably well, they are mainly restricted to a few instances of PDEs, e.g. a certain equation with a limited set of coefficients. This limits the generalization of neural solvers to diverse PDEs, impeding them from being practical surrogate models for numerical solvers. In this paper, we present the Universal PDE Solver (Unisolver) capable of solving a wide scope of PDEs by training a novel Transformer model on diverse data and conditioned on diverse PDEs. Instead of purely scaling up data and parameters, Unisolver stems from the theoretical analysis of the PDE-solving process. Our key finding is that a PDE solution is fundamentally under the control of a series of PDE components, e.g. equation symbols, coefficients, and boundary conditions. Inspired by the mathematical structure of PDEs, we define a complete set of PDE components and flexibly embed them as domain-wise (e.g. equation symbols) and point-wise (e.g. boundaries) conditions for Transformer PDE solvers. Integrating physical insights with recent Transformer advances, Unisolver achieves consistent state-of-the-art results on three challenging large-scale benchmarks, showing impressive performance gains and favorable PDE generalizability. |
