Generative diffusion learning for parametric partial differential equations
It provides a probabilistic operator learning framework for PDEs, enabling uncertainty quantification and noise robustness, which is valuable for scientific computing applications.
The paper develops a generative diffusion model to learn the solution operator for parametric PDEs, achieving comparable accuracy to Fourier Neural Operators while automatically quantifying uncertainty and handling noisy data.
We develop a class of data-driven generative models that approximate the solution operator for parameter-dependent partial differential equations (PDE). We propose a novel probabilistic formulation of the operator learning problem based on recently developed generative denoising diffusion probabilistic models (DDPM) in order to learn the input-to-output mapping between problem parameters and solutions of the PDE. To achieve this goal we modify DDPM to supervised learning in which the solution operator for the PDE is represented by a class of conditional distributions. The probabilistic formulation combined with DDPM allows for an automatic quantification of confidence intervals for the learned solutions. Furthermore, the framework is directly applicable for learning from a noisy data set. We compare computational performance of the developed method with the Fourier Network Operators (FNO). Our results show that our method achieves comparable accuracy and recovers the noise magnitude when applied to data sets with outputs corrupted by additive noise.