P3D: Scalable Neural Surrogates for High-Resolution 3D Physics Simulations with Global Context
This provides a scalable solution for researchers and engineers needing efficient high-resolution 3D physics simulations, though it appears incremental as an architectural improvement.
The authors tackled the problem of creating scalable neural surrogates for high-resolution 3D physics simulations by introducing a hybrid CNN-Transformer backbone architecture, which significantly outperformed existing methods in speed and accuracy and scaled to spatial resolutions up to 512³.
We present a scalable framework for learning deterministic and probabilistic neural surrogates for high-resolution 3D physics simulations. We introduce a hybrid CNN-Transformer backbone architecture targeted for 3D physics simulations, which significantly outperforms existing architectures in terms of speed and accuracy. Our proposed network can be pretrained on small patches of the simulation domain, which can be fused to obtain a global solution, optionally guided via a fast and scalable sequence-to-sequence model to include long-range dependencies. This setup allows for training large-scale models with reduced memory and compute requirements for high-resolution datasets. We evaluate our backbone architecture against a large set of baseline methods with the objective to simultaneously learn the dynamics of 14 different types of PDEs in 3D. We demonstrate how to scale our model to high-resolution isotropic turbulence with spatial resolutions of up to $512^3$. Finally, we demonstrate the versatility of our network by training it as a diffusion model to produce probabilistic samples of highly turbulent 3D channel flows across varying Reynolds numbers, accurately capturing the underlying flow statistics.