California Institute of Technology, Nvidia Corporation, United States of America
We propose MeshfreeFlowNet, a novel deep learning framework, to generate continuous (grid-free) spatiotemporal solutions from the low-resolution inputs. While being computationally efficient, MeshfreeFlowNet accurately recovers the fine-scale quantities of interest. MeshfreeFlowNet allows for: (i) the output to be sampled at all spatio-temporal resolutions; (ii) a set of Partial Differential Equation (PDE) constraints to be imposed; and (iii) training on fixed-size inputs on arbitrarily sized spatiotemporal domains owing to its fully convolutional encoder.
We empirically study the performance of PCSR on the task of super-resolution of turbulent flows in the Rayleigh–Bénard convection problem. Across a diverse set of evaluation metrics, we show that PCSR significantly outperforms existing baselines. Furthermore, we provide a large scale implementation of PCSR and show that it efficiently scales across large clusters, achieving 96.80% scaling efficiency on up to 128 GPUs and a training time of less than 4 minutes.