3 papers
cs.LG2025
Benchmarking neural surrogates on realistic spatiotemporal multiphysics flows
Runze Mao, Rui Zhang, Xuan Bai +21
Predicting multiphysics dynamics is computationally expensive and challenging due to the severe coupling of multi-scale, heterogeneous physical processes. While neural surrogates p…
physics.flu-dyn2025
Vector-based loss functions for turbulent flow field inpainting
Samuel J. Baker, Shubham Goswami, Xiaohang Fang +1
When developing scientific machine learning (ML) approaches, it is often beneficial to embed knowledge of the physical system in question into the training process. One way to achi…
physics.flu-dyn2024
EngineBench: Flow Reconstruction in the Transparent Combustion Chamber III Optical Engine
Samuel J. Baker, Michael A. Hobley, Isabel Scherl +3
We present EngineBench, the first machine learning (ML) oriented database to use high quality experimental data for the study of turbulent flows inside combustion machinery. Prior…