Data-efficient operator learning for solving high Mach number fluid flow problems
This addresses data-efficient operator learning for high-speed fluid dynamics, which is incremental as it builds on existing SciML methods.
The paper tackled the problem of predicting high Mach number fluid flows over irregular geometries with limited data using Scientific Machine Learning (SciML), showing that Neural Basis Functions (NBF) outperformed a baseline model by learning behavior modes from data.
We consider the problem of using SciML to predict solutions of high Mach fluid flows over irregular geometries. In this setting, data is limited, and so it is desirable for models to perform well in the low-data setting. We show that Neural Basis Functions (NBF), which learns a basis of behavior modes from the data and then uses this basis to make predictions, is more effective than a basis-unaware baseline model. In addition, we identify continuing challenges in the space of predicting solutions for this type of problem.