Cross-Domain Pretraining for Steady-State Neural CFD Surrogates

Key points

• In this work, we take a step toward addressing this by studying neural surrogates trained across different geometries, boundary conditions, and fidelities.1
• We find that cross-domain pretraining improves zero- and few-shot performance on held-out datasets relative to both training from scratch and transferring from domain-specific experts.1
• Furthermore, we study how and why cross-domain pretraining works in CFD surrogates, and find that simply pooling steady-state datasets is both sufficient and effective.1
• Given the high cost of generating CFD data, leveraging existing datasets through cross-domain pretraining will likely be a valuable strategy as future surrogates expand to tackle new problems and use cases.1

Sources (1)

• [1]Cross-Domain Pretraining for Steady-State Neural CFD Surrogates
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 04:49 PM

  Neural surrogates for computational fluid dynamics (CFD) have the potential to greatly enhance engineering innovation through accelerating simulation.

  In this work, we take a step toward addressing this by studying neural surrogates trained across different geometries, boundary conditions, and fidelities.

Extractive summary: sentences quoted from the sources.