{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiezr2fbmqcjqdh3czf3tud5bk52z5z3au4cy46zajvyhjmwtsgqu4",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mnrmjel5fij2"
  },
  "path": "/t/choosing-a-surrogate-model-architecture-to-predict-steady-state-thermal-fields-from-cad-geometry-fno-vs-pinn-vs-gnn/176615#post_1",
  "publishedAt": "2026-06-08T10:18:39.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "I work on thermal and CFD simulation for electronics and battery systems, and I’m trying to stand up an ML surrogate that predicts steady-state temperature fields from a parameterized geometry plus boundary conditions, so we can explore design variants without running a full solver each time.\n\nI’ve narrowed it to three candidate approaches and would value input from anyone who’s shipped something similar:\n\n  1. **Fourier Neural Operators (FNO)** — attractive for resolution independence, but most examples I’ve seen are on structured grids. Has anyone made FNO work cleanly on irregular engineering geometries without heavy remeshing onto a regular grid?\n\n  2. **Physics-Informed Neural Networks (PINN)** — appealing because they bake in the governing equations, but I’ve found training stability poor on stiff problems with sharp gradients (which thermal hot-spots are). Have people gotten PINNs reliable enough for engineering-grade accuracy, or are they still mostly demonstrative?\n\n  3. **Graph Neural Networks** on the mesh directly — feels the most natural fit for unstructured meshes, but I’m unsure about generalization to geometries outside the training distribution.\n\n\n\n\nMy constraints: training data is expensive (each label is a full CFD/thermal solve), so sample efficiency matters a lot, and I need errors low enough to trust for early design screening, not just qualitative trends.\n\nFor those who’ve built PDE surrogates in practice — which of these held up, and where did the accuracy actually break down?",
  "title": "Choosing a surrogate-model architecture to predict steady-state thermal fields from CAD geometry — FNO vs PINN vs GNN?"
}