# Using ML surrogate models to accelerate CFD/FEA simulations — what's working in practice for engineering data? > Source: > Published: 2026-06-22 08:53:47+00:00 I work in engineering simulation (CFD and FEA) and I’m increasingly interested in using ML to cut down the cost of expensive solver runs. The traditional loop — mesh, solve, post-process — can take hours per design iteration, and I’d love to hear from people who’ve actually deployed ML surrogates in this space rather than just read the papers. A few things I’m trying to get a realistic picture of: **Architectures:** For predicting fields (temperature, pressure, stress) over a geometry, what’s been working better in practice — graph neural networks on mesh data, Fourier Neural Operators, point-cloud approaches, or plain MLP/CNN surrogates on parameterized designs? **Data efficiency:** Simulation data is expensive to generate. How few training samples have people gotten away with for a useful surrogate, and does transfer learning across similar geometries actually help? **Physics-informed approaches:** Has anyone found PINNs practical for real engineering geometries, or are they still mostly a research curiosity compared to data-driven surrogates? **Generalization:** The hard part is a model that holds up on geometries/boundary conditions outside the training distribution. What’s worked for keeping surrogates trustworthy there? Interested in real-world experience — what gave you a usable accuracy-vs-speed tradeoff, and where did ML surrogates fall down and force you back to the full solver?