Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading
This work addresses the problem of applying existing PDE foundation models to challenging material dynamics simulations for researchers and engineers in fields like materials science and high-energy-density physics, providing an incremental understanding of their transferability.
This paper evaluates the out-of-distribution transfer capabilities of two pretrained PDE foundation models, POSEIDON and MORPH, to material dynamics under extreme loading conditions. It benchmarks their performance on shock-driven multi-material interface dynamics and dynamic fracture/failure evolution, focusing on terminal-state prediction.
Most PDE foundation models are pretrained and fine-tuned on fluid-centric benchmarks. Their utility under extreme-loading material dynamics remains unclear. We benchmark out-of-distribution transfer on two discontinuity-dominated regimes in which shocks, evolving interfaces, and fracture produce highly non-smooth fields: shock-driven multi-material interface dynamics (perturbed layered interface or PLI) and dynamic fracture/failure evolution (FRAC). We formulate the downstream task as terminal-state prediction, i.e., learning a long-horizon map that predicts the final state directly from the first snapshot without intermediate supervision. Using a unified training and evaluation protocol, we evaluate two open-source pretrained PDE foundation models, POSEIDON and MORPH, and compare fine-tuning from pretrained weights against training from scratch across training-set sizes to quantify sample efficiency under distribution shift.