Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910041137741824 |
|---|---|
| author | Rautela, Mahindra Most, Alexander Mansingh, Siddharth Pachalieva, Aleksandra Love, Bradley Malley, Daniel O Scheinker, Alexander Hickmann, Kyle Oyen, Diane Debardeleben, Nathan Lawrence, Earl Biswas, Ayan |
| author_facet | Rautela, Mahindra Most, Alexander Mansingh, Siddharth Pachalieva, Aleksandra Love, Bradley Malley, Daniel O Scheinker, Alexander Hickmann, Kyle Oyen, Diane Debardeleben, Nathan Lawrence, Earl Biswas, Ayan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04354 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading Rautela, Mahindra Most, Alexander Mansingh, Siddharth Pachalieva, Aleksandra Love, Bradley Malley, Daniel O Scheinker, Alexander Hickmann, Kyle Oyen, Diane Debardeleben, Nathan Lawrence, Earl Biswas, Ayan Machine Learning 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. |
| title | Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.04354 |