Metraipolis › archive › dc_000ff2ea8cef

RECAST: A Machine-Learning Framework for Correction and Super-Resolution of Coarse-Grid PDE Solvers — arXiv:2608.11572

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.11572
License (as archived): CC0-1.0
Archived: 2026-10-19T05:39:50.908Z
SHA-256 of the archived text: 31ff5eb73e79d32b0943d531538060db818e104e038dd31e9c979268f9181b2b
Stable URL of this page: https://metraipolis.com/documento/dc_000ff2ea8cef

How to cite

RECAST: A Machine-Learning Framework for Correction and Super-Resolution of Coarse-Grid PDE Solvers — arXiv:2608.11572 — arXiv (en), https://arxiv.org/abs/2608.11572 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_000ff2ea8cef (Metraipolis archive dc_000ff2ea8cef, sha256 31ff5eb73e79d32b0943d531538060db818e104e038dd31e9c979268f9181b2b)

BibTeX

@misc{dc000ff2ea8cef,
  title = {RECAST: A Machine-Learning Framework for Correction and Super-Resolution of Coarse-Grid PDE Solvers — arXiv:2608.11572},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11572},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_000ff2ea8cef; sha256 31ff5eb73e79d32b0943d531538060db818e104e038dd31e9c979268f9181b2b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11572. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coarse-grid numerical solvers can substantially reduce the computational cost of time-dependent PDE simulation, but under-resolution often degrades both the trajectory and the spatial fidelity of the solution. We introduce RECAST (Recurrent Error Correction And Super-resolution of coarse-grid Trajectories), a machine-learning framework designed to restore this lost accuracy while retaining coarse-grid evolution. RECAST combines learned correction within the numerical time-stepping loop with reconstruction of the corresponding fine-grid state from the corrected coarse history. We evaluate the framework on six one-dimensional PDE systems spanning transport, diffusion, dispersion, reaction, and wave dynamics, using spatial grids coarsened by factors of 8-16 and 1000-step closed-loop rollouts from unseen initial conditions. Across the test cases, RECAST remains closely aligned with the fine-grid reference solutions and reduces time-averaged relative error by approximately 50-92% compared with the corresponding uncorrected coarse-grid solvers. Additional tests show generalization to unseen PDE parameter values, while comparison with a contemporary coarse-correction architecture shows that RECAST achieves lower error and better long-horizon agreement with the fine-grid reference over 5000-step rollouts. These results demonstrate that the learned correction and reconstruction capabilities of RECAST can enable substantially coarser PDE evolution without the corresponding loss of solution fidelity, providing a proof-of-concept route toward machine-learning acceleration of higher-dimensional numerical simulations across science and engineering.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2608.11572 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:18:32.477Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).