Metraipolis › archive › dc_a923e98eeebf

CEENs: Causality-enforced evolutional networks for solving time-dependent partial differential equations — arXiv:2610.04405

Source
arXiv
Original
https://arxiv.org/abs/2610.04405
License (as archived)
CC0-1.0
Archived
2026-10-06T05:30:32.806Z
SHA-256 of the archived text
31ddb2d0d0ca24a628168da70bf521985b4875e78ef802651df89e6ffc692e54
Stable URL of this page
https://metraipolis.com/documento/dc_a923e98eeebf

How to cite

CEENs: Causality-enforced evolutional networks for solving time-dependent partial differential equations — arXiv:2610.04405 — arXiv, https://arxiv.org/abs/2610.04405 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a923e98eeebf (Metraipolis archive dc_a923e98eeebf, sha256 31ddb2d0d0ca24a628168da70bf521985b4875e78ef802651df89e6ffc692e54)
BibTeX
@misc{dca923e98eeebf,
  title = {CEENs: Causality-enforced evolutional networks for solving time-dependent partial differential equations — arXiv:2610.04405},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04405},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a923e98eeebf; sha256 31ddb2d0d0ca24a628168da70bf521985b4875e78ef802651df89e6ffc692e54},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04405. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Despite the growing popularity of physics-informed neural networks (PINNs), their applicability in the long-time integration of partial differential equations (PDEs) remains constrained. We argue that this problem stems from the lack of consideration of temporal causality in the original PINN formulation, resulting in a bias towards satisfying governing equations at later times before learning the initial condition and hence leading to erroneous solutions. To this end, we propose a novel method that seamlessly integrates temporal causality into the training process. Drawing inspiration from classical numerical methods where the temporal causality is reflected, we divide the time domain into nonoverlapping subintervals, assign a unique neural network to each subinterval, and construct a loss function founded on the integral form of PDEs within these subintervals. The proposed networks undergo sequential training, beginning with the initial time step. Our method demonstrates significant improvement in accuracy for long-time simulations of various PDE problems where the original PINN method fails while it requires less computational cost and memory compared to the PINN method. A parallelization algorithm is provided to further enhance the computational efficiency, showing a significant speedup for solving time-dependent PDEs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2610.04405 — 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 2026-10-06T05:27:05.678Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).