Structure-preserving Fourier Neural Operators for Long-time Cahn-Hilliard Dynamics under Coarse Temporal Supervision (Q7366673)

From MaRDI portal

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

scientific article from arXiv
Language Label Description Also known as
default for all languages
No label defined
    English
    Structure-preserving Fourier Neural Operators for Long-time Cahn-Hilliard Dynamics under Coarse Temporal Supervision
    scientific article from arXiv

      Statements

      math.NA
      0 references
      physics.comp-ph
      0 references
      2026
      0 references
      0 references
      Structure-preserving Fourier Neural Operators for Long-time Cahn-Hilliard Dynamics under Coarse Temporal Supervision (English)
      0 references
      Yingli Li
      0 references
      Y. C. Zhou
      0 references
      We develop a two-stage structure-preserving Fourier Neural Operator (FNO) framework for long-time Cahn-Hilliard simulations under coarse temporal supervision by incorporating physical principles into machine learning: bound-conforming regularization (bcFNO) stabilizes the prediction, and structure-function regularization (spFNO) corrects late-stage coarsening statistics.
      0 references
      Cahn-Hilliard
      0 references
      Fourier Neural Operators
      0 references
      Structure-preserving
      0 references

      Identifiers

      0 references