PulseAugur
EN
LIVE 13:08:01

New ESPINN framework aids phase-field model identification

By PulseAugur Editorial · [3 sources] ·

Researchers have developed an extended pseudo-spectral physics-informed neural network (ESPINN) framework to identify phase-field models from observational data. This method allows for the simultaneous recovery of bulk chemical potential and unknown gradient coefficients, crucial for understanding pattern formation in phase separation. Numerical experiments using the Cahn-Hilliard equation show that ESPINN can accurately reconstruct these parameters even from limited data, with performance degrading gracefully in the presence of noise and improving with more snapshots. AI

IMPACT This framework offers a data-efficient method for learning complex physical properties, potentially accelerating scientific discovery in materials science and other fields.

RANK_REASON The cluster describes a new research paper detailing a novel neural network framework for scientific modeling.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

New ESPINN framework aids phase-field model identification

COVERAGE [3]

  1. arXiv cs.LG TIER_1 English(EN) · Callum Marsh, Radek Erban, Andreas Munch ·

    Extended pseudo-spectral physics-informed neural networks for phase-field models

    arXiv:2606.24660v1 Announce Type: cross Abstract: Phase-field models play a central role in the continuum description of phase separation, in which the bulk free-energy density and the interfacial thickness parameter determine pattern formation and microstructural evolution. In p…

  2. arXiv cs.LG TIER_1 English(EN) · Andreas Munch ·

    Extended pseudo-spectral physics-informed neural networks for phase-field models

    Phase-field models play a central role in the continuum description of phase separation, in which the bulk free-energy density and the interfacial thickness parameter determine pattern formation and microstructural evolution. In practice, these constitutive quantities are rarely …

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    Extended pseudo-spectral physics-informed neural networks for phase-field models

    Phase-field models play a central role in the continuum description of phase separation, in which the bulk free-energy density and the interfacial thickness parameter determine pattern formation and microstructural evolution. In practice, these constitutive quantities are rarely …

RELATED TOPICS