Back to feed
arXiv cs.LG
arXiv cs.LG
6/26/2026
Physics-guided Convolutional Neural Network for Domain Growth Prediction in Systems with Conserved Kinetics

Physics-guided Convolutional Neural Network for Domain Growth Prediction in Systems with Conserved Kinetics

Short summary

A physics-informed convolutional neural network learns to predict microstructural evolution in phase-separating systems, combining deep learning with the Cahn-Hilliard equation. The model maintains long-term stability and accurately reproduces the Lifshitz-Slyozov domain-growth law. This demonstrates effective surrogate modeling for conserved-kinetics systems applicable to complex dynamical systems.

  • •Physics-guided CNN predicts phase separation dynamics with long-term stability
  • •Model preserves mixture composition and matches Lifshitz-Slyozov growth law
  • •Framework extends to other complex systems governed by conserved kinetics

Generated with AI, which can make mistakes.

#research-breakthrough#ai-tools
Read full article at arXiv cs.LG

Is this a good recommendation for you?

Explore more

Towards Fast GNN Surrogates for CO2 Migration in Complex Geological Formations
arXiv cs.LG
Noise-Driven Escape from Metastable Phases explains Grokking in Deep Neural Networks
arXiv cs.LG
Geometry-free prediction of inertial lift forces in microfluidic devices using deep learning
arXiv cs.LG
When Do Conservation Laws Survive Learned Representations? Certified Horizons for Latent World Models
arXiv cs.LG