Deep learning framework enables cross-physics mapping between distinct physical domains

Researchers have introduced Cross-Physics Mapping (CPM), a novel framework for operator learning that enables deep learning models to translate between physical domains governed by different equations. The study proposes conditions for such mappings through compatible latent representations and a dimensionless scaling principle. Experiments with diffusion and wave fields showed that while wave-to-diffusion mappings are more stable, diffusion-to-wave mappings are more challenging, with U-NO architecture performing best in the latter case. AI

IMPACT This research could enable new applications in scientific modeling and simulation by allowing AI to bridge different physical phenomena.

RANK_REASON The cluster contains a research paper detailing a new framework and experimental results for operator learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Cross-Physics Mapping
• deep learning
• DeepONet
• Fourier
• Galerkin neural operators
• ResUNet

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →