New ONECYL benchmark advances graph-based CFD surrogate modeling

Researchers have introduced ONECYL, a new benchmark designed to advance graph-based surrogate modeling for computational fluid dynamics (CFD) simulations. This benchmark addresses the scarcity of datasets for unsteady flow past a circular cylinder across various flow regimes. ONECYL includes high-fidelity simulations, time-resolved data, and a unified evaluation framework to assess model accuracy and physical fidelity. A Graph Transformer model was developed as a baseline, demonstrating that encoding cylinder geometry and using physics-based regularization improves prediction accuracy and generalization. AI

IMPACT Advances graph-based surrogate modeling for CFD, potentially accelerating simulation speeds and improving accuracy in fluid dynamics research.

RANK_REASON The cluster describes a new benchmark and a baseline model for graph-based surrogate modeling in computational fluid dynamics, published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Gotit.pub
• Graph transformer neural network force field for prediction of atomic forces and energies in molecular dynamic simulations
• Hugging Face
• ONECYL
• ScienceCast
• Variational Multiscale Enrichment Method for Modeling of Structures Subjected to Extreme Environments

• paper
• infra

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