New 'Sculpt' framework improves urban wind prediction accuracy

Researchers have developed a novel framework called Sculpt to improve the accuracy and kinematic admissibility of urban wind prediction models. Traditional neural surrogates struggle with mass conservation and wall impermeability, issues that Sculpt addresses by integrating these constraints directly into its parameterization. This nested potential framework generates divergence-free velocity updates and enforces impermeability without requiring a per-step pressure projection, utilizing a multi-resolution approach to capture large-scale flow structures. The effectiveness of Sculpt was evaluated using the UrbanWindFlow dataset, which encompasses various urban morphologies and inflow conditions. AI

IMPACT This framework could improve the accuracy of climate modeling and urban planning tools.

RANK_REASON This is a research paper detailing a new computational framework for a specific scientific problem. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations
• UrbanWindFlow

• paper
• model release

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