← Back to Model Beat
Policy·1d ago·all news from July 7, 2026

Inpainting U-Net for seamless pedestrian-level wind prediction across urban morphologies

Researchers have developed a two-stage U-Net framework that models pedestrian-level wind patterns across diverse urban layouts. By using this AI-based inpainting technique, designers can predict wind flow significantly faster than traditional high-fidelity simulation methods.

Covered by 1 source

  • AarXiv CS.AIJingzi Huang, Claire E. Heaney, Tao Li, Xinzhe Li, Graham O. Hughes, Maarten van Reeuwijk1d ago

Related stories

PolicyPritzker signs Illinois bill aimed at artificial intelligence accountabilityJul 6 · 11 sourcesPolicyChinese AI Models Advance, Causing US Cybersecurity AnxietyJul 6 · 4 sourcesPolicyPairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact GenerationJul 3Policy6G Sensing Security: Distributed Game-Theoretic RL for Urban Beamforming and Attacker DetectionJul 8