aiqbench analysis
This research applies Conditional Flow Matching, a generative AI technique, to rapidly simulate complex 3D urban wind and temperature fields that traditional Large-eddy simulations cannot compute quickly enough for iterative design. By operating in overlapping pixel spaces, the model overcomes GPU memory limits while accurately capturing turbulent stochasticity with low error rates against physics-based reference data. This approach makes turbulence-aware urban climate adaptation computationally feasible by bridging the gap between high-fidelity physics and fast generative inference.
Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
arXiv:2610.10430v1 Announce Type: cross Abstract: Rapid and accurate prediction of urban wind and temperature fields is important for urban microclimate design and climate adaptation. Large-eddy simulation (LES) effectively resolves these instantaneous fields, but its application is limited in iterative design of urban microclimate applications due to high computational cost. Existing regressive data-driven models offers quick outputs, but they produce only deterministic point predictions that inherently fail to represent turbulent stochasticity. This paper adopts a novel generative framework of Conditional Flow Matching (CFM) that uses building geometry and mean flow as guidance to generate plausible three-dimensional instantaneous velocity and temperature fields for urban microclimate in seconds. To overcome the GPU memory bottleneck of pixel space 3D generation, the model operates in parallel on overlapping pixel space through a shared-noise initialization that preserves high spatial continuity of flow structure across the entire domain. Against reference LES data, the CFM surrogate can rapidly and accurately restore the first-order statistics with Normalized Root Mean Square Error (NRMSE) of 2.99% for wind and 1.77% for temperature, second-order turbulence metrics with NRMSE of 7.17% for wind and 8.84% for temperature, turbulent kinetic energy with NRMSE of 7%, probability density function and vertical profiles in representative locations. Wind engineering application of local gust prediction demonstrate that the speed and accuracy of CFM, supporting the use of generative AI for making turbulence-aware resilient urban design and climate adaptation more computationally feasible.
Abstract:Rapid and accurate prediction of urban wind and temperature fields is important for urban microclimate design and climate adaptation. Large-eddy simulation (LES) effectively resolves these instantaneous fields, but its application is limited in iterative design of urban microclimate applications due to high computational cost. Existing regressive data-driven models offers quick outputs, but they produce only deterministic point predictions that inherently fail to represent turbulent stochasticity. This paper adopts a novel generative framework of Conditional Flow Matching (CFM) that uses building geometry and mean flow as guidance to generate plausible three-dimensional instantaneous velocity and temperature fields for urban microclimate in seconds. To overcome the GPU memory bottleneck of pixel space 3D generation, the model operates in parallel on overlapping pixel space through a shared-noise initialization that preserves high spatial continuity of flow structure across the entire domain. Against reference LES data, the CFM surrogate can rapidly and accurately restore the first-order statistics with Normalized Root Mean Square Error (NRMSE) of 2.99% for wind and 1.77% for temperature, second-order turbulence metrics with NRMSE of 7.17% for wind and 8.84% for temperature, turbulent kinetic energy with NRMSE of 7%, probability density function and vertical profiles in representative locations. Wind engineering application of local gust prediction demonstrate that the speed and accuracy of CFM, supporting the use of generative AI for making turbulence-aware resilient urban design and climate adaptation more computationally feasible.
Fluid Dynamics (physics.flu-dyn); Computational Engineering, Finance, and Science (cs.CE); Machine Learning (cs.LG); Atmospheric and Oceanic Physics (physics.ao-ph)
arXiv:2610.10430 [physics.flu-dyn]
(or arXiv:2610.10430v1 [physics.flu-dyn] for this version)
https://doi.org/10.48550/arXiv.2610.10430 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 260 words
Related coverage
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · Oct 8, 2026
News
Quantum Computing Report · Jun 7, 2026
Efficient Flow Matching using Latent Variables
arXiv · Jun 16, 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · Sep 4, 2026