Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
Conditional flow matching generates 3D urban wind and temperature fields in seconds with low error versus LES.
The paper uses conditional flow matching, guided by building geometry and mean flow, to generate three-dimensional instantaneous urban velocity and temperature fields in seconds. Overlapping pixel-space generation with shared-noise initialization avoids GPU memory limits while keeping spatial continuity. Against large-eddy simulation, NRMSE is 2.99% for wind and 1.77% for temperature on first-order statistics, and about 7% to 9% on second-order turbulence metrics. A local gust case shows the surrogate can support turbulence-aware urban design at far lower cost than LES.
- Conditional flow matching generates stochastic 3D wind and temperature fields.
- Shared-noise overlapping tiles preserve continuity under GPU memory limits.
- First-order NRMSE is 2.99% for wind and 1.77% for temperature.
- Turbulent kinetic energy NRMSE is about 7% versus large-eddy simulation.
Full article228 words · extracted from arxiv.org · click to collapse
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.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2610.10430