Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields

2026-10-07

AI Summary

This study addresses the high computational cost and inherent difficulty in capturing turbulent stochasticity when predicting instantaneous wind and temperature fields in urban microclimates. We propose a generative framework based on Conditional Flow Matching (CFM), driven by large-eddy simulation data and conditioned on building geometry and mean flow conditions. To overcome GPU memory bottlenecks, we introduce an overlapping spatial parallelism mechanism with shared noise initialization, enabling second-level, high-fidelity generation of three-dimensional multivariate physical fields. Experimental results demonstrate that the normalized root-mean-square errors for first-order wind speed and temperature statistics reach 2.99% and 1.77%, respectively, while second-order metrics remain around 8%. The method accurately reproduces turbulent kinetic energy and probability distributions, validating the feasibility of leveraging generative AI to empower iterative design for resilient cities.

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.

Problem

• Urban Microclimate
• 3D Instantaneous Fields
• Turbulent Stochasticity
• Conditional Flow Matching
• Computational Cost

Innovation

• Conditional Flow Matching
• 3D Generative Model
• Urban Microclimate
• Shared-noise Initialization
• Turbulence Stochasticity