arXiv：cs.LG· Shaoxiang Qin, Theodore Potsis, Dongxue Zhan, Xue Liu, Ted Stahopoulos, Liangzhu Leon Wang·· 13 小时前
FLUME：基于傅里叶神经算子的快速城市微气候模拟器，可预测未知城市形态下的风场与温度场
Fast localized urban microclimate emulator: wind and temperatures in unseen urban morphologies
AI 导读
研究者提出 FLUME，一个基于傅里叶神经算子的几何感知框架，可快速预测三维风场与温度场。该方法引入多方向距离特征（MDDF），仅用 23 个城市街区的 CFD 数据即可训练，在未知城市配置上实现流向速度平均绝对误差 0.2 m/s、温度误差 0.19°C，并通过深度集成与保形预测给出校准的不确定性区间。
正文
Abstract:Urban microclimate, encompassing wind and temperature fields shaped by building geometry, strongly affects building energy use, pedestrian wind comfort, pollutant dispersion, the urban heat island, and public health. Conventional Computational Fluid Dynamics (CFD) is computationally prohibitive for rapid assessments, while many deep learning approaches require extensive training data and struggle with generalization to unseen configurations. In this work, we present the Fast Localized Urban Microclimate Emulator (FLUME), a rapid, data-efficient, and geometry-aware framework based on a Fourier neural operator for predicting three-dimensional wind and temperature fields. FLUME assumes that, under prescribed inflow and thermal forcing, much of the spatial variation of these mean fields is controlled by surrounding building geometry. The framework introduces a Multi-Directional Distance Feature (MDDF), which captures geometry over adaptive, visibility-defined spatial scales. By decomposing simulations of only 23 urban blocks into smaller 3D patches enriched with precomputed MDDF information, FLUME enables learning from limited CFD data. The model achieves mean absolute errors of 0.2 m/s for streamwise velocity and 0.19$^{\circ}$C for temperature on unseen urban configurations. A deep ensemble provides a practical proxy for epistemic uncertainty, and conformal prediction transforms these estimates into calibrated prediction intervals. Ensemble spread is positively related to local prediction error, with greater uncertainty in roof-level shear layers, building wakes, and vertical velocity near the ground. These results indicate FLUME's potential for rapid scenario assessment in urban design and urban climate studies.
| Comments: | Interactive FLUME demo: this https URL |
| Subjects: | Fluid Dynamics (physics.flu-dyn); Machine Learning (cs.LG) |
| Cite as: | arXiv:2503.19708 [physics.flu-dyn] |
| (or arXiv:2503.19708v3 [physics.flu-dyn] for this version) | |
| https://doi.org/10.48550/arXiv.2503.19708 arXiv-issued DOI via DataCite |
Submission history
From: Shaoxiang Qin [view email]
[v1]
Tue, 25 Mar 2025 14:36:01 UTC (2,694 KB)
[v2]
Tue, 19 May 2026 20:04:41 UTC (3,572 KB)
[v3]
Fri, 9 Oct 2026 15:06:11 UTC (3,468 KB)
来源：arXiv：cs.LG · arxiv.org