使用局部化傅里叶神经算子建模多变量高分辨率三维城市微气候
Modeling Multivariable High-resolution 3D Urban Microclimate Using Localized Fourier Neural Operator
AI总结：
针对FNO在多变量高分辨率三维城市微气候预测中存在的输出模糊、内存需求高和数据需求大等局限，提出Local-FNO模型，通过局部训练、几何编码和分块重叠，在单GPU上以近50倍CFD的速度实现高精度、高分辨率的湍流与热通量预测。
摘要：
结合风速和温度的准确城市微气候分析对于节能城市规划、支持碳减排、提升公共健康与舒适度以及推进低空经济至关重要。然而，耦合速度和温度的传统计算流体力学（CFD）模拟计算成本高昂。近期机器学习的进展为加速城市微气候模拟提供了有前景的替代方案。傅里叶神经算子（FNO）在预测城市风场中的单变量速度幅值方面已展现出效率和准确性。然而，对于多变量高分辨率三维城市微气候预测，FNO面临三个关键局限：输出质量模糊、GPU内存需求高以及大量数据需求。为了解决这些问题，我们提出了一种新型局部化傅里叶神经算子（Local-FNO）模型，该模型采用局部训练、几何编码和分块重叠。Local-FNO能够准确预测城市微气候中60秒内快速变化的湍流，该时长是平均湍流积分时间尺度的四倍，其速度平均误差为0.35 m/s，温度平均误差为0.30 °C。它还能准确捕捉由速度-温度相关性表示的湍流热通量。在2 km乘2 km的区域内，Local-FNO能将湍流模式解析至10 m分辨率。它在单个32 GB GPU上以1.5亿特征维度提供高分辨率预测，速度几乎是CFD求解器的50倍。与FNO相比，Local-FNO实现了预测误差降低23.9%，湍流脉动相关性提升47.3%。
英文摘要：
Accurate urban microclimate analysis with wind velocity and temperature is vital for energy-efficient urban planning, supporting carbon reduction, enhancing public health and comfort, and advancing the low-altitude economy. However, traditional computational fluid dynamics (CFD) simulations that couple velocity and temperature are computationally expensive. Recent machine learning advancements offer promising alternatives for accelerating urban microclimate simulations. The Fourier neural operator (FNO) has shown efficiency and accuracy in predicting single-variable velocity magnitudes in urban wind fields. Yet, for multivariable high-resolution 3D urban microclimate prediction, FNO faces three key limitations: blurry output quality, high GPU memory demand, and substantial data requirements. To address these issues, we propose a novel localized Fourier neural operator (Local-FNO) model that employs local training, geometry encoding, and patch overlapping. Local-FNO provides accurate predictions for rapidly changing turbulence in urban microclimate over 60 seconds, four times the average turbulence integral time scale, with an average error of 0.35 m/s in velocity and 0.30 °C in temperature. It also accurately captures turbulent heat flux represented by the velocity-temperature correlation. In a 2 km by 2 km domain, Local-FNO resolves turbulence patterns down to a 10 m resolution. It provides high-resolution predictions with 150 million feature dimensions on a single 32 GB GPU at nearly 50 times the speed of a CFD solver. Compared to FNO, Local-FNO achieves a 23.9% reduction in prediction error and a 47.3% improvement in turbulent fluctuation correlation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
