3D High Resolution Urban Microclimate Reconstruction and Sensor Placement Optimization Based on Diffusion-based Deep Learning

Y. L. Xu

doi:10.1016/j.buildenv.2026.114877

3D High Resolution Urban Microclimate Reconstruction and Sensor Placement Optimization Based on Diffusion-based Deep Learning

2026-06-15

0

OA

AI

DOI：10.1016/j.buildenv.2026.114877

原文链接

查看原文

摘要

En 中文

• 提出了一种HGR框架，用于在有限计算资源下预测高分辨率城市微气候。• 使用时空变异性分析缩小传感器布置优化的搜索空间。• 采用基于SHAP的方法识别最优传感器布置位置。• 基于蒙特利尔地区的案例研究展示了所提出框架的有效性。

Keyword:

urban microclimate

diffusion model

MAP-GA

sensor placement

CNN

: CFD

Computational Fluid Dynamics

CNN

Convolutional Neural Network

CPU

Central Processing Unit

CityBEM

City Building Energy Model

CityFFD

City Fast Fluid Dynamics

DDPM

Denoising Diffusion Probabilistic Model

DL

Deep Learning

DNS

Direct Numerical Simulation

GAN

Generative Adversarial Network

GNN

Graph Neural Network

GP

Gaussian Process

GPU

Graphics Processing Unit

HGR

Hierarchical Generative-Refinement

IDDPM

Improved Denoising Diffusion Probabilistic Model

LFNO

Localized Fourier Neural Operator

LSTM

Long Short-Term Memory

MAE

Mean Absolute Error

MAP

Maximum a Posteriori

MAP-GA

Maximum a Posteriori Gradient Ascent

ML

Machine Learning

OOM

Out-of-memory

PCA

Principal Component Analysis

POD

Proper Orthogonal Decomposition

RANS

Reynolds-Averaged Navier–Stokes

RBF

Radial Basis Function

RMSE

Root Mean Square Error

SGMS-GNN

Scalable Graph-based Memory-Saving Graph Neural Network

SHAP

Shapley Additive Explanations

SVD

Singular Value Decomposition

T

Air Temperature

U

V, W, Velocity components in x-, y-, and z-directions

UHI

Urban Heat Island

VAE

Variational Autoencoder

3D High Resolution Urban Microclimate Reconstruction and Sensor Placement Optimization Based on Diffusion-based Deep Learning

摘要

AI总结

期刊

机构

引用论文