Modeling multivariable high-resolution 3D urban microclimate using localized fourier neural operator

Building and Environment, Год журнала: 2025, Номер unknown, С. 112668 - 112668

Опубликована: Фев. 1, 2025

Язык: Английский

A hybrid machine learning framework for wind pressure prediction on buildings with constrained sensor networks

Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2025, Номер unknown

Опубликована: Апрель 18, 2025

Abstract Accurate and efficient prediction of wind pressure distributions on high‐rise building façades is crucial for mitigating structural risks in urban environments. Conventional approaches rely extensive sensor networks, often hindered by cost, accessibility, architectural limitations. This study proposes a novel hybrid machine learning (ML) framework that reconstructs high‐fidelity (HFWP) coefficient fields from limited number sensors leveraging dynamic spatiotemporal feature extraction mapping. The methodology consists four key stages: (1) low‐fidelity field reconstruction data using constrained QR decomposition, (2) dimensionality reduction both HFWP reconstructions to extract dominant features, (3) mapping the reduced‐order representations long short‐term memory network, (4) over time. proposed approach, which predicts time history coefficients various directions, validated tunnel data, with case studies multiple façades—including windward, right‐side, leeward surfaces—under placement scenarios. also evaluated against alternative ML models, demonstrating superior accuracy reconstructing full field. results highlight robustness generalization capability model across different directions configurations, making it practical solution real‐time estimation health monitoring digital twin applications.

Язык: Английский

Deep Learning for Urban Wind Prediction: An Mlp-Mixer Approach with 3d Encoding

Опубликована: Янв. 1, 2025

Язык: Английский