Machine learning prediction and analysis of area-averaged external pressure coefficients for low-rise dual-slope building roofs in a uniform turbulent flow field
Abstract
Accurate prediction of roof area-averaged external pressure coefficients ( C̅p,A ) is crucial for low-rise building design. To isolate geometric and turbulence effects from atmospheric wind shear, wind tunnel experiments were conducted under uniform turbulent flow conditions covering roof pitch angles (0°–30°), wind directions, and turbulence intensities. To overcome the smoothing limitations of conventional regression methods, an ensemble learning framework (Random Forest, XGBoost, and LightGBM) was developed and evaluated using a rigorous Leave-One-Slope-Out (LOSO) cross-validation strategy. Results show that around the roof pitch angle of α = 18.4°, a pronounced variation in aerodynamic pressure response occurs under oblique wind conditions. XGBoost maintains robust predictive performance, outperforming conventional response surface modeling under nonlinear transition conditions. Furthermore, extrapolation failure at α = 30° delineates the practical limits of data-driven models in predicting unseen aerodynamic regimes. Finally, SHAP analysis demonstrates that the model-derived feature attribution patterns are generally consistent with previously reported aerodynamic observations, providing a physically interpretable framework for wind load prediction under complex flow transitions.
Related
- Empirical Parameterizations of ULF Power and Drift Orbit Averaged Radial Diffusion Coefficients From Ground Magnetometers for Different MLT
- Machine-learning prediction of freezing temperature in Pb-contaminated soils remediated with biochar
- Hybrid stacked bidirectional deep learning with attention based air pollution prediction for environmental sustainability
- Beyond advection: A Lagrangian framework for microplastic transport in depth-averaged shallow water flows
- Machine learning-driven prediction of heavy metal pollution for aquatic health surveillance and disease control
BibTeX
@article{yang2026machine,
title = {{Machine learning prediction and analysis of area-averaged external pressure coefficients for low-rise dual-slope building roofs in a uniform turbulent flow field}},
author = {Mengchang Yang and Yinghang Fu and Yangjin Yuan and Huiling Duan and Jie Wang and Il-seung Yang},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-71463-9},
url = {https://www.nature.com/articles/s41598-026-71463-9},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine learning prediction and analysis of area-averaged external pressure coefficients for low-rise dual-slope building roofs in a uniform turbulent flow field
AU - Mengchang Yang
AU - Yinghang Fu
AU - Yangjin Yuan
AU - Huiling Duan
AU - Jie Wang
AU - Il-seung Yang
PY - 2026
DA - 2026/10/01
JO - Scientific Reports
DO - 10.1038/s41598-026-71463-9
UR - https://www.nature.com/articles/s41598-026-71463-9
AB - Accurate prediction of roof area-averaged external pressure coefficients ( C̅_p,A ) is crucial for low-rise building design. To isolate geometric and turbulence effects from atmospheric wind shear, wind tunnel experiments were conducted under uniform turbulent flow conditions covering roof pitch angles (0°–30°), wind directions, and turbulence intensities. To overcome the smoothing limitations of conventional regression methods, an ensemble learning framework (Random Forest, XGBoost, and LightGBM) was developed and evaluated using a rigorous Leave-One-Slope-Out (LOSO) cross-validation strategy. Results show that around the roof pitch angle of α = 18.4°, a pronounced variation in aerodynamic pressure response occurs under oblique wind conditions. XGBoost maintains robust predictive performance, outperforming conventional response surface modeling under nonlinear transition conditions. Furthermore, extrapolation failure at α = 30° delineates the practical limits of data-driven models in predicting unseen aerodynamic regimes. Finally, SHAP analysis demonstrates that the model-derived feature attribution patterns are generally consistent with previously reported aerodynamic observations, providing a physically interpretable framework for wind load prediction under complex flow transitions.
SN - 2045-2322
ER -