Interpretation of Machine-Learning-Based (Black-box) Wind Pressure Predictions for Low-Rise Gable-Roofed Buildings Using Shapley Additive Explanations (SHAP)

Buildings

Upaka Rathnayake¹  Pasindu Meddage²  Hazi Md. Azamathulla³  Imesh Ekanayake⁴  Udara Sachinthana Perera⁵  Md Azlin Md Said⁶ 

[1] Department of Civil Engineering, Faculty of Engineering, Sri Lanka Institute of Information Technology, Malabe 10115, Sri Lanka;Department of Civil and Environmental Engineering, Faculty of Engineering, University of Ruhuna, Hapugala 80042, Sri Lanka;Department of Civil and Environmental Engineering, The Faculty of Engineering, The University of West Indies, St. Augustine 32080, Trinidad and Tobago;Department of Computer Engineering, Faculty of Engineering, University of Peradeniya, Pereadeniya 20400, Sri Lanka;Department of Technology, Kothalawala Defense University, Rathmalana 10390, Sri Lanka;School of Civil Engineering, Universiti Sains Malaysia, Nibong Tebal 14300, Penang, Malaysia;

关键词: explainable machine learning;    pressure coefficient;    shapley additive explanation;    tree-based machine learning;    gable-roofed low-rise building;   

DOI  :  10.3390/buildings12060734

来源: DOAJ

【 摘 要 】

Conventional methods of estimating pressure coefficients of buildings retain time and cost constraints. Recently, machine learning (ML) has been successfully established to predict wind pressure coefficients. However, regardless of the accuracy, ML models are incompetent in providing end-users’ confidence as a result of the black-box nature of predictions. In this study, we employed tree-based regression models (Decision Tree, XGBoost, Extra-tree, LightGBM) to predict surface-averaged mean pressure coefficient (C_p,mean), fluctuation pressure coefficient (C_p,rms), and peak pressure coefficient (C_p,peak) of low-rise gable-roofed buildings. The accuracy of models was verified using Tokyo Polytechnic University (TPU) wind tunnel data. Subsequently, we used Shapley Additive Explanations (SHAP) to explain the black-box nature of the ML predictions. The comparison revealed that tree-based models are efficient and accurate in wind-predicting pressure coefficients. Interestingly, SHAP provided human-comprehensible explanations for the interaction of variables, the importance of features towards the outcome, and the underlying reasoning behind the predictions. Moreover, SHAP confirmed that tree-based predictions adhere to the flow physics of wind engineering, advancing the fidelity of ML-based predictions.

【 授权许可】

Unknown