Research on Light Comfort of Waiting Hall of High-Speed Railway Station in Cold Region Based on Interpretable Machine Learning

Upon the need for sustainability and natural lighting performance simulation for high-speed railway station waiting halls in cold regions, a new prediction method was proposed for the quantitative analysis of their natural lighting performance in the early design stage. Taking the waiting hall of Harbin West Railway Station as the prototype, the authors explore the optimization design of green performance-oriented waiting halls in this paper. To maximize daylight and minimize visual discomfort, and with the help of Rhinoceros and Grasshopper and Ladybug, and Honeybee platform simulation programs, spatial elements such as building orientation, shape and windowing were simulated through optimizing target sDA, UDI and DGPexceed, respectively, based on natural lighting performance. Additionally, a dataset covering several light environment influencing factors was constructed by parametric simulations to develop a gradient boosted regression tree (GBRT) model. The results showed that the model was valid; that is, the coefficient of determination between the predicted value and the target one exceeds 0.980 without overfitting, indicating that the interpretability analysis based on the GBRT prediction model can be used to fully explore the contribution of related design parameters of the waiting hall to the indoor light environment indexes, and to facilitate more efficient lighting design in the early design stage without detailed analysis. In addition, the GBRT prediction model can be used to replace the traditional one as the effective basis for decision support. To conclude, the skylight ratio played a significant role in UDI, while the section aspect ratio (SAR) and plan aspect ratio (PAR) served as the key design parameters for sDA and DGPexceed, respectively. At the same time, the building orientation had the least degree of influence on the natural lighting of the waiting hall.

Cette oeuvre a été publiée sous la license Creative Commons Attribution 4.0 (CC-BY 4.0). Il est autorisé de partager et adapter l'oeuvre tant que l'auteur est crédité et la license est indiquée (avec le lien ci-dessus). Vous devez aussi indiquer si des changements on été fait vis-à-vis de l'original.