Investigation of influential variations among variables in daylighting glare metrics using machine learning and SHAP

Abstract

Previous studies have shown the inconsistent performance of various daylighting glare prediction metrics in office daylit-dominated environments. This lack of consensus may stem from a limited understanding of how their component variables contribute to the prediction power reflected on these discomfort glare models. Previous studies predominantly focused on individual variables' linear, independent impact on glare discomfort prediction, neglecting to explore their non-linear and interaction contributions. This study addressed these limitations by evaluating regularly used glare variables using machine learning-based feature selection and SHAP interpretation methods to parse the collected dataset in a subjective survey. By applying different machine learning algorithms and SHAP explainers, we have identified their contribution importance to the prediction of different scales of glare discomfort rating when incorporated into one model and have observed the difference of interaction effects between these variables on predicting glare discomfort ratings. Our findings indicate that vertical eye illuminance, maximal luminance, and window mean luminance exhibit strong prediction power and significant interaction effects on glare discomfort sensations, indicating that they could be the dominant contributors to glare predictive metrics. Contrast effect variables within the field of view had less predictive influence on glare scales when combined with other variables. This innovative approach enables a comprehensive assessment of different variables' influential sequence and interaction consequences when incorporated into the glare prediction model. It facilitates the development of the new glare discomfort prediction model.