Influences of the thermal environment on pedestrians’ thermal perception and travel behavior in hot weather

Walkable cities are critically important for promoting the well-being of urban residents and reducing air pollution and greenhouse gas (GHG) emissions. The walkability of a city is affected by its thermal environment. To gain a better understanding on how the urban thermal environment affects walkability, this study investigated the relationships between outdoor thermal conditions, thermal perceptions of pedestrians, and their walking speeds. A total of 337 pedestrians were monitored and interviewed at four carefully chosen sites with contrasting urban morphologies in Hong Kong, along with the simultaneous collection of site-specific climatic data. Based on the data, relationships between thermal conditions, thermal perceptions, and walking speeds were analyzed exploratively and quantitatively. The results show that pedestrians’ average thermal sensation and thermal comfort are well-characterized by linear models using universal thermal indices as independent variables. Additionally, pedestrian walking speeds can be modeled by a polynomial regression model (R2 = 0.719), artificial neural network (ANN) models (highest R2 = 0.762 in the test dataset and R2 = 0.907 in the whole dataset) and a deep neural network (DNN) model (R2 = 0.791 in the test dataset and R2 = 0.931 in the whole dataset). These findings can assist in urban planning and improve city walkability.