As climate change intensifies, it is an important task in reducing heat disasters to derive which areas are most vulnerable by exploring factors that affect thermal environment. Anthropogenic heat release factors have contributed to local temperature increases in cities. However, existing studies have mainly focused on the static sector of anthropogenic heat release factors. Therefore, this study addresses the effects of urban spatial temperatures considering anthropogenic heat release factors, with a focus on the mobility sector. An average summer temperature (avS) estimating model was developed with deep neural network (DNN) and random forest (RF) in detailed spatial units within a city (1 km spatial resolution) using eight mobility sector and four static sector indicators as input variables. The feasibility of introducing mobility indicators was verified by performing a correlation analysis between temperature and traffic flows. Mobility exhibited a higher correlation with the climate sector than with static road indicators. The RF model with mobility indicators effectively estimated spatial distribution of air temperatures, with an RMSE of 0.0777 and R2 of 0.9121, and outperformed the DNN model. This study provides a reference for heatwave risk management and the control of various urban anthropogenic heat release factors, including the mobility sector.