The urban heat island (UHI) is exacerbated during heat waves, which have been reported to be more frequent in recent years. Unwanted consequences of the UHI not only include an increase in mean/peak energy demand, but an escalation in the heat-related mortality and disease. Although UHI mitigation strategies are being implemented by cities, they serve as mid to longterm solutions. The implementation of short-term mitigation strategies is paramount for cities to reduce the immediate risks of the heat-related hazards. Various prognostic tools have been developed to empower urban planners and decision makers in minimizing the related risks. These tools are mainly based on stationary parameters, such as the average surface temperature of a city, and are independent of land-use/land-cover (LULC). Furthermore, the outdoor temperatures are utilized to develop such models. However, heat-related risks occur mostly in indoor spaces, and correlations between indoor and outdoor spaces are rarely considered.In this study, a predictive model for the indoor air temperature of buildings is developed using the artificial neural network (ANN) concept. A four-month measurement campaign was conducted to obtain indoor temperatures of more than 50 buildings located on the island of Montreal. The area is then separated into 11 regions, each containing at least one of the measured buildings. The ANN model is then trained to be sensitive to the neighborhood's characteristics and LULC of each region. The surrounding radial area that influences the building's indoor temperature is first defined within an effective radius, by analyzing areas with radii ranging from 20m to 500m in 20m increments. Hence, the effective radius is found for each region to be within a radial area, where the environment beyond its limit does not significantly impact the building indoor air temperature. This technique trains a single model for the city, encompassing the unique characteristics of the sub-regions that contain buildings under study. An effective radius was established to lie within 320m to 380m. Analysing surrounding radial areas within this range enabled the network to effectively forecast future indoor conditions resulting from UHI effects, producing hourly indoor temperature predictions with an MSE of 0.68. Furthermore, the ability of the developed tool in the city planning is investigated with an additional case study.