Modelling site-specific outdoor temperature for buildings in urban environments

Building performance simulations often rely on standardised meteorological datasets, which may not accurately reflect urban microclimates. This study highlights the complexity of temperature dynamics near buildings influenced by multiple factors. A static correction factor is unfeasible for adjusting meteorological data from suburban stations to city centres. To address this, air temperature variability in different urban locations was analysed using data from a city-centre weather station, 32 facade-mounted sensors and thermographic imaging. The selected locations for analysis are representative of approximately 25% of the housing stock in Wrocław, Poland. This was compared with standard meteorological data from Wrocław II, located at an airport. These analyses formed the basis for developing a predictive machine-learning model to account for thermal variability based on building type, location, facade orientation and facade materials. Focusing on the summer period to assess nocturnal cooling potential, the model achieved high accuracy, with R2 > 0.93 in training and 0.92 in validation. These findings underscore the need for microclimate-informed meteorological adjustments in building simulations. Practice relevance Implementing corrections to outdoor temperature in urban environments can significantly enhance the accuracy of energy modelling, particularly for natural ventilation strategies addressing urban overheating. However, due to the complexity of temperature dynamics near buildings, defining a single static correction factor for climate parameters such as temperature is unlikely to be effective. Analysis indicates that even multiple regression approaches result in correction factors that are difficult to apply in practice. Adjustments must be determined separately for facade orientation, building height, external wall structure and urban location. The proposed method enables the generation of dynamic, high-spatial-resolution temperature data, incorporating facade orientation and specific building floor heights. These refined datasets can be used to adjust meteorological station measurements, improving the accuracy of simulations. When applied to a typical meteorological year dataset, this approach may offer a way to better represent thermal variability in urban environments, supporting more context-sensitive building-energy modelling.