Climate change is expected to increase the frequency and duration of hot weather and its associated adverse health effects. In dense urban areas, these phenomena will be exacerbated by the Urban Heat Island (UHI) effect and indoor overheating.

The Urban Heat Island effect shows the differences among temperatures in urban areas and the surrounding rural ones. Previous studies have demonstrated that temperature differences could be up to 8 °C during the hottest periods of summer in Madrid , and that it varies according to the urban structure. Associated to this effect, the impact of temperature increase over dwelling indoor thermal comfort seems to double cooling energy demand . In Madrid, fuel poor households already suffering from inadequate indoor temperatures can face important overheating problems and, as a consequence, relevant health problems could become more frequent and stronger. This poses an increment in mortality rates in risk groups that should be evaluated. This research is aimed at establishing the geospatial connection between the urban heat island and the most vulnerable population living in the city of Madrid. Hence, those areas most in need for an urban intervention can be detected and prioritized.

Despite great advances on building energy evaluation, available climate data does not include the effects of the Urban Heat Island (UHI). This phenomenon, which increases the temperature in urban areas, is variable in both time and space, and implies an important lack of accuracy when simulating within an urban context. During this research the relevance of the UHI in relation to the dwellings energy performance has been confirmed, as well as the existing barriers to integrate the current UHI representations into the dynamic energy simulation process. Therefore, it is necessary to carry out an update of the existing models, in order to implement it into the energy evaluation process. In this work, as a first stage of the study and based on current techniques of geolocation and the use of Geographic Information Systems (GIS), it is established a methodology to acquire automatically an update of the UHI through isotherm maps. It is aimed to set up the starting point from which the integration of the UHI into the energy simulation process will happen.

In the last decades, urban climate researchers have highlighted the need for a reliable provision of meteorological data in the local urban context. Several efforts have been made in this direction using Artificial Neural Networks (ANN), demonstrating that they are an accurate alternative to numerical approaches when modelling large time series. However, existing approaches are varied, and it is unclear how much data are needed to train them. This study explores whether the need for training data can be reduced without overly compromising model accuracy, and if model reliability can be increased by selecting the UHI intensity as the main model output instead of air temperature. These two approaches were compared using a common ANN configuration and under different data availability scenarios. Results show that reducing the training dataset from 12 to 9 or even 6 months would still produce reliable results, particularly if the UHI intensity is used. The latter proved to be more effective than the temperature approach under most training scenarios, with an average RMSE improvement of 16.4% when using only 3 months of data. These findings have important implications for urban climate research as they can potentially reduce the duration and cost of field measurement campaigns.