The urban form and extreme microclimate events can have an important impact on the energy performance of buildings, urban comfort and human health. State-of-the-art building energy simulations require information on the urban microclimate, but typically rely on ad-hoc numerical simulations, expensive in-situ measurements, or data from nearby weather stations. As such, they do not account for the full range of possible urban microclimate variability and findings cannot be generalized across urban morphologies. To bridge this knowledge gap, this study proposes two data-driven models to downscale climate variables from the meso to the micro scale in arbitrary urban morphologies, with a focus on extreme climate conditions. The models are based on a feedforward and a deep neural network (NN) architecture, and are trained using results from computational fluid dynamics (CFD) simulations of flow over a series of idealized but representative urban environments, spanning a realistic range of urban morphologies. Both models feature a relatively good agreement with corresponding CFD training data, with a coefficient of determination R² = 0.91 (R² = 0.89) and R² = 0.94 (R² = 0.92) for spatially-distributed wind magnitude and air temperature for the deep NN (feedforward NN). The models generalize well for unseen urban morphologies and mesoscale input data that are within the training bounds in the parameter space, with a R² = 0.74 (R² = 0.69) and R² = 0.81 (R² = 0.74) for wind magnitude and air temperature for the deep NN (feedforward NN). The accuracy and efficiency of the proposed CFD-NN models makes them well suited for the design of climate-resilient buildings at the early design stage.

Building more energy-efficient and sustainable urban areas that will both mitigate the effects of climate change and anticipate living conditions in future climate scenarios requires the development of new tools and methods that can help urban planners, architects and communities achieve this goal. In the current study, we designed a workflow that links different methodologies developed separately, to derive the energy consumption of a university school campus for the future. Three different scenarios for typical future years (2039, 2069, 2099) were run, as well as a renovation scenario (Minergie-P). We analyzed the impact of climate change on the heating and cooling demand of buildings and determined the relevance of taking into account the local climate in this particular context. The results from the simulations confirmed that in the future, there will be a constant decrease in the heating demand, while the cooling demand will substantially increase. Significantly, it was further demonstrated that when the local urban climate was taken into account, there was an even higher rise in the cooling demand, but also that a set of proposed Minergie-P renovations were not sufficient to achieve resilient buildings. We discuss the implication of this work for the simulation of building energy consumption at the neighborhood scale and the impact of future local climate on energy system design. We finally give a few perspectives regarding improved urban design and possible pathways for future urban areas.