Combining computational fluid dynamics and neural networks to characterize microclimate extremes: Learning the complex interactions between meso-climate and urban morphology
Artikel i vetenskaplig tidskrift, 2022

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.

Urban morphology

Extreme microclimate conditions

Wind speed

Air temperature

CFD simulations

Neural networks

Författare

Kavan Javanroodi

Ecole Polytechnique Federale de Lausanne (EPFL)

Vahid Nik

Chalmers, Arkitektur och samhällsbyggnadsteknik, Byggnadsteknologi

Lunds universitet

Marco G. Giometto

Columbia University

J. L. Scartezzini

Ecole Polytechnique Federale de Lausanne (EPFL)

Science of the Total Environment

0048-9697 (ISSN)

Vol. 829 154223

Ämneskategorier

Annan data- och informationsvetenskap

Annan samhällsbyggnadsteknik

Husbyggnad

DOI

10.1016/j.scitotenv.2022.154223

PubMed

35245539

Mer information

Senast uppdaterat

2022-03-31