A Machine Learning Approach for the Efficient Estimation of Ground-Level Air Temperature in Urban Areas

TL;DR

This work explores the usefulness of image-to-image deep neural networks for correlating spatial and meteorological variables of a urban area with street-level air temperature and confirms deep neural networks are confirmed to be faster and less computationally expensive alternative for ground-level air temperature compared to numerical models.

Abstract

The increasingly populated cities of the 21st Century face the challenge of being sustainable and resilient spaces for their inhabitants. However, climate change, among other problems, makes these objectives difficult to achieve. The Urban Heat Island (UHI) phenomenon that occurs in cities, increasing their thermal stress, is one of the stumbling blocks to achieve a more sustainable city. The ability to estimate temperatures with a high degree of accuracy allows for the identification of the highest priority areas in cities where urban improvements need to be made to reduce thermal discomfort. In this work we explore the usefulness of image-to-image deep neural networks (DNNs) for correlating spatial and meteorological variables of a urban area with street-level air temperature. The air temperature at street-level is estimated both spatially and temporally for a specific use case, and compared with existing, well-established numerical models. Based on the obtained results, deep neural networks are confirmed to be faster and less computationally expensive alternative for ground-level air temperature compared to numerical models.

Figures (8)

• Figure 1: The study area divided in patches. The patches shadowed in yellow correspond to the validation ones while the purple ones to the test patches. The meteorological stations are located in the red dots.
• Figure 2: The U-Net architecture proposed for the estimation of Ta. The sum in the latent space corresponds to a concatenation of two flattened vectors.
• Figure 3: Aggregated spatial distribution U-Net at 05:00 (top) and 14:00 (bottom).
• Figure 4: Hourly aggregated Ta for all the 164 days for the UrbClim model (top) and U-Net model (bottom). In the figure the left image shows the 5:00 aggregation and the right image the 14:00 aggregation.
• Figure 5: Time series of Ta for different LWT days, for all the test locations. The values measured by the meteorological stations are represented by the black line. The Ta values obtained by the UrbClim model are in red, whereas the ones estimated by U-Net model in green.