On the Deep Learning Approach for Improving the Representation of Urban Climate: The Paris Urban Heat Island and Temperature Extremes

Abstract

As cities encompass most of the global population, it is crucial to understand the effects of climate change in an urban context to develop tailored adaptation and mitigation strategies. Physically-based models, computationally demanding, present scale limitations that hinder the representation of cities and their effects on the climate and vice-versa. Therefore, alternative methodologies are sought. Deep Learning (DL) is a growing technology that has become a universal presence in society and the scientific community, geosciences included, showing promising results. In this study, we applied DL models (Convolutional Neural Networks) to simulate land surface temperature (LST) and 2-meter maximum and minimum temperatures (T2max and T2min, respectively) over Paris between 2004 and 2022, and compared the results with ERA5, the most recent ECMWF atmospheric reanalysis. Several experiments featuring different sets of ERA5 predictors were used as input data to the DL models. Afterwards, the quality of the DL models in simulating the urban heat island (UHI) over Paris was assessed. Our results showed substantial improvements in LST, T2m and UHI simulation with DL (using a small number of predictors) in comparison to ERA5. This study supports the potential of DL to help improve the simulation of temperature extremes in an urban context.

Keywords: Urban heat island, Land surface temperature, 2-meter Temperature, Deep learning, Convolutional Neural Network