Downscaling urban thermal signals with machine learning: A case study of Danish functional urban areas

Abstract

As climate change prospects point towards the pressing need for local-scale adaptation measures, it becomes of utmost importance to recognise intra-urban hotspots of excessive heat exposure. Accordingly, there is a pressing societal need to downscale the available near-surface air temperature predictions (reanalysis, forecasts, or projections) from the regional (kilometric) to a local (sub-kilometric) resolution, to facilitate the identification of short-term critical areas within metropolitan regions of cities, where acclimatisation and public health preventive measures actions should be prioritised. This work presents a Machine Learning (ML)-based methodology for upsampling near-surface air temperature from a 2.5 × 2.5Km to a 125 × 223 m (0.002 × 0.002°) grid, the Urban Thermal Signal Downscaling (UTS-D) model. The model was developed over four Danish Functional Urban Areas – Copenhagen, Aarhus, Aalborg and Odense - using crowdsourced data from citizen-own weather stations, along with geospatial predictors that are well-known determinants of the Urban Heat Island (UHI) effect. The best overall results were achieved with a Random Forest model with an overall Mean Absolute Error (MAE) of 0.76 K for the overall test subset, 0.66 K during heatwave and 0.85 K during coldwave subsets, denoting the model's good performance under extreme heat conditions. When evaluating against reference in-situ stations, the model's accuracy shows a slight decrease compared to the background numerical weather predictor model, suggesting that, by training solely on crowdsourced stations (clustered in urban areas), there is a tendency towards overestimating rural air temperatures. Nevertheless, regarding the spatial pattern, the model captures the thermal signature of the underlying urban infrastructure, allowing to disclose neighbourhood-level details.