The urban heat island effect is well recognized and has been quantified using ground observations within and outside urban areas. Earth Observation has further revealed small-scale local spatial differences, especially in urban surface temperatures, that have been shown to be highly correlated with differences in the urban fabric. However, surface temperatures do not directly translate to human-experienced temperatures, and hence high-resolution air temperature data is of high relevance. However, air temperature is not easily measured from space, and seldom do ground measurements allow for small-scale differences to be quantified to a satisfactory degree. In the present study, we assessed the added value of an air temperature product downscaled using machine learning compared to the high-resolution reanalysis model that formed its foundation. The downscaled product was developed using satellite data, local observations from privately owned weather stations, and high-resolution reanalysis. The comparison focused on Denmark’s four largest urban areas and examined the two data product’s ability to describe the urban heat island effect at the city scale as well as intra-city differences in air temperatures. Both data products show similar urban heat island effects at the city scale, while the downscaled product shows greater intra-city variance in air temperature, with patterns that are somewhat correlated with both urban density and urban green spaces. Generally, the downscaling product offers city planners a better data basis for evaluating where to prioritize contingency and mitigation measures within the urban space.

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) scale, 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 2.5x2.5Km to a 125×223m (0.002x0.002°) 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 0.76K for the overall test subset, 0.66K during HW and 0.85K during CW 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.

Intra-urban air temperature is highly heterogeneous, and coarse-resolution products cannot resolve the neighbourhood-scale variability that urban heat management requires. The objective of this study is to assess whether the Urban Thermal Signal Downscaling (UTS-D) methodology, previously developed and tested over Danish Functional Urban Areas (FUAs) with the DAnish ReAnalysis (DANRA), can be re-implemented with a pan-European reanalysis and retrained in cities with contrasting climates, and to quantify the incremental value of a vegetation-seasonality predictor. The approach is applied to four European FUAs spanning contrasting climate zones, i.e., Copenhagen (Denmark), Lisbon (Portugal), Seville (Spain) and Athens (Greece). Two modifications were introduced: the regional weather component was replaced with the pan-European Copernicus Regional Reanalysis (CERRA), enabling application beyond Denmark, and a monthly climatological Normalized Difference Vegetation Index (NDVI) was added as a non-fixed predictor to capture the seasonality of vegetation cooling. A Random Forest model was trained to predict the residual bias between CERRA 2 m air temperature and quality-controlled observations from citizen-owned weather stations, combined with static landscape and urban predictors. Using a 2019–2022 training/cross-validation strategy and an independent 2023 test year, the downscaled model substantially outperformed raw CERRA in all four cities, reducing the test-year mean absolute error from 1.02–1.99 °C to 0.69–1.06 °C (a 32–55% reduction) and reaching R² of 0.94–0.98. Absolute error reductions were particularly relevant on hot days (HD) (0.52–1.21 °C); however, such periods are also the ones during which CERRA errors tend to be largest, indicating that the hot-day added value mainly reflects the correction of a larger reanalysis bias. NDVI provided only a marginal additional improvement (≤0.02 °C; ≤2%), statistically significant but negligible in practical terms. Errors were lowest in Copenhagen, which has the densest citizen-station network, and highest in Seville, which has the sparsest; however, a network-thinning experiment showed that station density explains only part of these differences, pointing to the combined role of station density, the magnitude of the reanalysis error, climate and urban morphology. These results show that UTS-D is methodologically transferable, i.e., it can be retrained successfully with CERRA wherever sufficiently dense citizen-station observations exist, and provide a basis for future heat-health and urban adaptation applications.