Added Value for Urban Heat Island Quantification from Machine Learning Downscaling of Air Temperatures
Authors:
- Hjalte Jomo Danielsen SørupHSHjalte Jomo Danielsen Sørup
- Maria CastroMCMaria Castro
- Kasper Stener HintzKHKasper Stener Hintz
- Rune Magnus Koktvedgaard ZeitzenRZRune Magnus Koktvedgaard Zeitzen
- Peter ThejllPTPeter Thejll
- Quentin PalettaQPQuentin Paletta
- Mark R. PayneMPMark R. Payne
- Inês GirãoIGInês Girão
- Ana OliveiraAOAna Oliveira
Open Access
- 20 March 2026
- journal article
- research article
- Published by MDPI AG in Urban Science
- Vol. 10 (3) , 171
Abstract
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.Keywords
Funding Information
- European Space Agency (4000143628/24/I-DT)
This publication has 32 references indexed in Scilit:
- Impact of seasonality and land use changes on urban heat island using earth-observing satellites2024
- Advances in remote sensing in measuring urban heat island effect and its management2024
- Artificial intelligence for sustainable urban climate studies2024
- Earth observation applications for urban mapping and monitoring: research prospects, opportunities and challenges2024
- Deep learning approach for monitoring urban land cover changes2024
- Influence of the proportion, height and proximity of vegetation and buildings on urban land surface temperatureInternational Journal of Applied Earth Observation and Geoinformation, 2021
- Investigating urban heat island through spatial analysis of New York City streetscapesJournal of Cleaner Production, 2019
- Heat Health Risks2017
- Simulations of the London urban heat islandQuarterly Journal of the Royal Meteorological Society, 2011
- The energetic basis of the urban heat islandQuarterly Journal of the Royal Meteorological Society, 1982