Work

Transfer learning reveals large discrepancies between air and land surface temperatures in cities

Year: 2026

Type: article

Abstract: Understanding of urban weather and climate is severely limited by data poverty resulting from a dearth of true urban weather stations 1,2 . As a result, land surface temperature ( T s ), obtained from remote sensing platforms, has been widely used as a stand-in for near-surface air temperature ( T a ) 3–7 despite their fundamental differences 8 , especially in urban areas. This has led to erroneous characterization of urban heat stress and urban climate impacts 9 . Here we develop a novel urban transfer learning framework (U-TL) to address this critical gap and to provide urban high-resolution air temperature (U-HAT) data at large scales across the contiguous United States (CONUS). U-TL demonstrates high accuracy and strong robustness in predicting urban T a , even with limited training data. The resulting U-HAT is the first high-resolution urban T a dataset capable of accurately reproducing observed and well-established urban climatology. U-HAT reveals substantial T s –T a discrepancies and therefore cautions the use of T s to characterize urban heat. We show that satellite-measured T s substantially overestimates both urban heat stress magnitude and intra-city disparities, which have very consequential implications for urban heat exposure, vulnerability, and adaptation policy making.

Source: Nature Communications

DOI: 10.1038/s41467-026-73716-7

Authors: Yiwen Zhang, Lei Zhao, TC Chakraborty, Priyam Mazumdar, Keer Zhang, Pierre Gentine