Transfer learning reveals large discrepancies between air and land surface temperatures in cities
Yiwen Zhang, Lei Zhao, TC Chakraborty, Priyam Mazumdar, Keer Zhang, Pierre Gentine · 2026
Read Transfer learning reveals large discrepancies between air and land surface temperatures in cities by Yiwen Zhang, Lei Zhao, TC Chakraborty, Priyam Mazumdar, Keer Zhang, Pierre Gentine (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13389406.txt.
Description
Yiwen Zhang's team built a transfer-learning system that estimates true urban air heat at high detail across the contiguous United States, replacing satellite surface heat as a stand-in. Cities lack dense weather stations, so surface heat has been widely substituted for air heat despite fundamental differences.
Their urban transfer-learning system model air heat accurately even with limited training data and reproduced established urban climate patterns. Satellite surface readings substantially overstated both heat-stress magnitude and within-city variation, warning planners that exposure and vulnerability maps built on surface heat may mislead adaptation policy.
Catalog record
| CREATOR | Yiwen Zhang, Lei Zhao, TC Chakraborty, Priyam Mazumdar, Keer Zhang, Pierre Gentine |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 73 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |