Original data of the manuscript

Source
DataCite
Published
2026
License
Creative Commons Attribution 4.0 International
Themes
Cycling & Walkability, Sustainable Cities, Climate & Temperature

Get the data from DataCite

About this dataset

Understanding how urban morphological controls on land surface temperature (LST) vary across seasons remains challenging, particularly in high-altitude cities where strong solar radiation and complex topography may alter relationships between urban morphology and LST. Using Lhasa, a typical city on the Qinghai–Tibet Plateau, as a case study, this study investigates seasonal relationships between street-scale urban morphology and LST using a geographically weighted XGBoost (GW-XGBoost) model combined with SHAP interpretation techniques. Seasonal LST datasets were derived from multi-temporal Landsat imagery, and a series of street geometry, building morphology, green-space, and topographic indicators were constructed to characterize urban spatial form. The results reveal pronounced seasonal shifts in the dominant controls of LST. During summer, green space aggregation (AI green ) was...

How the data was collected

Seasonal LST datasets were derived from multi-temporal Landsat imagery, and a series of street geometry, building morphology, green-space, and topographic indicators were constructed to characterize urban spatial form.

Browse sustainability datasets on SusanHub