Artificial intelligence-enabled assessment of urban growth impacts on land surface temperature in a hot desert climate: a case study of Baghdad city

Rasul, Azad

2025-03-22 null null   null(卷), null(期), (null页)

查看原文

The rapid growth of urban areas can have a significant impact on the local climate, leading to higher temperatures and other changes. In hot desert climate areas, such as Baghdad, the effects of urbanization on temperature changes have been largely overlooked. This study investigated the impact of urban expansion on land surface temperature (LST) in Baghdad, Iraq. Notably, this study employs an artificial intelligence method known as random forest for land-use/land-cover (LULC) classification, utilizing three Landsat images spanning the temporal spectrum from 1985 to 2021 to monitor land use transformations and associated LST variations. The results showed that vegetated areas declined by 46.8% during the study period, while built-up areas increased by 124.7%. This decline in vegetation was accompanied by an increase in LST, with bare soil recording the highest temperatures ranging from 331.3 to 322.7 K. The study also discovered a strong inverse relationship between LST and vegetation, as well as between LST and moisture. These findings suggest that urban expansion can lead to higher LSTs in desert climates, which may affect the health and well-being of residents. The study identifies key factors controlling LST, offering insights into strategies to mitigate the temperature effects of urban expansion.