Spatial-Temporal Evolution and Cooling Effect of Irrigated Cropland in Inner Mongolia Region

Monitoring the dynamic distribution of irrigated cropland and assessing its cooling effects are essential for advancing sustainable agriculture amid climate change. This study presents an integrated framework for irrigated cropland monitoring and cooling effect assessment. Leveraging dense time series vegetation indices with Google Earth Engine (GEE), we evaluated multiple machine learning algorithms within to identify the most robust approach (random forest algorithm) for mapping irrigated cropland in Inner Mongolia from 2010 to 2020. Furthermore, we developed an effective method to quantify the diurnal, seasonal, and interannual cooling effects of irrigation. Our generated irrigated cropland maps demonstrate high accuracy, with overall accuracy ranging from 0.85 to 0.89. This framework effectively captures regional cropland expansion patterns, revealing a substantial increase in irrigated cropland across Inner Mongolia by 27,466.09 km2 (about +64%) between 2010 and 2020, with particularly pronounced growth occurring after 2014. Analysis reveals that irrigated cropland lowered average daily land surface temperature (LST) by 0.25 °C compared to rain-fed cropland, with the strongest cooling effect observed between July and August by approximately 0.64 °C, closely associated with increased evapotranspiration. Our work highlights the potential of satellite-based irrigation monitoring and climate impact analysis, offering a valuable tool for supporting climate-resilient agriculture practices.