Examining Land Use and Land Cover Changes and their Impacts on the Land Surface Temperatures in Southwestern Bangladesh: A Remote Sensing and Machine Learning Approach

期刊论文
发表日期：

2026年3月3日

查看全文

Md Zidanur Rahman Zidan,
Sujit Kumar Roy,
Muhammad Tahidur Rahman,
Md.Shafayat Ullah,
Snigdha Setu Paul Mouna,
Shahriar Md Arifur Rahman,
Mohammad Mohinuzzaman

摘要

The southwest Region of Bangladesh, primarily the Khulna Division, is a rapidly urbanizing area characterized by a diverse landscape. Recently, this area has undergone notable urban expansion, resulting in changes in land cover that affect Land Surface Temperature (LST) and increase the Urban Heat Island (UHI) effect. This study employs cloud-based geospatial analysis in Google Earth Engine (GEE) and machine-learning techniques to examine interactions between Land Use Land Cover (LULC) and LST. Multi-temporal Landsat 5 and Landsat 8 data were used to derive LST and spectral indices, complemented by MODIS LST products, Sentinel-2 land cover data, and ancillary climatic and topographic datasets (GPCP, MERRA-2, SRTM, and GUF). Spectral index analysis (NDVI, NDWI, NDBI), Pearson’s correlation analysis, and Random Forest modeling were applied to identify the drivers of LST variability from 2000 to 2022. The results reveal that urban areas expanded by almost 4.5-fold during the study period, whereas vegetation and water bodies decreased by 9.48% and 31.18%, respectively, and bare land increased by 4.91%. The mean LST for the entire division increased from 27.76 °C in 2000 to 31.71 °C in 2022, representing a total rise of 3.95 °C. Urban areas experienced a greater increase in temperature, with the mean LST rising by 5.92 °C. In contrast, non-urban areas (vegetation, water, and bare land) combinedly experienced a more moderate rise in LST of 3.05 °C. Urban areas exhibited 2.87 °C higher temperatures than non-urban areas, demonstrating that the conversion of vegetated and water-covered surfaces to built-up land directly intensified surface heating. For pixels that converted from non-urban to urban areas, temperature increased by 3.52 °C. Individually, LST increased by 2.73 °C in vegetation areas, 2.13 °C in water bodies, and 3.70 °C in bare land. The expansion of vegetation and water bodies during earlier periods significantly influenced LST in 2010 and 2020, indicating that increased vegetation cover and surface moisture cooled LST. A feature-importance analysis using a Random Forest indicates that LULC is the dominant predictor of LST, accounting for 16.83% of the regional variance. The results demonstrate that urban expansion, coupled with the loss of vegetation and wetlands, directly contributes to increased heat intensity in Khulna. These results underscore the importance of evidence-based urban planning strategies that prioritize the preservation of vegetation and water bodies, regulate the expansion of built-up areas, and incorporate heat-mitigation measures to enhance urban climate resilience.

Graphical Abstract

The graphical abstract illustrates the relationship between land use and land cover (LULC) change and land surface temperature (LST) dynamics in the Southwest Region of Bangladesh between 2000 and 2022. Over the 22 years, urban areas expanded by 1821 km², while vegetation and water bodies decreased by 959 km² and 1238 km², respectively, alongside a moderate increase in bare land (376 km²). This transformation led to a substantial rise in LST, with the overall regional temperature increasing by 3.95 °C. Urban areas exhibited the largest increase (5.92 °C), whereas non-urban areas showed a smaller increase (3.05 °C). Vegetation, water, and bare lands individually experienced temperature rises of 2.73 °C, 2.13 °C, and 3.70 °C, respectively, highlighting the disproportionate warming of built-up surfaces. The findings also reveal a pronounced Urban Heat Island (UHI) effect, with urban areas averaging 2.87 °C warmer than non-urban areas, and non-urban-to-urban land transitions contributing an additional 3.52 °C increase. Feature-importance analysis using the Random Forest model indicates that LULC is the dominant factor influencing LST, accounting for 16.83% of the observed changes. The model demonstrates strong predictive performance, with an R-squared of 0.81, a low RMSE of 0.95 °C, and a MEP of 3.38%, indicating only a small deviation between observed and predicted LST values. This visualization highlights how rapid urban expansion and the loss of natural land cover exacerbate thermal stress in the region. The study highlights the urgent need for sustainable urban planning and for conserving vegetation and water bodies to mitigate the intensification of LST and UHI.