Mapping and predicting urban heat island intensity hotspots through a space–time machine learning framework in Bangladesh

Abstract Urban Heat Island Intensity (UHII) has become a pressing urban climate issue in rapidly developing nations such as Bangladesh. This study presents a nationwide thana-level assessment of UHII trends from 1990 to 2023 using remote sensing, geospatial analysis, and machine learning techniques. Land Surface Temperature (LST) was derived from Landsat imagery to quantify UHII, and a Space–Time Cube framework with Mann–Kendall trend analysis was applied to identify persistent, intensifying, emerging, and diminishing hotspot patterns. Major urban centers, including Dhaka, Narayanganj, and Khulna, exhibited increasing UHII, while Barisal and Mymensingh showed emerging cold spots. A Random Forest model was developed to forecast UHII up to 2040, revealing further intensification in densely populated and industrial zones. The results indicate that major metropolitan areas, particularly Dhaka, Narayanganj, and Khulna, exhibit persistent and intensifying heat hotspots, whereas divisions like Barisal and Mymensingh show emerging cold spots. The findings emphasize the need for climate-responsive urban planning and green infrastructure. This study establishes a baseline for long-term UHII monitoring and serves as a framework for future research aimed at developing predictive models and targeted mitigation strategies to enhance urban climate resilience.