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.

Keywords

Urban heat island intensity / Land surface temperature / Remote sensing / Machine learning / Space time cube / Emerging hotspot analysis

References

[1] Abdullah S, Barua D, Abdullah SMA, Rabby YW. Investigating the impact of land use/land cover change on present and future land surface temperature (LST) of Chittagong, Bangladesh. Earth Systems and Environment. 2022, 6(1): 221-235.

[2] Ahmed B, Kamruzzaman M, Zhu X, Rahman MS, Choi K. Simulating land cover changes and their impacts on land surface temperature in Dhaka, Bangladesh. Remote Sensing. 2013, 5(12): 5969-5998.

[3] Akter T, Gazi MdY, Mia MdB. Assessment of land cover dynamics, land surface temperature, and heat island growth in Northwestern Bangladesh using satellite imagery. Environmental Processes. 2021, 8(2): 661-690.

[4] Ali AAB, Mitra C, Rahaman SKN. Mapping the heat with spatial trends and emerging temperature hotspots in the contiguous U.S. (CONUS) counties from 2000 to 2022. Spatial Information Research. 2025, 33(1): 35.

[5] Avand M, Moradi H. Using machine learning models, remote sensing, and GIS to investigate the effects of changing climates and land uses on flood probability. Journal of Hydrology. 2021, 595: 125663.

[6] Avdan U, Jovanovska G. Algorithm for automated mapping of land surface temperature using LANDSAT 8 satellite data. Journal of Sensors. 2016, 20161-8.

[7] Brammer H. The physical geography of Bangladesh. 2012University Press Limited

[8] Chakraborty T, Hsu A, Manya D, Sheriff G. Disproportionately higher exposure to urban heat in lower-income neighborhoods: A multi-city perspective. Environmental Research Letters. 2019, 14: 1-10.

[9] Chen YC, Chiu HW, Su YF, Wu YC, Cheng KS. Does urbanization increase diurnal land surface temperature variation? Evidence and implications. Landscape and Urban Planning. 2017, 157: 247-258.

[10] Dewan A, Kiselev G, Botje D, Mahmud GI, Bhuian MH, Hassan QK. Surface urban heat island intensity in five major cities of Bangladesh: Patterns, drivers, and trends. Sustainable Cities and Society. 2021, 71: 102926.

[11] Drori Ret al. . Precipitation-sensitive dynamic threshold: A new approach for NDVI classification. Remote Sensing. 2020, 1281231.

[12] Eckstein, D., Künzel, V., Schäfer, L., & Winges, M. (2019). Global climate risk index 2020. Germanwatch.

[13] Esri. (2021). How hot spot analysis (Getis-Ord Gi*) works—Help/ArcGIS Desktop. Esri. https://pro.arcgis.com/en/pro-app/latest/tool-reference/spatial-statistics/h-how-hot-spot-analysis-getis-ord-gi-spatial-stati.htm

[14] Fatemi, M., & Narangifard, M. (2019). Monitoring LULC changes and its impact on the LST and NDVI in District 1 of Shiraz City. Arabian Journal of Geosciences,12(4), 127.

[15] Gadekar, K., Pande, C. B., Rajesh, J., Gorantiwar, S. D., & Atre, A. A. (2023). Estimation of land surface temperature and urban heat island by using Google Earth Engine and remote sensing data. In Climate change impacts on natural resources, ecosystems and agricultural systems (pp. 367–389). https://doi.org/10.1007/978-3-031-19059-9_14

[16] GED (General Economics Division). (2018). Bangladesh delta plan 2100, Volume 1: Strategy. Bangladesh Planning Commission, Government of Bangladesh: Dhaka.

[17] Getis A, Ord JK. The analysis of spatial association by use of distance statistics. Geographical Analysis. 1992, 243189-206.

[18] Girardet H. People and nature in an urban world. One Earth. 2020, 22135-137.

[19] Gohain KJ, Mohammad P, Goswami A. Assessing the impact of land use land cover changes on land surface temperature over Pune city, India. Quaternary International. 2021, 575: 259-269.

[20] Haque MS, Rahman MT, Ahmed N. Assessment of urban heat island effect using remote sensing: A case study of Dhaka City, Bangladesh. Environmental Challenges. 2019, 2: 100017

[21] Hashim, H. (2019). Urban vegetation mapping using very high-resolution imagery and NDVI thresholding. ISPRS Archives, XLII-4/W16, 237–244. https://doi.org/10.5194/isprs-archives-XLII-4-W16-237-2019

[22] Heaviside C, Macintyre H, Vardoulakis S. The urban heat island: Implications for health in a changing environment. Current Environmental Health Reports. 2017, 4296-305.

[23] Heisler, G. M., & Brazel, A. J. (2010). The urban physical environment: Temperature and urban heat islands. In Urban Ecosystem Ecology (Vol. 55, pp. 29–56). Howard, L. (1833). The climate of London: Deduced from meteorological observations (Vol. 1). Cambridge University Press.

[24] Hu XM, Xue M, Klein PM, Illston BG, Chen S. Analysis of urban effects in Oklahoma City using a dense surface observing network. Journal of Applied Meteorology and Climatology. 2016, 55(3): 723-741.

[25] Huang X, Huang J, Wen D, Li J. An updated MODIS global urban extent product (MGUP) from 2001 to 2018 based on an automated mapping approach. International Journal of Applied Earth Observation and Geoinformation. 2021, 95: 102255.

[26] Imran HM, Hossain A, Islam AS, Rahman A, Bhuiyan MAE, Paul S, Alam A. Impact of land cover changes on land surface temperature and human thermal comfort in Dhaka City of Bangladesh. Earth Systems and Environment. 2021, 5667-693.

[27] Jahan, I. (2024). Urban heat island (UHI) development and mitigation measures in three Bangladesh cities: Dhaka, Chattogram, and Sylhet (Doctoral dissertation, University of Delaware).

[28] Kafy, A. A. (2019). Estimation of urban heat islands effect and its impact on climate change: A remote sensing and GIS-based approach in Rajshahi District. Kafy, Abdulla-Al, Hasan, Mohammad, Faisal, Abdullah-Al, Nipun, Waresul Hassan, & Noman, Abdullah.

[29] Kafy, A. A., Islam, M., Sikdar, S., Ashrafi, T. J., Al-Faisal, A., Islam, M. A., & Ali, M. Y. (2021). Remote sensing-based approach to identify the influence of land use/land cover change on the urban thermal environment: A case study in Chattogram City, Bangladesh. In Re-envisioning remote sensing applications (pp. 217–240). CRC Press.

[30] Karakuş CB. The impact of land use/land cover (LULC) changes on land surface temperature in Sivas City Center and its surroundings and assessment of urban heat island. Asia-Pacific Journal of Atmospheric Sciences. 2019, 55(4): 669-684.

[31] Kaya S, Basar UG, Karaca M, Seker DZ. Assessment of urban heat islands using remotely sensed data. Ekoloji. 2012, 21(84): 107-113.

[32] Kendall MG, Gibbons JD. Rank correlation methods. 19905th edGriffin

[33] Kerr, Y. H., Lagouarde, J. P., Nerry, F., & Ottlé, C. (2004). Land surface temperature retrieval techniques and applications: Case of the AVHRR. In Thermal remote sensing in land surface processing (pp. 55–131).

[34] Khatun H, Sumiya NN, Ali AAB. Achieving sustainable development goals in Bangladesh: Does population density matter?. The Dhaka University Journal of Earth and Environmental Sciences. 2021, 8(2): 1-15.

[35] Kotharkar R, Ramesh A, Bagade A. Urban heat island studies in South Asia: A critical review. Urban Climate. 2018, 24: 1011-1026.

[36] Kusuma SS, Munir AKM, Nazri AKM. Determination of land surface temperature and urban heat island effect in Jakarta Metropolitan Area. Natural Hazards. 2023, 115: 1-17.

[37] Lai J, Zhan W, Huang F, Quan J, Hu L, Gao L, Ju W. Does quality control matter? Surface urban heat island intensity variations estimated by satellite-derived land surface temperature products. ISPRS Journal of Photogrammetry and Remote Sensing. 2018, 139: 212-227.

[38] Leal Filho W, Wolf F, Shula K, Maharaj PE. The role of urban heat islands in climate change adaptation and resilience: Strategies and policies. Climate Risk Management. 2021, 33: 100345

[39] Luo M, Lau N. Increasing heat stress in urban areas of Eastern China: Acceleration by urbanization. Geophysical Research Letters. 2018, 4513060-13069.

[40] Macarof P, Statescu F. Comparison of NDBI and NDVI as indicators of surface urban heat island effect in Landsat 8 imagery: A case study of Iasi. Present Environment and Sustainable Development. 2017, 11(2): 91-100.

[41] Malik, M. S., Shukla, J. P., & Mishra, S. (2019). Relationship of LST, NDBI and NDVI using Landsat-8 data inKandaihimmat Watershed, Hoshangabad, India. Indian Journal of Geo-Marine Sciences, 48(1), 25–31.

[42] Mann HB. Nonparametric tests against trend. Econometrica. 1945, 13(3): 245.

[43] Manoli G, Fatichi S, Schläpfer M, Yu K, Crowther TW, Meili N, Bou-Zeid E. Magnitude of urban heat islands largely explained by climate and population. Nature. 2019, 573777255-60.

[44] Mitchell D, Heaviside C, Schaller N, Allen M, Ebi KL. Attributing human mortality during extreme heat waves to anthropogenic climate change. Environmental Research Letters. 2016, 11(7): 074006.

[45] Mora C, Dousset B, Caldwell Iet al. . Global risk of deadly heat. Nature Climate Change. 2017, 7: 501-506.

[46] Mourshed M. The impact of the projected changes in temperature on heating and cooling requirements in buildings in Dhaka, Bangladesh. Applied Energy. 2011, 88113737-3746.

[47] Ord JK, Getis A. Local spatial autocorrelation statistics: Distributional issues and an application. Geographical Analysis. 1995, 27(4): 286-306.

[48] Pal S, Ziaul S. Detection of land use and land cover change and land surface temperature in English Bazar Urban Centre. Egyptian Journal of Remote Sensing and Space Sciences. 2017, 20(1): 125-145.

[49] Pande CB, Srivastava A, Moharir KN, Radwan N, Mohd Sidek L, Alshehri F, Zhran M. Characterizing land use/land cover change dynamics by an enhanced random forest machine learning model: A Google Earth Engine implementation. Environmental Sciences Europe. 2024, 36(1): 84.

[50] Peng S, Piao S, Ciais P, Friedlingstein P, Ottlé C. Surface urban heat island across 419 global big cities. Environmental Science & Technology. 2012, 462696-703.

[51] Pettorelli N, Vik JO, Mysterud A, Gaillard JM, Tucker CJ, Stenseth NC. Using the satellite-derived NDVI to assess ecological responses to environmental change. Trends in Ecology & Evolution. 2005, 20(9): 503-510.

[52] Rahaman SN, Nelson J, Ali AABet al. . A multivariate geostatistical framework to assess the spatio-temporal dynamics of air pollution and land surface temperature in Bangladesh. Earth Systems and Environment. 2025, 9: 71-91.

[53] Rahman MN, Rony MRH, Jannat FA, Chandra Pal S, Islam MS, Alam E, Islam ARMT. Impact of urbanization on urban heat island intensity in major districts of Bangladesh using remote sensing and geo-spatial tools. Climate. 2021, 10(1): 3.

[54] Santamouris M. Regulating the damaged thermostat of the cities—Status, impacts and mitigation challenges. Energy and Buildings. 2015, 91: 43-56.

[55] Santamouris M. Recent progress on urban overheating and heat island research: A review. Energy and Buildings. 2020, 207: 109482.

[56] Shahfahad, Talukdar, S., Rihan, Mohd., Hang, H. T., Bhaskaran, S., & Rahman, A. (2022). Modelling urban heat island (UHI) and thermal field variation and their relationship with land use indices over Delhi and Mumbai metro cities. Environment, Development and Sustainability, 24(3), 3762–3790. https://doi.org/10.1007/s10668-021-01587-7

[57] Tong S, Prior J, McGregor G, Shi X, Kinney P. Urban heat: An increasing threat to global health. BMJ (Clinical Research Ed.). 2022, 375n2467.

[58] Tzavali A, Paravantis JP, Mihalakakou G, Fotiadi A, Stigka E. Urban heat island intensity: A literature review. Fresenius Environmental Bulletin. 2015, 244537-4554

[59] Uddin AS, Khan N, Islam ARMT, Kamruzzaman M, Shahid S. Changes in urbanization and urban heat island effect in Dhaka City. Theoretical and Applied Climatology. 2022, 1473891-907.

[60] United Nations Office for Disaster Risk Reduction. (n.d.). Home. UNDRR. Retrieved July 5, 2025, from https://www.undrr.org/

[61] United Nations. (2019). World population prospects - Population Division. United Nations. Retrieved January 15, 2025, from https://population.un.org/wpp/

[62] van Oldenborgh, G. J., Philip, S., Kew, S. F., & King, A. (2018). Rapid attribution of the extreme heat waves in Northern Europe. World Weather Attribution.

[63] Wang, K., Wang, J., Wang, P., Sparrow, M., Yang, J., & Chen, H. (2007). Influences of urbanization on surface characteristics as derived from the Moderate-Resolution Imaging Spectroradiometer: A case study for the Beijing metropolitan area. Journal of Geophysical Research: Atmospheres, 112(D22), D22S06. https://doi.org/10.1029/2006JD007997

[64] Wang Y, Berardi U, Akbari H. Comparing the effects of urban heat island mitigation strategies for Toronto, Canada. Energy and Buildings. 2016, 114: 2-19.

[65] Zha Y, Gao J, Ni S. Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. International Journal of Remote Sensing. 2003, 24(3): 583-594.

[66] Zhang Z, Paschalis A, Mijic A, Meili N, Manoli G, van Reeuwijk M, Fatichi S. A mechanistic assessment of urban heat island intensities and drivers across climates. Urban Climate. 2022, 44101215.

[67] Zhao Q, Yu L, Li X, Peng D, Zhang Y, Gong P. Progress and trends in the application of Google Earth and Google Earth Engine. Remote Sensing (Basel). 2021, 13183778.

RIGHTS & PERMISSIONS

The Author(s)