Predicting surface urban heat island intensity and its drivers using machine learning and spatial XAI for achieving SDG-11

Abstract

Surface Urban Heat Island (SUHI) is a major environmental concern especially in rapidly expanding cities with substantial impacts on urban climate, human health, and energy demand. Despite extensive documentation of the phenomenon, our understanding of the driving forces behind SUHI remains limited. Therefore, the present study is intended to analysed the drivers of SUHI and their spatial pattern of influence in Mumbai metropolitan region (MMR) using google earth engine (GEE) and machine learning (ML) models. The SUHI intensity has been calculated using ML models like random forest (RF), gradient boosting, XGBoost, and LightGBM. The divers of SUHI have been analysed using explainable artificial intelligence (XAI) and for the spatial pattern of influence of the drivers, a novel spatial XAI model has been estimated. Multi-stage feature selection involving correlation screening and variance inflation factor (VIF) analysis ensured numerical stability and interpretability. Model performance has been evaluated using multiple metrics, including R², RMSE, MAE, explained variance, bias, and maximum error. Result shows that LightGBM has the best overall performance, achieving a test R² of 0.86 and the lowest RMSE (1.49 °C), followed by XGBoost (test R² = 0.86; RMSE = 1.52 °C). Spatial cross-validation produced conservative yet robust estimates (CV R² = 0.77–0.78), confirming strong spatial generalisation. Bootstrap-based uncertainty analysis further shows narrow confidence intervals for both R² and RMSE, indicating high model stability and low sensitivity to sampling variability. Graphical and spatial XAI analyses identified built-up intensity (NDBI), bare land index, night-time light intensity, and population density as dominant positive drivers of SUHII. SUHI intensity in low category has decreased from 13.69 percent in 2002 to 6.31 percent in 2024 while SUHI intensity in very high zone has increased significantly. Spatial prediction shows pronounced SUHII hotspots in densely urbanised and industrial zones, whereas coastal areas, vegetated regions, and water bodies consistently exhibited lower SUHII. The spatial heterogeneity captured by XAI highlights the necessity of location-specific mitigation strategies rather than uniform city-wide interventions. These findings provide critical evidence to enhance urban thermal comfort and resilience for achieving sustainable development goals (SDGs) such as SDG-11.3 (sustainable urban growth), SDG-11.5 (resilience to urban hazards), SDG-11.6 (reducing environmental impacts), and SDG-11.7 (inclusive access to green spaces).

Keywords

Urban expansion / Surface urban heat island intensity / Driving forces of SUHII / Explainable AI / Machine learning / Sustainable development goals

References

[1] Abhishek N, Jenamani M, Mahanty B. Urban growth in Indian cities: Are the driving forces really changing?. Habitat International, 2017, 69: 48-57

[2] Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., ... & Herrera, F. (2023). Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence. Information Fusion, 99, 101805.

[3] Ascencio EJ, Barja A, Benmarhnia T, Carrasco-Escobar G. Disproportionate exposure to surface-urban heat islands across vulnerable populations in Lima city, Peru. Environmental Research Letters, 2023, 18(7): 074001

[4] Bardhan R, Pan J, Chen S, Cho TY. Breathing space in a compact city: Impacts of urban re-densification on Mumbai’s low-income housing environment. Habitat International, 2024, 149 103098

[5] de Bont, J., Nori-Sarma, A., Stafoggia, M., Banerjee, T., Ingole, V., Jaganathan, S., ... & Ljungman, P. (2024). Impact of heatwaves on all-cause mortality in India: A comprehensive multi-city study. Environment International, 184, 108461.

[6] Chakrabortty R, Kumar A, Mishuk SR, Pramanik M, Avtar R, Manna H, Zhran M. Assessment of urban environment quality using analytical hierarchical process and multi-dimensional decomposition analysis for Mumbai metropolitan region, India. Advances in Space Research, 2025, 7532792-2809

[7] Chapman S, Thatcher M, Salazar A, Watson JE, McAlpine CA. The effect of urban density and vegetation cover on the heat island of a subtropical city. Journal of Applied Meteorology and Climatology, 2018, 57(11): 2531-2550

[8] Chen L, Zhang Y, Zhu E, Che Y, Wu Y. Segregation of sea breezes and cooling effects on land-surface temperatures in a coastal city. Sustainable Cities and Society, 2025, 118 106017

[9] Cleland SE, Steinhardt W, Neas LM, West JJ, Rappold AG. Urban heat island impacts on heat-related cardiovascular morbidity: A time series analysis of older adults in US metropolitan areas. Environment International, 2023, 178 108005

[10] Fang Q, Liu C, Ren Z, Fu Y, Fan H, Wang Y, Yu Z. Spatiotemporal analysis of surface urban heat island dynamics in central Yunnan city cluster. Sustainability, 2024, 16(11): 4819

[11] Ghaffarian S, Taghikhah FR, Maier HR. Explainable artificial intelligence in disaster risk management: Achievements and prospective futures. International Journal of Disaster Risk Reduction, 2023, 98 104123

[12] Gohain KJ, Goswami A, Mohammad P, Kumar S. Modelling relationship between land use land cover changes, land surface temperature and urban heat island in Indore city of central India. Theoretical and Applied Climatology, 2023, 15131981-2000

[13] Guo G, Wu Z, Xiao R, Chen Y, Liu X, Zhang X. Impacts of urban biophysical composition on land surface temperature in urban heat island clusters. Landscape and Urban Planning, 2015, 135: 1-10

[14] Gupta, S. (2013). Groundwater information: Greater Mumbai District, Maharashtra. Central Ground Water Board, Nagpur. https://www.cgwb.gov.in/old_website/District_Profile/Maharashtra/Greater%20Mumbai.pdf

[15] Huang, W. T. K., Masselot, P., Bou-Zeid, E., Fatichi, S., Paschalis, A., Sun, T., ... & Manoli, G. (2023). Economic valuation of temperature-related mortality attributed to urban heat islands in European cities. Nature Communications, 14(1), 7438.

[16] Hwang B, Sou HD, Oh JH, Park CR. Cooling effect of urban forests on the urban heat island in Seoul. South Korea. Plos One, 2023, 18(7 e0288774

[17] Khamchiangta D, Dhakal S. Physical and non-physical factors driving urban heat island: Case of Bangkok Metropolitan Administration. Thailand. Journal of Environmental Management, 2019, 248109285

[18] Kong G, Peng J, Corcoran J. Modelling urban heat island effects: A global analysis of 216 cities using machine learning techniques. Computational Urban Science, 2025, 51): 1-12

[19] Kotharkar R, Bagade A. Evaluating urban heat island in the critical local climate zones of an Indian city. Landscape and Urban Planning, 2018, 169: 92-104

[20] Kumar, P., Debele, S. E., Khalili, S., Halios, C. H., Sahani, J., Aghamohammadi, N., ... & Jones, L. (2024). Urban heat mitigation by green and blue infrastructure: Drivers, effectiveness, and future needs. The Innovation, 5(2), 100588

[21] Li Y, Sun Y, Li J, Gao C. Socioeconomic drivers of urban heat island effect: Empirical evidence from major Chinese cities. Sustainable Cities and Society, 2020, 63 102425

[22] Liou YA, Tran DP, Nguyen KA. Spatio-temporal patterns and driving forces of surface urban heat island in Taiwan. Urban Climate, 2024, 53 101806

[23] Litardo J, Palme M, Borbor-Córdova M, Caiza R, Macías J, Hidalgo-León R, Soriano G. Urban heat island intensity and buildings’ energy needs in Duran, Ecuador: Simulation studies and proposal of mitigation strategies. Sustainable Cities and Society, 2020, 62 102387

[24] Mangal S, Kumar D, Dhupper R, Kumari M, Gupta AK. Identifying influential climatic factors for urban risk studies in rapidly urbanizing region. Computational Urban Science, 2024, 4(1): 9

[25] Meng F, Yan S, Tian G, Wang Y. Surface urban heat island effect and its spatiotemporal dynamics in metropolitan area: A case study in the Zhengzhou metropolitan area China. Frontiers in Environmental Science, 2023, 11: 1247046

[26] Mentaschi, L., Duveiller, G., Zulian, G., Corbane, C., Pesaresi, M., Maes, J., ... & Feyen, L. (2022). Global long-term mapping of surface temperature shows intensified intra-city urban heat island extremes. Global Environmental Change, 72, 102441.

[27] Metzler, A. B., Nathvani, R., Sharmanska, V., Bai, W., Muller, E., Moulds, S., ... & Ezzati, M. (2023). Phenotyping urban built and natural environments with high-resolution satellite images and unsupervised deep learning. Science of The Total Environment, 893, 164794.

[28] Mohajerani A, Bakaric J, Jeffrey-Bailey T. The urban heat island effect, its causes, and mitigation, with reference to the thermal properties of asphalt concrete. Journal of Environmental Management, 2017, 197522-538

[29] Mohamed OY, Zahidi I. Artificial intelligence for predicting urban heat island effect and optimising land use/land cover for mitigation: Prospects and recent advancements. Urban Climate, 2024, 55 101976

[30] Mohammad P, Goswami A. Quantifying diurnal and seasonal variation of surface urban heat island intensity and its associated determinants across different climatic zones over Indian cities. Giscience & Remote Sensing, 2021, 58(7): 955-981

[31] Mohammad P, Goswami A, Chauhan S, Nayak S. Machine learning algorithm based prediction of land use land cover and land surface temperature changes to characterize the surface urban heat island phenomena over Ahmedabad city, India. Urban Climate, 2022, 42 101116

[32] Naikoo MW, Islam ARMT, Mallick J, Rahman A. Land use/land cover change and its impact on surface urban heat island and urban thermal comfort in a metropolitan city. Urban Climate, 2022, 41 101052

[33] Oke TR. City size and the urban heat island. Atmospheric Environment (1967), 1973, 7(8): 769-779

[34] Oke TR, Mills G, Christen A, Voogt JA. Urban climates. 2017Cambridge University Press

[35] Pan, L., Lu, L., Fu, P., Nitivattananon, V., Guo, H., & Li, Q. (2023). Understanding spatiotemporal evolution of the surface urban heat island in the Bangkok metropolitan region from 2000 to 2020 using enhanced land surface temperature. Geomatics, Natural Hazards and Risk, 14.

[36] Pandey B, Zhang Q, Seto KC. Time series analysis of satellite data to characterize multiple land use transitions: A case study of urban growth and agricultural land loss in India. Journal of Land Use Science, 2018, 13(3): 221-237

[37] Parveen N, Siddiqui L, Sarif MN, Islam MS, Khanam N, Mohibul S. Industries in Delhi: Air pollution versus respiratory morbidities. Process Safety and Environmental Protection, 2021, 152495-512

[38] Patel S, Indraganti M, Jawarneh RN. Land surface temperature responses to land use dynamics in urban areas of Doha, Qatar. Sustainable Cities and Society, 2024, 104 105273

[39] Peng J, Liu Q, Xu Z, Lyu D, Du Y, Qiao R, Wu J. How to effectively mitigate urban heat island effect? A perspective of waterbody patch size threshold. Landscape and Urban Planning, 2020, 202 103873

[40] Peng, S., Piao, S., Ciais, P., Friedlingstein, P., Ottle, C., Bréon, F. M., ... & Myneni, R. B. (2012). Surface urban heat island across 419 global big cities. Environmental Science & Technology, 46(2), 696–703.

[41] Qian J, Meng Q, Zhang L, Schlink U, Hu X, Gao J. Characteristics of anthropogenic heat with different modeling ideas and its driving effect on urban heat islands in seven typical Chinese cities. Science of the Total Environment, 2023, 886 163989

[42] Qiu GY, Zou Z, Li X, Li H, Guo Q, Yan C, Tan S. Experimental studies on the effects of green space and evapotranspiration on urban heat island in a subtropical megacity in China. Habitat International, 2017, 68: 30-42

[43] Radomska, M., Clarke, R., & Hewlett, D. (2023). Sustainable Project Management of Green Spaces, Protected and Conserved Areas: Opportunities and Challenges. Managing Protected Areas: People and Places, 115–141.

[44] Risnayah S, Mudhalifana W, Restele L. Dynamics of urban heat island and NO2 gas during the Covid-19 pandemic. Tunas Geografi, 2023, 12(2): 90-102

[45] Roxon J, Ulm F, Pellenq R. Urban heat island impact on state residential energy cost and CO2 emissions in the United States. Urban Climate, 2020, 31 100546

[46] Salam M, Islam MK, Jahan I, Chowdhury MA. Assessing the impacts of vegetation loss and land surface temperature on Surface Urban Heat Island (SUHI) in Gazipur District Bangladesh. Computational Urban Science, 2024, 4(1): 24

[47] Semenzato P, Bortolini L. Urban heat island mitigation and urban green spaces: Testing a model in the city of Padova (Italy). Land, 2023, 122476

[48] Sethi SS, Vinoj V. Urbanization and regional climate change-linked warming of Indian cities. Nature Cities, 2024, 16402-405

[49] Shahfahad, Bindajam, A. A., Naikoo, M. W., Horo, J. P., Mallick, J., Rihan, M., ... & Rahman, A. (2023). Response of soil moisture and vegetation conditions in seasonal variation of land surface temperature and surface urban heat island intensity in sub-tropical semi-arid cities. Theoretical and Applied Climatology, 153(1), 367–395.

[50] Shahfahad., Talukdar, S., Naikoo, M. W., & Rahman, A. (2024). Urban expansion and vegetation dynamics: The role of protected areas in preventing vegetation loss in a growing mega city. Habitat International, 150, 103129.

[51] Sharma GK, Ghuge VV. Spatio-temporal analysis of urban growth in the Mumbai metropolitan area using landsat imagery. Discover Cities, 2025, 2(1): 100

[52] Siddiqui, A., Kushwaha, G., Nikam, B., Srivastav, S. K., Shelar, A., & Kumar, P. (2021). Analysing the day/night seasonal and annual changes and trends in land surface temperature and surface urban heat island intensity (SUHII) for Indian cities. Sustainable Cities and Society, 75, 103374.

[53] Sidiqui P, Tariq M, Ng A. An investigation to identify the effectiveness of socioeconomic, demographic, and buildings’ characteristics on surface urban heat island patterns. Sustainability, 2022, 145 2777

[54] Singh RB, Grover A, Zhan J. Inter-seasonal variations of surface temperature in the urbanized environment of Delhi using Landsat thermal data. Energies, 2014, 731811-1828

[55] Smith IA, Fabian MP, Hutyra LR. Urban green space and albedo impacts on surface temperature across seven United States cities. Science of the Total Environment, 2023, 857 159663

[56] Talukdar S, Naikoo MW, Rihan M, Mohammad P, Rahman A. Seasonal dynamics of land surface temperature and urban thermal comfort with land use land cover pattern in semi-arid Indian cities: Insights for sustainable urban management. Urban Climate, 2024, 57 102105

[57] Tamiminia H, Salehi B, Mahdianpari M, Quackenbush L, Adeli S, Brisco B. Google Earth Engine for geo-big data applications: A meta-analysis and systematic review. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 164: 152-170

[58] Tan X, Sun X, Huang C, Yuan Y, Hou D. Comparison of cooling effect between green space and water body. Sustainable Cities and Society, 2021, 67 102711

[59] Teke A, Kavzoglu T. Exploring the decision-making process of ensemble learning algorithms in landslide susceptibility mapping: Insights from local and global eXplainable AI analyses. Advances in Space Research, 2024, 74(8): 3765-3785

[60] Tian, P., Li, J., Cao, L., Pu, R., Wang, Z., Zhang, H., ... & Gong, H. (2021). Assessing spatiotemporal characteristics of urban heat islands from the perspective of an urban expansion and green infrastructure. Sustainable Cities and Society, 74, 103208.

[61] United Nations (2022). Make cities and human settlements inclusive, safe, resilient and sustainable. Department of Economic and Social Affairs – United Nations Statistics Division. Retrieved From: https://unstats.un.org/sdgs/report/2023/goal-11/#:~:text=The%20world’s%20population%20reached%208,70%20per%20cent%20by%202050.

[62] Venter ZS, Chakraborty T, Lee X. Crowdsourced air temperatures contrast satellite measures of the urban heat island and its mechanisms. Science Advances, 2021, 7(22 eabb9569

[63] Wang N, Zhang H, Dahal A, Cheng W, Zhao M, Lombardo L. On the use of explainable AI for susceptibility modeling: Examining the spatial pattern of SHAP values. Geoscience Frontiers, 2024, 154 101800

[64] Wouters, H., De Ridder, K., Poelmans, L., Willems, P., Brouwers, J., Hosseinzadehtalaei, P., ... & Demuzere, M. (2017). Heat stress increase under climate change twice as large in cities as in rural areas: A study for a densely populated midlatitude maritime region. Geophysical Research Letters, 44(17), 8997–9007.

[65] Yao R, Huang X, Zhang Y, Wang L, Li J, Yang Q. Estimation of the surface urban heat island intensity across 1031 global cities using the regression-modification-estimation (RME) method. Journal of Cleaner Production, 2024, 434 140231

[66] Yu H, Sun D. Quantification of urban heat island effect and differences in regional influence based on footprint analysis: A case study of the Beijing–Tianjin–Hebei urban agglomeration. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 6910-6919

[67] Yu S, Zhang Z, Liu F, Wang X, Hu S. Urban expansion in the megacity since 1970s: A case study in Mumbai. Geocarto International, 2021, 366): 603-621

[68] Zennaro, F., Furlan, E., Simeoni, C., Torresan, S., Aslan, S., Critto, A., & Marcomini, A. (2021). Exploring machine learning potential for climate change risk assessment. Earth-Science Reviews, 220, 103752.

[69] Zhang, Q., He, J., Ren, C., Chang, C., Tang, W., Ju, X., ... & Liu, L. (2025). Sensitive shrubland and unique urbanization patterns: the key to understanding emerging towns growth in arid regions. Environmental Monitoring and Assessment, 197(3), 273.

[70] 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, 44 101215

[71] Zhou Y, Guan H, Huang C, Fan L, Gharib S, Batelaan O, Simmons C. Sea breeze cooling capacity and its influencing factors in a coastal city. Building and Environment, 2019, 166 106408

RIGHTS & PERMISSIONS

The Author(s)