Regional Urban Heat Island Risk Mapping Using PCA and Fuzzy Clustering

Darniati Darniati; Muhammad Rizal  Haris; Muhammad Faisal; Lisa Fitriani  Ishak

doi:10.29207/resti.v10i5.7420

Authors

Darniati Darniati Universitas Muhammadiyah Makassar
Muhammad Rizal Haris Universitas Muhammadiyah Makassar
Muhammad Faisal Universitas Muhammadiyah Makassar
Lisa Fitriani Ishak Universitas Muhammadiyah Makassar

DOI:

https://doi.org/10.29207/resti.v10i5.7420

Keywords:

fuzzy clustering, principal component analysis, remote sensing, spatial risk mapping, urban heat island

Abstract

Urban Heat Island (UHI) effects pose increasing challenges in rapidly urbanizing tropical regions, where land-cover transformation and population concentration intensify spatial thermal risk. This study proposes an integrated Principal Component Analysis-Fuzzy C-Means spatial framework to classify and map regional UHI risk across Sulawesi Island, Indonesia, using multi-source geospatial data. Land surface temperature, vegetation condition, built-up intensity, and population density were harmonized on a 1 km grid for the 2024-2025 period. Dimensionality reduction was performed to extract dominant spatial variance, followed by fuzzy clustering to represent gradual transitions in UHI risk. The results indicate a strong dominance of the first principal component, explaining more than 99.9% of total variance in both years, reflecting a stable integrated urban-environmental gradient. Three UHI risk classes were delineated, representing low-risk cool areas, moderate-risk transitional zones, and high-risk densely built urban regions. Although a two-cluster solution achieved the lowest numerical validity, a three-cluster configuration was adopted to better capture transitional urban conditions relevant to spatial planning. The resulting maps reveal concentrated UHI risk in major urban centers, particularly Makassar and expanding peri-urban corridors. The proposed framework provides a robust, interpretable, and policy-relevant approach for regional-scale UHI risk assessment in data-limited tropical environments.

Downloads

Download data is not yet available.

References

[1] L. Yao, S. Sun, C. Song, Y. Wang, and Y. Xu, “Recognizing surface urban heat ‘island’ effect and its urbanization association in terms of intensity, footprint, and capacity: A case study with multi-dimensional analysis in Northern China,” J. Clean. Prod., vol. 372, p. 133720, 2022, doi: https://doi.org/10.1016/j.jclepro.2022.133720.

[2] R. M. Abou Samra, “Investigating and mapping day-night urban heat island and its driving factors using Sentinel/MODIS data and Google Earth Engine. Case study: Greater Cairo, Egypt,” Urban Clim., vol. 52, p. 101729, 2023, doi: https://doi.org/10.1016/j.uclim.2023.101729.

[3] C. Zhang, Y. Yang, and L. Yu, “Assessing urban surface thermal environment and heat health risk in Chinese cities: A twenty-year study,” Urban Clim., vol. 59, p. 102304, 2025, doi: https://doi.org/10.1016/j.uclim.2025.102304.

[4] R. Jia et al., “Population heat exposure risk from the perspective of urban heat island spatial expansion in China during 2005–2020,” Urban Clim., vol. 56, p. 101987, 2024, doi: https://doi.org/10.1016/j.uclim.2024.101987.

[5] T. Sarker, P. Fan, J. P. Messina, N. Mujahid, E. Aldrian, and J. Chen, “Impact of Urban built-up volume on Urban environment: A Case of Jakarta,” Sustain. Cities Soc., vol. 105, p. 105346, 2024, doi: https://doi.org/10.1016/j.scs.2024.105346.

[6] R. E. N. Rongcai, W. U. Guoxiong, and C. A. I. Ming, “MOD11A2 MODIS/Terra Suhu/Emisivitas Permukaan Tanah 8 Hari L3 Global 1km SIN Grid V006,” 2015, doi: https://doi.org/10.5067/MODIS/MOD11A2.006.

[7] R. E. N. Rongcai, W. U. Guoxiong, and C. A. I. Ming, “MODIS/Terra Vegetation Indices Monthly L3 Global 1km SIN Grid V061,” 2021, doi: https://doi.org/10.5067/MODIS/MOD13A3.061.

[8] E. C. J. R. Centre, GHSL data package 2023. Publications Office of the European Union, 2023. doi: 10.2760/098587.

[9] Kholif, “Constrained estimates of 2015-2030 total number of people per grid square at a resolution of 3 arc (approximately 100m at the equator) R2025A version v1,” p. 6, 2025, doi: https://hub.worldpop.org/doi/10.5258/SOTON/WP00839.

[10] Y. Zhou and Q. Weng, “Building up a data engine for global urban mapping,” Remote Sens. Environ., vol. 311, p. 114242, 2024, doi: https://doi.org/10.1016/j.rse.2024.114242.

[11] F. Hung, M. Aboelnour, D. Wood, and J. Zhang, “Urban heat risks reimagined: A framework for global physical hazard assessment,” Urban Clim., vol. 64, p. 102659, 2025, doi: https://doi.org/10.1016/j.uclim.2025.102659.

[12] Z. Zhu, S. Qiu, and S. Ye, “Remote sensing of land change: A multifaceted perspective,” Remote Sens. Environ., vol. 282, p. 113266, 2022, doi: https://doi.org/10.1016/j.rse.2022.113266.

[13] P. Shen, “Spatiotemporal mapping of urban air temperature and UHI under TMY condition: A reference station based machine learning approach,” Energy Build., vol. 343, p. 115923, 2025, doi: https://doi.org/10.1016/j.enbuild.2025.115923.

[14] A. Wang, Y. Dai, M. Zhang, and E. Chen, “Exploring the cooling intensity of green cover on urban heat island: A case study of nine main urban districts in Chongqing,” Sustain. Cities Soc., vol. 124, p. 106299, 2025, doi: https://doi.org/10.1016/j.scs.2025.106299.

[15] S. Liang et al., “Advancements in high-resolution land surface satellite products: A comprehensive review of inversion algorithms, products and challenges,” Sci. Remote Sens., vol. 10, p. 100152, 2024, doi: https://doi.org/10.1016/j.srs.2024.100152.

[16] I. Onțel, V. Amihăesei, D. Micu, A. Dumitrescu, and S. Cheval, “Influence of environmental factors on land surface temperature and surface urban heat island. A cross-country analysis in Romania,” Sustain. Cities Soc., vol. 128, p. 106454, 2025, doi: https://doi.org/10.1016/j.scs.2025.106454.

[17] Z. Lin, H. Xu, X. Yao, C. Yang, and D. Ye, “How does urban thermal environmental factors impact diurnal cycle of land surface temperature? A multi-dimensional and multi-granularity perspective,” Sustain. Cities Soc., vol. 101, p. 105190, 2024, doi: https://doi.org/10.1016/j.scs.2024.105190.

[18] D. Liu et al., “Spatio-temporal patterns and population exposure risks of urban heat island in megacity Shanghai, China,” Sustain. Cities Soc., vol. 108, p. 105500, 2024, doi: https://doi.org/10.1016/j.scs.2024.105500.

[19] H. Xu, C. Li, Y. Hu, R. Kong, Q. Wang, and Y. Zhou, “Long-term temporal and spatial divergence patterns of urban heat risk in the Beijing–Tianjin–Hebei urban agglomeration,” Urban Clim., vol. 56, p. 102085, 2024, doi: https://doi.org/10.1016/j.uclim.2024.102085.

[20] A. Golzari Oskouei et al., “Feature-weighted fuzzy clustering methods: An experimental review,” Neurocomputing, vol. 619, p. 129176, 2025, doi: https://doi.org/10.1016/j.neucom.2024.129176.

[21] H. Zhang and S.-L. Huang, “Improved fuzzy C-means clustering algorithm based on fuzzy particle swarm optimization for solving data clustering problems,” Math. Comput. Simul., vol. 233, pp. 311–329, 2025, doi: https://doi.org/10.1016/j.matcom.2025.02.012.

[22] M. Thamrin et al., “Machine learning for global trade analysis: a hybrid clustering approach using DBSCAN, elbow, and SOM,” IAES Int. J. Artif. Intell., vol. 14, no. 4, p. 3033, Aug. 2025, doi: https://doi.org/10.11591/ijai.v14.i4.pp3033-3046.

[23] E. Elmarakby and H. Elkadi, “Prioritising urban heat island mitigation interventions: Mapping a heat risk index,” Sci. Total Environ., vol. 948, p. 174927, 2024, doi: https://doi.org/10.1016/j.scitotenv.2024.174927.

[24] B. Yan and Z. Xie, “A robust fuzzy cluster validity index based on local distances,” Expert Syst. Appl., vol. 295, Jan. 2026, doi: https://doi.org/10.1016/j.eswa.2025.128883.

[25] Y. Ji, Z. Li, Y. Liu, H. Tang, H. Sun, and T. Feng, “How urban sprawl patterns shape the thermal environment during hot summers: An empirical analysis of 338 Chinese cities,” Environ. Impact Assess. Rev., vol. 117, p. 108251, 2026, doi: https://doi.org/10.1016/j.eiar.2025.108251.

[26] G. K. Sharma and V. V. Ghuge, “Assessment of urban growth dynamics using landscape expansion index: A study of 514 metropolitan cities from 1975 to 2020,” Land use policy, vol. 153, p. 107557, 2025, doi: https://doi.org/10.1016/j.landusepol.2025.107557.

[27] Q. Wang, H. Wang, L. Ren, J. Chen, and X. Wang, “Hourly impact of urban features on the spatial distribution of land surface temperature: A study across 30 cities,” Sustain. Cities Soc., vol. 113, p. 105701, 2024, doi: https://doi.org/10.1016/j.scs.2024.105701.

[28] M. P. da Silva et al., “Advancing agricultural remote sensing: A comprehensive review of deep supervised and Self-Supervised Learning for crop monitoring,” Comput. Graph., vol. 133, p. 104434, 2025, doi: https://doi.org/10.1016/j.cag.2025.104434.

[29] J. Zhang et al., “Spatiotemporal dynamic mapping of heat exposure risk for different populations in city based on hourly multi-source data,” Sustain. Cities Soc., vol. 107, p. 105454, 2024, doi: https://doi.org/10.1016/j.scs.2024.105454.

[30] A. Chauhan et al., “Chapter 10 - Earth observation applications for urban mapping and monitoring: research prospects, opportunities and challenges,” in Earth Observation in Urban Monitoring, A. Kumar, P. K. Srivastava, P. Saikia, and R. K. Mall, Eds., Elsevier, 2024, pp. 197–229. doi: https://doi.org/10.1016/B978-0-323-99164-3.00007-0.

[31] D. Ehrlich, T. Kemper, M. Pesaresi, and C. Corbane, “Built-up area and population density: Two Essential Societal Variables to address climate hazard impact,” Environ. Sci. Policy, vol. 90, pp. 73–82, 2018, doi: https://doi.org/10.1016/j.envsci.2018.10.001.

[32] W. Qian, F. Rao, X. Li, and D. Lai, “Mapping priority zones for urban heat mitigation in Shanghai: Heat risk vs. shelter provision,” Comput. Environ. Urban Syst., vol. 121, p. 102330, 2025, doi: https://doi.org/10.1016/j.compenvurbsys.2025.102330.

[33] L. H. Son, “Enhancing clustering quality of geo-demographic analysis using context fuzzy clustering type-2 and particle swarm optimization,” Appl. Soft Comput., vol. 22, pp. 566–584, 2014, doi: https://doi.org/10.1016/j.asoc.2014.04.025.

[34] Y. Zhou, H. Huang, J. Ma, Q. Liu, and Y. Guo, “Complex spatiotemporal thermal effects caused by urban densification: Patterns, characteristics, mechanisms and strategies,” Build. Environ., vol. 288, p. 114008, 2026, doi: https://doi.org/10.1016/j.buildenv.2025.114008.

[35] A. Soltani, P. Azizi, A. Rahimioun, and M. Sedaghatfard, “Volumetric urban sprawl: Horizontal and vertical growth in two metropolitans,” J. Urban Manag., vol. 14, no. 4, pp. 1004–1021, 2025, doi: https://doi.org/10.1016/j.jum.2025.03.006.

[36] A. Soltani, A. Dehghani, and P. Azizi, “Volumetric insights into urban growth analysis: Investigating vertical and horizontal patterns,” Sustain. Cities Soc., vol. 130, p. 106589, 2025, doi: https://doi.org/10.1016/j.scs.2025.106589.

[37] M. Davtalab and S. Byčenkienė, “Synergistic effects of spatial urban form on PM2.5 concentration and urban heat islands: A multi-scale explanatory machine learning,” J. Clean. Prod., vol. 538, p. 147226, 2026, doi: https://doi.org/10.1016/j.jclepro.2025.147226.

[38] T. Ye et al., “Billions of people exposed to increasing heat but decreasing greenness from 2000 to 2022,” Innov., vol. 6, no. 5, p. 100870, 2025, doi: https://doi.org/10.1016/j.xinn.2025.100870.

[39] Z. Stalhandske et al., “Global assessment of population exposure to multiple climate-related hazards from 2003 to 2021: a retrospective analysis,” Lancet Planet. Heal., vol. 9, no. 8, p. 101295, 2025, doi: https://doi.org/10.1016/j.lanplh.2025.101295.

[40] F. Zhang, G. Chen, J. Hua, and C. Ren, “Investigating the dynamic pattern of regional heat health risks: A case study of Guangdong Province, China,” Urban Clim., vol. 57, p. 102127, 2024, doi: https://doi.org/10.1016/j.uclim.2024.102127.

[41] J. Yin, H. Wang, and J. Zhang, “Exploring the thermal effects and influencing factors of urban parks during diurnal variations,” Sustain. Cities Soc., vol. 129, p. 106499, 2025, doi: https://doi.org/10.1016/j.scs.2025.106499.

[42] Y. Xiao et al., “Seasonal variability and multi-factor analysis of urban park cooling effects: A case study of Nanjing, China,” Sustain. Cities Soc., vol. 131, p. 106711, 2025, doi: https://doi.org/10.1016/j.scs.2025.106711.

[43] M. Chen, X. Li, A. Dang, Y. Weng, and S. Qiu, “Adapting to heatwaves: Optimizing urban green spaces in Beijing to reduce heat health risks,” Sustain. Cities Soc., vol. 130, p. 106600, 2025, doi: https://doi.org/10.1016/j.scs.2025.106600.

[44] T. Zhang et al., “A new framework for assessing and dealing with heat risk from an urban resilience perspective,” J. Clean. Prod., vol. 479, p. 144008, 2024, doi: https://doi.org/10.1016/j.jclepro.2024.144008.

[45] M. Faisal et al., “A Hybrid MOO, MCGDM, and Sentiment Analysis Methodologies for Enhancing Regional Expansion Planning: A Case Study Luwu - Indonesia,” Int. J. Math. Eng. Manag. Sci., vol. 10, no. 1, pp. 163–188, Feb. 2025, doi: https://doi.org/10.33889/IJMEMS.2025.10.1.010.

[46] M. Faisal et al., “A Hybrid MOO-MCDM-PSOM Approach for Mapping Urban Carbon Trade Policies,” Feb. 12, 2025. doi: https://doi.org/10.33889/IJMEMS.2025.10.6.101.

[47] X. Dong, X. Li, Y. Ye, D. Su, R. Yang, and A. Lausch, “Measuring urban thermal environment from accessibility-based perspective: A case study in a populous city,” Geogr. Sustain., vol. 5, no. 3, pp. 329–342, 2024, doi: https://doi.org/10.1016/j.geosus.2024.02.004.