Estimating the spatial distribution of urban heat islands in six central districts of Ulaanbaatar city using machine learning algorithm
DOI:
https://doi.org/10.5564/mjgg.v62i46.4125Keywords:
Urban heat island, Machine learning, Land surface temperatureAbstract
Urban Heat Islands (UHIs) represent a growing environmental challenge in rapidly urbanizing cities, particularly in extreme climate regions such as Ulaanbaatar, Mongolia. This study aims to model and analyze the spatial distribution of UHIs across six central districts of Ulaanbaatar using Landsat 5 and Landsat 8 satellite imagery. Land Surface Temperature (LST) was derived from Landsat 8, and its relationship with six spectral indices the Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Modified Normalized Difference Water Index (MNDWI), Bare Soil index (BI), Normalized Differences Water Index (NDWI), and Normalized Building Soil Index (NDBSI) was assessed. Two ensemble machine learning algorithms, Random Forest (RF) and Extreme Gradient Boosting (XGB), were employed to model UHI patterns. RF performed better in 1994 (a coefficients of determination (R²) = 0.72, a root-mean-square error (RMSE) = 1.89°C), while XGB showed superior performance in 2024 (R2 = 0.75, RMSE = 1.97°C). BI and NDBSI were the most influential contributors to UHI intensity, whereas vegetated areas (NDVI, MNDVI) had consistent cooling effects. The spatial modeling revealed a clear intensification of UHI effects over time, particularly in built-up and bare land zones. This study is significant as it applies ML techniques to long-term satellite data in a cold-climate, data-limited urban setting. By providing a rare longitudinal perspective, it contributes to understanding UHI dynamics in Mongolia and demonstrates the potential of open-access remote sensing data combined with ML for urban climate assessments. The findings offer valuable insight for urban planners, emphasizing the critical role of green infrastructure in mitigating thermal stress and informing climate-resilient development strategies in rapidly growing cities.
Downloads
153
References
[1] P. Hoffmann, O. Krueger, and K. H. Schlünzen, “A statistical model for the urban heat island and its application to a climate change scenario,” Int. J. Climatol, vol. 32, no. 8, pp. 1238–1248, May 2011. Available: doi: 10.1002/joc.2348.
[2] X. Zhou and H. Chen, “Impact of urbanization-related land use land cover changes and urban morphology changes on the urban heat island phenomenon,” Sci. Total Environ, vol. 635, pp. 1467–1476, Sep. 2018. Available: doi: 10.1016/j.scitotenv.2018.04.091.
[3] B. Y. Tam, W. A. Gough, and T. Mohsin, “The impact of urbanization and the urban heat island effect on day to day temperature variation,” Urban Clim., vol. 12, pp. 1–10, Jun. 2015. Available: doi: 10.1016/j.uclim.2014.12.004.
[4] S. Talukdar et al., “Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations—A Review,” Remote Sens, vol. 12, no. 7, p. 1135, Apr. 2020. Available: doi: 10.3390/rs12071135.
[5] D. Sainbayar, “Modeling the spatial distribution of atmospheric carbon dioxide concentration” in Ph.D. dissertation, School of Science, National University of Mongolia, Ulaanbaatar, Mongolia, 2024, pp. 115.
[6] C. Yoo, J. Im, D. Cho, Y. Lee, D. Bae, and P. Sismanidis, “Downscaling MODIS nighttime land surface temperatures in urban areas using ASTER thermal data through local linear forest,” Int. J. Appl. Earth Obs. Geoinf., vol. 110, pp. 102827, Jun. 2022,. Available: doi: 10.1016/j.jag.2022.102827.
[7] T. S. Arulananth et al., “Analysis of Reason to Global Warming Based on Heat Pattern Using Hyperspectral Imaging: Artificial Intelligence Application,” Remote Sens Earth Syst Sci, vol. 7, pp 379–388, Sep. 2024, Available: doi: 10.1007/s41976-024-00130-2.
[8] National Statistics Office of Mongolia. (2024). Statistical yearbook 2024 pp. 40. [Online]. Available: https://www.nso.mn/mn/statistic/file-library/view/82183302.
[9] D. Amarsaikhan, A. Enkhmanlai, G. Tsogzol, A. Munkh-Erdene, E. Jargaldalai, D. Enkhjargal & B. Byambadolgor, “Urban land use change study in Ulaanbaatar city using RS and GIS,” Journal of Institute of Mathematics and Digital Technology, 5(1), 40-49, 2023. Available: doi: 10.5564/jimdt.v5i1.3317
[10] R. C. Estoque and Y. Murayama, “Monitoring surface urban heat island formation in a tropical mountain city using Landsat data (1987–2015),” ISPRS J. Photogramm. Remote Sens., vol. 133, pp. 18–29, 2017. Available: doi: 10.1016/j.isprsjprs.2017.09.008.
[11] B. Byambadolgor, D. Amarsaikhan, “Mapping the spatial distribution of urban heat islands in Darhan and Erdenet cities,” Mongolia, Full paper published in Proceeding of the ACRS, Ulaanbaatar, Mongolia, 2022.
[12] M. Y. Yasin, J. Abdullah, N. M. Noor, M. M. Yusoff, and N. M. Noor, “Landsat observation of urban growth and land use change using NDVI and NDBI analysis,” IOP Conference Series: Earth and Environmental Science, vol. 1067, no. 1, p. 012037, Oct. 2022. Available: doi: 10.1088/1755-1315/1067/1/012037.
[13] K.S. Arunab and A. Mathew, “Exploring spatial machine learning techniques for improving land surface temperature prediction,” Kuwait Journal of Science, vol. 51, no. 3, pp. 100242–100242, May 2024. Available: doi: 10.1016/j.kjs.2024.100242.
[14] E. Nyamjargal, D. Amarsaikhan, A. Munkh-Erdene, V. Battsengel, and Ch. Bolorchuluun, “Object-based classification of mixed forest types in Mongolia,” Geocarto International, vol. 35, no. 14, pp. 1615–1626, Jun 2019. Available: doi: 10.1080/10106049.2019.1583775.
[15] M. K. Uçar, M. Nour, H. Sindi, and K. Polat, “The Effect of Training and Testing Process on Machine Learning in Biomedical Datasets,” Mathematical Problems in Engineering, vol. 2020, pp. 1–17, May 2020, Available: doi:10.1155/2020/2836236.
[16] D. Zhou, S. Zhao, S. Liu, L. Zhang, and C. Zhu, “Surface urban heat island in China’s 32 major cities: Spatial patterns and drivers,” Remote Sensing of Environment, vol. 152, pp. 51–61, Sep. 2014, doi: 10.1016/j.rse.2014.05.017.
[17] X. Li, Y. Zhou, G. R. Asrar, M. Imhoff, and X. Li, “The surface urban heat island response to urban expansion: A panel analysis for the conterminous United States,” Sci. Total Environ, vol. 605–606, pp. 426–435, Dec. 2017, Available: doi: 10.1016/j.scitotenv.2017.06.229.
[18] S. Razzaghi Asl, “Rooftops for Whom? Some Environmental Justice Issues in Urban Green Roof Policies of Three North American Cities,” Environmental Policy and Law, pp. 1–12, Dec. 2022. Available: doi: 10.3233/epl-220015.
[19] N. Debbage, C. Shepherd, M. Hall, and S. C. Cordero, “Integrating socio-environmental data in machine learning for urban heat island mapping,” Computers, Environment and Urban Systems, vol. 83, p. 101521, 2020.
[20] J. A. Voogt and T. R. Oke, “Thermal remote sensing of urban climates,” Remote Sensing of Environment, vol. 86, no. 3, pp. 370–384, Aug. 2003. Available: doi: 10.1016/s0034-4257(03)00079-8.
[21] Y. Hu, J. Zhang, and Y. Lin, “A machine learning approach for urban land surface temperature modeling: A case study in Wuhan, China,” Remote Sens, vol. 12, no. 17, p. 2784, 2020.
[22] C. C. Pham, N. T. Nguyen, Q. T. Tran, and N. N. Nguyen, “Prediction of surface urban heat island in Ho Chi Minh City, Viet Nam using remote sensing and logistic regression model,” IOP Conference Series Earth and Environmental Science, vol. 1349, no. 1, pp. 012031–012031, May 2024. Available: doi: 10.1088/1755-1315/1349/1/012031.
[23] Ghazaleh Tanoori, A. Soltani, and Atoosa Modiri, “Machine Learning for Urban Heat Island (UHI) Analysis: Predicting Land Surface Temperature (LST) in Urban Environments,” Urban clim, vol. 55, pp. 101962–101962, May 2024. Available: doi: 10.1016/j.uclim.2024.101962.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Byambadolgor Batdorj, Amarsaikhan Damdinsuren, Sainbayar Dalantai, Munkh-Erdene Altangerel
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on any research article in the Mongolian Journal of Geography and Geoecology is retained by the author(s).
The authors grant the Mongolian Journal of Geography and Geoecology a license to publish the article and identify itself as the original publisher.
Articles in the Mongolian Journal of Geography and Geoecology are Open Access articles published under a Creative Commons Attribution 4.0 International License CC BY.
This license permits use, distribution and reproduction in any medium, provided the original work is properly cited.
