Improving Urban Heat Island Predictions Based on Support Vector Regression and Multi-Sensor Remote Sensing: A Case Study in Malang City

Authors

  • Yunifa Miftachul Arif
  • Salma Ainur Rohma
  • Hani Nurhayati
  • Taranita Kusumadewi
  • Fresy Nugroho
  • Ahmad Fahmi Karami

DOI:

https://doi.org/10.26594/register.v10i2.5022

Keywords:

urban heat island, Land Surface Temperature, Deep Learning, Prediction, Machine Learning

Abstract

The Urban Heat Island (UHI) phenomenon causes significant temperature increases in urban areas, adversely affecting the environment and public health. This research develops a prediction model of land surface temperature in Malang City using Support Vector Regression (SVR) with remote sensing data from Landsat-8, Sentinel-2, and SRTM. A cloud masking process is applied to improve image quality, while features such as NDVI, NDBI, NDWI, NDMI, elevation, and LST are calculated and normalized. The test results show that the Radial Basis Function (RBF) kernel with hyperparameters C = 10, Epsilon = 0.1, and gamma = 1 provides the best performance, with R² of 0.887, MSE of 1.625, and MAPE of 2.71%. This study shows that SVR with RBF kernel and appropriate tuning parameters can improve prediction accuracy. These results provide a strong basis for the development of more effective prediction models in managing UHI in big cities .

References

A. Al Kafy et al., “The operational role of remote sensing in assessing and predicting land use/land cover and seasonal land surface temperature using machine learning algorithms in Rajshahi, Bangladesh,” Appl. Geomatics, vol. 13, no. 4, pp. 793–816, 2021, doi: 10.1007/s12518-021-00390-3.

M. Unal Cilek and A. Cilek, “Analyses of land surface temperature (LST) variability among local climate zones (LCZs) comparing Landsat-8 and ENVI-met model data,” Sustain. Cities Soc., vol. 69, no. October 2020, p. 102877, 2021, doi: 10.1016/j.scs.2021.102877.

A. Mathew, S. Sreekumar, S. Khandelwal, and R. Kumar, “Prediction of land surface temperatures for surface urban heat island assessment over Chandigarh city using support vector regression model,” Sol. Energy, vol. 186, no. June 2018, pp. 404–415, 2019, doi: 10.1016/j.solener.2019.04.001.

T. Kusumadewi et al., “Urban Phytoarchitecture Design Options: Greenspace Orientation and Tree Species Intensification,” J. Adv. Res. Appl. Sci. Eng. Technol., vol. 31, no. 1, pp. 183–196, 2023, doi: 10.37934/araset.31.1.183196.

Q. Xie and Q. Sun, “Monitoring thermal environment deterioration and its dynamic response to urban expansion in Wuhan, China,” Urban Clim., vol. 39, no. August, p. 100932, 2021, doi: 10.1016/j.uclim.2021.100932.

M. T. G. Furuya et al., “A machine learning approach for mapping surface urban heat island using environmental and socioeconomic variables: a case study in a medium-sized Brazilian city,” Environ. Earth Sci., vol. 82, no. 13, pp. 1–14, 2023, doi: 10.1007/s12665-023-11017-8.

P. Kumari, V. Garg, R. Kumar, and K. Kumar, “Impact of urban heat island formation on energy consumption in Delhi,” Urban Clim., vol. 36, no. December 2020, p. 100763, 2021, doi: 10.1016/j.uclim.2020.100763.

R. Fitria, D. Kim, J. Baik, and M. Choi, “Impact of Biophysical Mechanisms on Urban Heat Island Associated with Climate Variation and Urban Morphology,” Sci. Rep., vol. 9, no. 1, pp. 1–13, 2019, doi: 10.1038/s41598-019-55847-8.

A. Addas, “Machine Learning Techniques to Map the Impact of Urban Heat Island: Investigating the City of Jeddah,” Land, vol. 12, no. 6, 2023, doi: 10.3390/land12061159.

M. Varentsov, M. Krinitskiy, and V. Stepanenko, “Machine Learning for Simulation of Urban Heat Island Dynamics Based on Large-Scale Meteorological Conditions,” Climate, vol. 11, no. 10, pp. 1–24, 2023, doi: 10.3390/cli11100200.

L. Gawuc, M. Jefimow, K. Szymankiewicz, M. Kuchcik, A. Sattari, and J. Struzewska, “Statistical Modeling of Urban Heat Island Intensity in Warsaw, Poland Using Simultaneous Air and Surface Temperature Observations,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 13, pp. 2716–2728, 2020, doi: 10.1109/JSTARS.2020.2989071.

A. Previati and G. B. Crosta, “Characterization of the subsurface urban heat island and its sources in the Milan city area, Italy,” Hydrogeol. J., vol. 29, no. 7, pp. 2487–2500, 2021, doi: 10.1007/s10040-021-02387-z.

S. Jain, S. Sannigrahi, S. Sen, and S. Bhatt, “Urban heat island intensity and its mitigation strategies in the fast- growing urban area,” J. Urban Manag., vol. 9, no. 1, pp. 54–66, 2020, doi: 10.1016/j.jum.2019.09.004.

I. S. Maijama’a, Y. Yusof, and M. F. Mohsin, “Determination of support vector regression parameters using African buffalo optimization algorithm,” Indones. J. Electr. Eng. Comput. Sci., vol. 28, no. 2, pp. 1088–1095, 2022, doi: 10.11591/ijeecs.v28.i2.pp1088-1095.

K. H. Suradiradja, I. S. Sitanggang, L. Abdullah, and I. Hermadi, “Estimation of biomass of forage sorghum (sorghum bicolor) Cv. Samurai-2 using support vector regression,” Indones. J. Electr. Eng. Comput. Sci., vol. 30, no. 3, pp. 1786–1794, 2023, doi: 10.11591/ijeecs.v30.i3.pp1786-1794.

A. K. Taloor, Drinder Singh Manhas, and G. Chandra Kothyari, “Retrieval of land surface temperature, normalized difference moisture index, normalized difference water index of the Ravi basin using Landsat data,” Appl. Comput. Geosci., vol. 9, no. August 2020, p. 100051, 2021, doi: 10.1016/j.acags.2020.100051.

H. Shi, G. Xian, R. Auch, K. Gallo, and Q. Zhou, “Urban heat island and its regional impacts using remotely sensed thermal data—a review of recent developments and methodology,” Land, vol. 10, no. 8, 2021, doi: 10.3390/land10080867.

P. Rao, P. Tassinari, and D. Torreggiani, “Exploring the land-use urban heat island nexus under climate change conditions using machine learning approach: A spatio-temporal analysis of remotely sensed data,” Heliyon, vol. 9, no. 8, p. e18423, 2023, doi: 10.1016/j.heliyon.2023.e18423.

B. Banerjee, A. Pal, A. K. Tiwari, and R. Kanchan, “Assessing the land use dynamics and thermal environment using geospatial techniques in the industrial city of Chotanagpur Plateau Region, India,” Environ. Monit. Assess., vol. 196, no. 7, p. 609, 2024, doi: 10.1007/s10661-024-12752-6.

C. Qiu, L. Liebel, L. H. Hughes, M. Schmitt, M. Korner, and X. X. Zhu, “Multitask Learning for Human Settlement Extent Regression and Local Climate Zone Classification,” IEEE Geosci. Remote Sens. Lett., vol. 19, pp. 0–4, 2022, doi: 10.1109/LGRS.2020.3037246.

A. Lefebvre, C. Sannier, and T. Corpetti, “Monitoring urban areas with Sentinel-2A data: Application to the update of the Copernicus High Resolution Layer Imperviousness Degree,” Remote Sens., vol. 8, no. 7, pp. 1–21, 2016, doi: 10.3390/rs8070606.

M. Hofton, R. Dubayah, J. B. Blair, and D. Rabine, “Validation of SRTM elevations over vegetated and non-vegetated terrain using medium footprint lidar,” Photogramm. Eng. Remote Sensing, vol. 72, no. 3, pp. 279–285, 2006, doi: 10.14358/PERS.72.3.279.

R. M. Adnan et al., “Air temperature prediction using different machine learning models,” Indones. J. Electr. Eng. Comput. Sci., vol. 22, no. 1, pp. 534–541, 2021, doi: 10.11591/ijeecs.v22.i1.pp534-541.

D. Parbat and M. Chakraborty, “A python based support vector regression model for prediction of COVID19 cases in India,” Chaos, Solitons and Fractals, vol. 138, p. 109942, 2020, doi: 10.1016/j.chaos.2020.109942.

Q. Klopfenstein and S. Vaiter, “Linear support vector regression with linear constraints,” Mach. Learn., vol. 110, no. 7, pp. 1939–1974, 2021, doi: 10.1007/s10994-021-06018-2.

I. Izonin, R. Tkachenko, N. Horbal, M. Greguš, V. Verhun, and Y. Tolstyak, “An Approach Toward Numerical Data Augmentation and Regression Modeling Using Polynomial-Kernel-Based SVR,” in Lecture Notes in Networks and Systems, M. Saraswat, S. Roy, C. Chowdhury, and A. H. Gandomi, Eds., Singapore: Springer Singapore, 2022, pp. 771–781. doi: 10.1007/978-981-16-5120-5_58.

C. Lopez-Martin, M. Azzeh, A. Bou-Nassif, and S. Banitaan, “Upsilon-SVR Polynomial Kernel for Predicting the Defect Density in New Software Projects,” Proc. - 17th IEEE Int. Conf. Mach. Learn. Appl. ICMLA 2018, pp. 1377–1382, 2018, doi: 10.1109/ICMLA.2018.00224.

M. J. van Gerrevink and S. Veraverbeke, “Evaluating the near and mid infrared bi-spectral space for assessing fire severity and comparison with the differenced normalized burn ratio,” Remote Sens., vol. 13, no. 4, pp. 1–19, 2021, doi: 10.3390/rs13040695.

Y. Murayama and R. Wang, “Editorial: Special Issue on Geographical Analysis and Modeling of Urban Heat Island Formation,” Remote Sens., vol. 15, no. 18, pp. 1–5, 2023, doi: 10.3390/rs15184474.

A. Botchkarev, “A new typology design of performance metrics to measure errors in machine learning regression algorithms,” Interdiscip. J. Information, Knowledge, Manag., vol. 14, pp. 45–76, 2019, doi: 10.28945/4184.

D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, pp. 1–24, 2021, doi: 10.7717/PEERJ-CS.623.

E. A. Storey, K. R. Lee West, and D. A. Stow, “Utility and optimization of LANDSAT-derived burned area maps for southern California,” Int. J. Remote Sens., vol. 42, no. 2, pp. 486–505, 2021, doi: 10.1080/01431161.2020.1809741.

J. Li, R. Sun, T. Liu, W. Xie, and L. Chen, “Prediction models of urban heat island based on landscape patterns and anthropogenic heat dynamics,” Landsc. Ecol., vol. 36, no. 6, pp. 1801–1815, 2021, doi: 10.1007/s10980-021-01246-2.

Published

2024-12-31

How to Cite

[1]
Y. Miftachul Arif, S. A. Rohma, H. Nurhayati, T. Kusumadewi, F. Nugroho, and A. F. Karami, “Improving Urban Heat Island Predictions Based on Support Vector Regression and Multi-Sensor Remote Sensing: A Case Study in Malang City”, Register: Jurnal Ilmiah Teknologi Sistem Informasi, vol. 10, no. 2, Dec. 2024.

Issue

Section

Article