PERFORMANCE EVALUATION OF MACHINE LEARNING ALGORITHMS FOR MONITORING CONSTRUCTION DYNAMICS IN ESTERN HO CHI MINH CITY
Keywords
DOI:
https://doi.org/10.34238/tnu-jst.15597Abstract
This study evaluates the performance of machine learning algorithms, including Support Vector Machine, Random Forest, and Classification and Regression Trees, for monitoring construction dynamics in Eastern Ho Chi Minh City, during the period 2018-2024. Sentinel-2 satellite image time series were leveraged on the Google Earth Engine cloud computing platform to develop an automated quarterly data processing workflow. The methodology integrates the Grid Search hyperparameter optimization technique with the Wilcoxon non-parametric statistical test to ensure an objective model evaluation. Results indicate that the Support Vector Machine algorithm using the Radial Basis Function kernel achieved optimal performance, with an average overall accuracy of 84.62% and a Kappa coefficient of 0.7806, significantly outperforming the other two algorithms statistically. Change detection analysis reveals a robust expansion of construction land along major transportation axes; however, the monitoring process was considerably affected by cloud cover interference during the Southern rainy season. The study affirms that applying machine learning on big data platforms provides timely and accurate information for urban management.Downloads
References
Vietnam National Assembly, “Law on Construction No. 135/2025/QH15 dated December 10, 2025,” (in Vietnamese), 2025.
M. Pesaresi et al., “A global human settlement layer from optical HR/VHR RS data: concept and first results,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 6, no. 5, pp. 2102-2131, 2013.
P. Gong et al., “Annual maps of global artificial impervious area (GAIA) between 1985 and 2018,” Remote Sens. Environ., vol. 236, 2020, Art. no. 111510.
C. Kontgis, A. Schneider, J. Fox, S. Saksena, J. H. Spencer, and M. Castrence, “Monitoring peri-urbanization in the greater Ho Chi Minh City metropolitan area,” Appl. Geogr., vol. 53, pp. 377-388, 2014, doi: 10.1016/J.APGEOG.2014.06.029.
D. Wen et al., “Change Detection From Very-High-Spatial-Resolution Optical Remote Sensing Images: Methods, applications, and future directions,” IEEE Geosci. Remote Sens. Mag., vol. 9, no. 4, pp. 68-101, 2021.
Ho Chi Minh City Statistics Department, Statistical Yearbook 2024, (in Vietnamese), Ho Chi Minh City General Publishing House, 2025.
People’s Committee of Thu Duc City, Decision No. 6101/QD-UBND dated October 21, 2021, approving the Project “Building a smart city and digital transformation in Thu Duc City in the period 2021 – 2025,” (in Vietnamese), 2021.
S. Abdikan, F. B. Sanli, M. Ustuner, and F. Calò, “Land cover mapping using Sentinel-1 SAR data,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., vol. XLI-B7, pp. 757-761, 2016.
X. Sang et al., “Intensity and Stationarity Analysis of Land Use Change Based on CART Algorithm,” Sci. Rep., vol. 9, no. 1, 2019, Art. no. 12279.
N. Kranjčić, D. Medak, R. Župan, and M. Rezo, “Support Vector Machine Accuracy Assessment for Extracting Green Urban Areas in Towns,” Remote Sens., vol. 11, no. 6, 2019, Art. no. 655.
J. Biswas, M. A. Jobaer, S. F. Haque, M. S. Islam Shozib, and Z. A. Limon, “Mapping and monitoring land use land cover dynamics employing Google Earth Engine and machine learning algorithms on Chattogram, Bangladesh,” Heliyon, vol. 9, no. 11, 2023, Art. no. e21245, doi: 10.1016/J.HELIYON.2023.E21245.
V. T. Nguyen, X. T. Tran, N. H. Nguyen, and T. N. Le, “Research applications of specification and GIS process assessment urbanisation of Phu Ly City, Ha Nam province,” (in Vietnamese), J. Geod. Cartogr., no. 56, pp. 42-50, 2023.
T. H. T. Nguyen, T. T. Dang, T. S. M. Pham, and T. T. H. Ha, “Research classification of land use - land cover from Sentinel-2 satellite images based on the SVM algorithm,” (in Vietnamese), J. Sci. Nat. Resour. Environ., no. 45, pp. 74-82, 2023.
J. W. Rouse, R. H. Haas, J. A. Schell, and D. W. Deering, “Monitoring Vegetation Systems in the Great Plains with ERTS,” in Third ERTS-1 Symposium, Washington DC, USA: NASA, 1974, pp. 309-317.
Y. Zha, J. Gao, and S. Ni, “Use of normalized difference built-up index in automatically mapping urban areas from TM imagery,” Int. J. Remote Sens., vol. 24, no. 3, pp. 583-594, 2003.
A. Rikimaru, P. S. Roy, and S. Miyatake, “Tropical Forest Cover Density Mapping,” Int. Soc. Trop. Ecol., vol. 43, no. 1, pp. 39-47, 2002.
H. Xu, “Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery,” Int. J. Remote Sens., vol. 27, no. 14, pp. 3025-3033, 2006.
R. G. Congalton, “A review of assessing the accuracy of classifications of remotely sensed data,” Remote Sens. Environ., vol. 37, no. 1, pp. 35-46, 1991, doi: 10.1016/0034-4257(91)90048-B.
DemšarJanez, “Statistical Comparisons of Classifiers over Multiple Data Sets,” J. Mach. Learn. Res., vol. 7, pp. 1-30, 2006.
A. Cutler, D. R. Cutler, and J. R. Stevens, “Random Forests,” in Ensemble Machine Learning, C. Zhang and Y. Q. Ma, Eds., New York, NY: Springer, 2012, pp. 157-175.
