APPLICATION OF REMOTE SENSING DATA IN THE STUDY OF URBANIZATION PROCESSES
Abstract
Today, as the population continues to grow, the process of urbanization is also rapidly developing. The use of remote sensing data in the study of urbanization processes is considered highly effective and convenient.
In this article, maps of cities in the Tashkent region were created based on classification methods. Considering the relatively coarse spatial resolution of the Landsat satellite, samples were taken from raster data. A flowchart of processes using machine learning techniques in remote sensing data analysis was developed.
The results of the study show that changes in Tashkent indicate an active increase in urbanization. Open lands have significantly decreased, suggesting the construction of new buildings and infrastructure. At the same time, less attention has been paid to the preservation or expansion of green areas, reflecting limited efforts to improve the city’s ecology. Moreover, the expansion of the capital’s territory represents a higher level of urbanization, while the total area of green zones has markedly declined. The proportion of tree-covered areas decreased from 19% to 15% over the past 30 years, which in turn indicates a growing scarcity of greenery in the city.
Keywords
Urban, remote sensing, machine learning, classify, satellite images, Tashkent, Angren, forest, agriculture, barren soil, developed land, water.
References
- S. Halder and S. Bose, “Comparative study on remote sensing-based indices for urban ecology assessment: A case study of 12 urban centers in the metropolitan area of eastern India,” J. Earth Syst. Sci., vol. 133, no. 2, p. 100, May 2024, doi: 10.1007/s12040-024-02321-3.
- B. He et al., “Analysis of atmospheric pollution transport using aerosol optical depth remote sensing data and the optical flow method,” Atmospheric Pollut. Res., vol. 16, no. 3, p. 102415, Mar. 2025, doi: 10.1016/j.apr.2025.102415.
- T. Zhang et al., “Adaptability analysis and model development of various LS-factor formulas in RUSLE model: A case study of Fengyu River Watershed, China,” Geoderma, vol. 439, p. 116664, Nov. 2023, doi: 10.1016/j.geoderma.2023.116664.
- H. Tian, C. Xie, M. Zhong, Y. Ye, R. Zhou, and D. Zhao, “Urban tree carbon storage estimation using unmanned aerial vehicles remote sensing,” Urban For. Urban Green., vol. 107, p. 128755, May 2025, doi: 10.1016/j.ufug.2025.128755.
- J. Chang et al., “Estimation of carbon sequestration capacity of urban green infrastructure by fusing multi-source remote sensing data,” Int. J. Appl. Earth Obs. Geoinformation, vol. 141, p. 104643, Jul. 2025, doi: 10.1016/j.jag.2025.104643.