Monitoring land use/cover changes in cities adjacent to environmentally sensitive areas plays a key role in sustainable management. Urmia city, located near Lake Urmia, has experienced rapid growth in recent decades, raising concerns about its environmental consequences. This study aims to monitor the growth changes of Urmia city from 2005 to 2025 using spectral indices and the Support Vector Machine (SVM) algorithm.

Landsat 5 (2005) and Landsat 8 (2015 and 2025) satellite images were obtained from the US Geological Survey. NDVI (vegetation cover), DBSI (bare land), and UI (built up areas) indices were calculated to improve class separation. Image classification was performed using the SVM algorithm with a radial basis function kernel, and its accuracy was evaluated using ground control points.

The results showed that the SVM method performed very well, achieving an overall accuracy of 94% and a Kappa coefficient of 0.91 in 2025. The area of built up land increased from 68.3% in 2005 to 88.5% in 2025. In contrast, vegetation cover decreased from 5.5% to 2.4%, and bare land decreased from 26.2% to 9.1%. The highest urban growth rate occurred in the first period (2005–2015). The spatial pattern of expansion indicated that bare lands in the northwestern, southwestern, and eastern parts of the city were gradually and then completely converted into built up areas.

The continuation of the current sprawl trend, particularly on the city’s eastern front, directly threatens agricultural lands and orchards around Lake Urmia. Therefore, revising urban development plans with priority given to protecting these lands is essential.