District 22 of Tehran, as one of the rapidly developing urban areas, has undergone significant land use changes, making it a critical subject for environmental change studies. This research aimed to analyze and identify environmental and structural changes over the period from 2016 to 2021. Various remote sensing methods were employed, including Change Vector Analysis (CVA), regression techniques, and spectral indices.Satellite data from Sentinel-1 and Sentinel-2 were used in an integrated manner, and textural features were extracted from both optical and radar imagery. The results indicated that data fusion significantly improved classification accuracy: overall accuracy in 2016 reached 91% with a Kappa coefficient of 89%, while in 2021, overall accuracy was 86% with a Kappa coefficient of 85%. In addition to percentage changes in land use classes—construction (13%), vegetation (15%), water resources (4%), and soil (11%)—pixel-level analysis was also conducted. This enabled the identification of both the percentage and number of pixels that changed between different land use classes. For example, in the water class, the largest change was toward soil (18,300 pixels). In the road class, 21,000 pixels remained unchanged, while some transitioned to vegetation, construction, and water. Vegetation showed the highest stability with 158,000 unchanged pixels, although portions were converted to soil and construction. In the soil class, besides 42,000 stable pixels, over 156,000 pixels changed to roads and 12,000 to construction.This detailed analysis allows for more precise identification of change patterns and supports the development of targeted management strategies.