In recent years removing environmental pollution has become one of the main concerns of human life. Air quality in cities depends on weather conditions and the amount of pollutants produced. Today, air pollution is one of the most complex problems of human societies, which has left many negative effects on the health of living beings, especially humans. In this research, the average monthly and annual concentrations of air contaminators in the air pollution measurement stations of the General Directorate of Environmental Protection of Tehran province in the years 2013 to 2019 were examined. By using google earth engine site [1].  Processes that GEE (Google Earth Engine) contains a consolidated resource of open-access RS (Remote Sensing) datasets, along with a variety of algorithms to extract information for Earth’s surface monitoring [2], and using maximum likelihood classification method it recognized that examining the spatial changes of pollutants in the areas where there was more construction, the amount of contaminators was also higher. In terms of time, however, no special changes have been observed for all gases. For AI (Aerosol Index) pollutant, no very specific changes were observed within the region. We have seen a growing trend for carbon monoxide pollutant. For the nitrogen oxide pollutant, we have not seen any growth during this period of time. For sulfur dioxide, we have seen a growing trend. Also, in terms of seasonal changes, air pollutants are more concentrated in winter.

With more than 50 years of proximity to Tehran metropolis, the Kehrizak waste center has had destructive effects on the environment with the development of Tehran and the significant increase in waste production, including the change of land use units that are always affected by natural events, human actions, social issues and Economic. In this research, using Landsat 8 satellite images and remote sensing technique, the land use changes of Kahrizek waste center in thematic maps that are more accessible to users. Five vegetation indices NDVI, EVI, SAVI, LAI and VCI and six supervised classifications are investigated. Several methods were evaluated, parameters of overall accuracy and kappa coefficient. For this research, 4 classes of soil, water, building (urban area) and agricultural land were selected, and the results showed that the maximum likelihood classification method was the best method with an overall accuracy of 90.99% and a kappa coefficient of 0.85 and high similarity. Then, using the maximum likelihood classification method as the most accurate method, a user map was prepared from all images from 2011 to 2022. After calculating the area of ​​the floors, the results showed that the area of ​​the building floor increased by 71% and the area of ​​the agricultural land floor decreased by 80%.