Copy of 2420095_01-.xlsx

As a type of land degradation, desertification is a crucial phenomenon that negatively impacts the environment and threatens life on Earth. The desertification processes effectively influence the arid and semiarid regions and decrease the land's efficiency with increment speeds. Therefore, recognizing this phenomenon is very important. This study was conducted in The Sistan Plain, Iran, to monitor and forecast desertification using remote sensing-based indices, including land use and land cover (LULC) map, normalized differential vegetation index (NDVI), improved vegetation index (EVI), vegetation condition index (VCI), surface temperature condition index (TCI), modified normalized differential water level index (MNDWI) and salinity index (SI). In addition to satellite data, environmental indices, including standardized precipitation index (SPI) and streamflow drought index (SDI), were used. Satellite data of the study consisted of Landsat 5, and 8 images were taken in June each year over the ten years (1990-2020). Helping to comprehend the ecosystem's mechanisms and alterations before it gets irreversible, monitoring desertification is the most effective way to assess desertification processes. Because using different classification methods with the same data will yield different results, selecting an appropriate method for classifying remote sensing indices for monitoring desertification is necessary. Therefore, correct scientific assessment is required to classify the obtained results. On the other hand, the random forest (RF) method and the mixed model of automated cells and Markov chain (CA-Markov) were used to monitor desertification quantitatively and to predict the desertification condition in 2030, respectively.