Soil salinization is a pervasive global issue, particularly in semi-arid and dry areas. It constitutes the primary cause of soil degradation, significantly impairing soil functionality and agricultural productivity. Consequently, there is a pressing need for precise procedures to measure soil salinity in various areas, which are necessary for managing, correcting, monitoring, and utilizing saline soils effectively. This study employed remote sensing (RS) techniques as a robust approach for constructing predictive models of soil salinity by examining changes in soil salinity using different salinity indices and comparing them with electrical conductivity (EC) measurements for soil samples. Among the five salinity indices evaluated, the study identifies soil salinity (SI2) as the most accurate index that reflects Iraqi soil conditions. Consequently, the regression equations model is leveraged to predict the EC compatible with various soil types. Thus, the accuracy was increased by combining ground-truthing and sophisticated Remote sensing (RS). Land Surface Temperature (LST) and Normalized Difference Vegetation Index (NDVI) were calculated to study the relationship between them and soil salinity. It was found that LST changed during the study period at a rate of 61.3±2.8 and 99.8±1.9 for Baghdad and Basrah, respectively. The relationship between LST and salinity exhibits a weak correlation, indicating that temperature is not the primary factor contributing to the increase in soil salinity. This study highlights the potential of remote sensing in refining soil salinity prediction models. These realizations were used to build practical plans to mitigate the effects of soil salinity on agriculture and the surrounding ecosystem.
