Mapping of Soil Salinity in Absheron Soil Based on SENTINEL-2 Using LightGBM

Abstract

This paper reflects the results of assessing the degree of salinity of Absheron soils based on remote sensing technologies. The research was conducted in Sumgayit, Guzdek down station, and Yashma districts located in Absheron region of Azerbaijan. Certain areas of the Absheron region are ecologically clean areas with high tourism potential in the future. Classification of soils by salinity degree was performed using indices calculated from data in Sentinel-2 spectral channels. Previously obtained field measurements and ground observations using LightGBM machine learning algorithm were used to confirm the degree of soil salinization in the areas identified on satellite images. Based on a comparative analysis of machine learning and remote sensing methods, it was found that they provide similar results for soil salinity assessment when the study area does not cover a large area of land. This work has important implications for understanding soil salinity dynamics and could be used in further research on land and agricultural management at the regional level. For a country like Azerbaijan, the result obtained by the staff of the Soil Institute is of a local nature.