Predictive Mapping of Electrical Conductivity and Assessment of Soil Salinity in a Western Türkiye Alluvial Plain

The increase in soil salinity due to human-induced processes poses a severe threat agriculture on regional and global scale. Soil salinization caused by natural anthropogenic factors is vital environmental hazard, specifically semi-arid arid regions of the world. detection monitoring are critical sustainability management. current study compared performance machine learning models produce spatial maps electrical conductivity (EC) (as proxy for salinity) an alluvial irrigation plain. area located Isparta province (100 km2), land cover mainly irrigated, dominant soils Inceptisols, Mollisols, Vertisols. Digital mapping (DSM) methodology was used, referring digital representation formation with today’s technological advances. Plant soil-based indices produced from Sentinel 2A satellite image, topographic derived elevation model (DEM), CORINE classes were used as predictors. support vector regression (SVR) algorithm revealed best relationships area. Considering estimates different algorithms, according FAO classification, minimum 12.36% maximum 20.19% can be classified slightly saline. low dependence between residuals limited success hybrid methods. irrigated played significant role predicting level EC.