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 to agriculture on a regional and global scale. Soil salinization caused by natural and anthropogenic factors is an essential environmental hazard, especially in arid and semi-arid regions of the world. Detection and monitoring of salinity are critical to the sustainability of soil management. In this study, we compared the performance of non-linear machine learning models to produce spatial maps of electrical conductivity (EC) (as a proxy for salinity) in an alluvial irrigation plain. The study area is located in the Isparta province (100 km2), land cover is mainly irrigated, and dominant soils are Inceptisols (almost 52.46%), Mollisols (20.11 %) and Vertisols (12.06%). Digital soil mapping (DSM) methodology was used,together with plant and soil-based indices produced from the Sentinel 2A satellite image, Digital elevation model (DEM), derived topographic indices, and CORINE land cover classes were used as predictors. The support vector regression (SVR) algorithm revealed the best relationships in the study area. Considering the estimates of different algorithms, according to the FAO salinity classification, a minimum of 12.36% and a maximum of 20.19% of the study area can be classified as slightly saline. The low spatial dependence between model residuals limited the success of hybrid methods. The land irrigated cover played a signif-icant role in predicting the current level of EC.

KAYA Fuat;  SCHILLACI Calogero;  KESHAVARZI Ali;  BAŞAYIĞIT Levent; 

2023-02-21

MDPI

JRC130681

2073-445X (online),   

https://www.mdpi.com/2073-445X/11/12/2148,    https://publications.jrc.ec.europa.eu/repository/handle/JRC130681,   

10.3390/land11122148 (online),