Search

Modelling approaches are becoming an efficient tool in the forecasting of the salinization spread impact on the local and global scales. In the Lower-Cheliff plain, updating the information on soil salinity expansion is more than required as it continues to damage the agricultural environment in there. Through this study, we adopted an artificial methodology that consists of a combination of buffer analysis using Sentinel-2 data and machine learning modelling to assess their aptitude in the prediction and mapping of soil salinity. The adopted random forest (RF) algorithm included the reflectance information from of the bands from Blue ( ρ B l u e ), Green ( ρ G r e e n ), Red ( ρ R e d ), Near infrared (NIR), Vegetation red-edge (VRE) and Shortwave Infrared (SWIR), optimized with the geospatial buffering based on the 91 soil random samples collected during the summer of 2019 and measured for the Electrical Conductivity (EC) in the laboratory. The outputs from the geospatial buffering refined the goodness of the correlation between field data and the variables set from bands reflectance and selected salinity indices. The obtained coefficient of determination (R2) with Multiple Linear Regression (MLR) and Partial Least Square regression (PLS) models proved an improvement in the multivariable prediction of soil salinity with the optimized Sentinel-2 data (R2 = 0.61 and 0.68 + RMSE of 3.36 and 2.87 dS m−1 respectively), compared to the results from the 2015 multiple regression model, Given the high values of R2 = 0.77 and 0.95 and the low values of RMSE = 2.29 and 1.18 dS m−1 respectively; the RF regressor was very efficient in predicting EC either with all variables or with selected variables from the variable importance measure based on the mean decrease accuracy (MDA). The random forest classifier performed top of the range classification with an overall Accuracy (OA) about 99%, estimating that over 75% of the study area surface is suffering from the salinization extent. [ABSTRACT FROM AUTHOR]

This paper studies the geochemical evolution of the soil solution in contact with water irrigation of a positive residual Alkalinity, in order to predict their salinization path and structural degradation under the effect of water concentration by evaporation. Two soil textures, one equilibrated (S1) and the other is clay (S2), are distributed in pots made by PVC tubes of 5 cm diameter and 12 cm high in the laboratory. The water with a positive residual alkalinity (E: RSC> 0) is brought up to pots till soil is oversaturated then, after 24 hours, the water excess is shipping dry naturally and the soil reaches his retention capacity. The weight difference between the wet pot and the dry one gives the necessary water volume to push the soil into his field capacity. The total evaporation of the brought volume water is the concentration factor (CF). Soil solution contained in the pots is extracted for chemical analysis. Fifteen concentration factors were performed. As far as the waters are concentrated, the calcium and magnesium ions were precipitates and an increase in the sodium molality in the soil solution. The increase of the concentrations factors leads to the desorption of sodium ion to the exchange complex under the effect of depletion of elements with big solubility's (Ca and Mg). It was thus observed an increase in the SAR, especially for clayey soils, which led to the destruction of the structure. [ABSTRACT FROM AUTHOR]