Effect of hydro-geochemical processes and saltwater intrusion on groundwater quality and irrigational suitability assessed by geo-statistical techniques in coastal region of eastern Andhra Pradesh, India

Prediction of soil salinity in the Upputeru river estuary catchment, India, using machine learning techniques

Soil salinization is a widespread phenomenon leading to land degradation, particularly in regions with brackish inland aquaculture ponds. However, because of the high geographical and temporal fluctuation, monitoring vast areas provides substantial challenges. This study uses remote sensing data and machine learning techniques to predict soil salinity. Four linear models, namely linear regression, least absolute shrinkage and selection operator (LASSO), ridge, and elastic net regression, and three boosting algorithms, namely XGB regressor, LightGBM, and CatBoost regressor, were used to predict soil salinity. Cross-validation was performed by splitting the data into 30% for model testing and 70% for model training. Multiple metrics such as determination coefficient (R2), root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) were used to compare the performances of these algorithms. By comparison, the CatBoost regressor model performed better than the other models in both testing (MAE = 0.42, MSE = 0.28, RMSE = 0.53, R2 = 0.92) and training (MAE = 0.49, MSE = 0.36, RMSE = 0.60, R2 = 0.90) phases. Hence, the CatBoost regressor model was recommended for monitoring soil salinity in India's massive inland aquaculture zone.

Effects of Seawater Intrusion on the Groundwater Quality of Multi-Layered Aquifers in Eastern Saudi Arabia

The degradation of groundwater (GW) quality due to seawater intrusion (SWI) is a major water security issue in water-scarce regions. This study aims to delineate the impact of SWI on the GW quality of a multilayered aquifer system in the eastern coastal region of Saudi Arabia. The physical and chemical properties of the GW were determined via field investigations and laboratory analyses. Irrigation indices (electrical conductivity (EC), potential salinity (PS), sodium adsorption ratio (SAR), Na%, Kelly’s ratio (KR), magnesium adsorption ratio (MAR), and permeability index (PI)) and a SWI index (fsea) were obtained to assess the suitability of GW for irrigation. K-mean clustering, correlation analysis, and principal component analysis (PCA) were used to determine the relationship between irrigation hazard indices and the degree of SWI. The tested GW samples were grouped into four clusters (C1, C2, C3, and C4), with average SWI degrees of 15%, 8%, 5%, and 2%, respectively. The results showed that the tested GW was unsuitable for irrigation due to salinity hazards. However, a noticeable increase in sodium and magnesium hazards was also observed. Moreover, increasing the degree of SWI (fsea) was associated with increasing salinity, sodium, and magnesium, with higher values observed in the GW samples in cluster C1, followed by clusters C2, C3, and C4. The correlation analysis and PCA results illustrated that the irrigation indices, including EC, PS, SAR, and MAR, were grouped with the SWI index (fsea), indicating the possibility of using them as primary irrigation indices to reflect the impact of SWI on GW quality in coastal regions. The results of this study will help guide decision-makers toward proper management practices for SWI mitigation and enhancing GW quality for irrigation.