Monitoring the dynamics of irrigated parcels and impacts on phreatic water quality in the Mostaganem Plateau (northwestern Algeria): an integrated analysis using remote sensing and field data for 2010 and 2020.

Since the early 2000s, Algeria has implemented several agricultural policies to expand its irrigated areas and enhance its national food security. While these efforts have significantly increased irrigated land, they have raised concerns about groundwater sustainability. The study examines the impact of changes in irrigated parcels (IPs) between 2010 and 2020 on groundwater quality on the Mostaganem Plateau, an area of intense agricultural activity. Using Landsat satellite data and a range of spectral indices, including the Soil-Adjusted Vegetation Index (SAVI), Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Moisture Stress Index (MSI), and Chlorophyll Index Green (CIG), we have mapped the IPs and tracked their changes over time. The results based on a SAVI 0.38 threshold showed a net increase of 690 hectares. This result was validated by a machine learning method based on a support vector machine (SVM) algorithm with a high accuracy of 98% compared to the index method. Groundwater quality analyses revealed higher nitrate concentrations (up to 50 mg/L), while the salinity decreased significantly from 3650 to 1265. This improvement is attributed to more sustainable practices, such as drip irrigation and composting, along with improved rainfall conditions observed since 2005, as indicated by the Standardized Precipitation Index (SPI). This study underscores the value of integrating remote sensing and field data to monitor agricultural expansion and inform sustainable groundwater management in semi-arid regions.