This study delineates Groundwater Potential Zones (GWPZs) in the Mahi River Basin (MRB), where increasing groundwater stress is driven by urbanization, intensive agriculture, and limited recharge. Ten predictive factors: geology, geomorphology, slope, lineament density, drainage density, land use/land cover (LULC), Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Normalized Difference Water Index (NDWI), and Toposoil Grain Size Index (TGSI), were derived from multisource satellite imagery (Landsat 8 OLI/TIRS, Sentinel-2, SRTM DEM) and field observations. An Artificial Neural Network (ANN) model assigned nonlinear contribution weights to these inputs and generated a GWPZ map with five classes: Very Good (5.24%), Good (16.35%), Moderate (29.89%), Poor (30.88%), and Very Poor (17.64%). Model performance was validated quantitatively using the Area Under the ROC Curve (AUC = 0.850). Additional validation using 350 well locations showed strong spatial correspondence between predicted zones and groundwater depth. The Kruskal–Wallis H test (H = 42.87, p < 0.001) confirmed significant hydrogeological differences among ANN-predicted classes, while Moran’s I (0.037, p = 0.46) demonstrated spatial independence of prediction residuals. More than 62% of the basin falls within Moderate to Very Poor zones, emphasizing the need for strategic groundwater recharge planning. The integration of ANN with remote sensing and GIS offers a robust, data-driven model for sustainable groundwater resource management in semi-arid and data-poor regions.
A new study published in Scientific Reports presents a novel framework for mapping groundwater potential by integrating geospatial techniques with Artificial Neural Networks (ANN). Conducted in the Mahi River Basin (MRB) of western India—a region facing significant stress from over-extraction—the research addresses the critical need for precise groundwater assessment to guide sustainable management.
Researchers utilized ten key predictive factors influencing groundwater dynamics: geology, geomorphology, slope, lineament density, drainage density, land use/land cover (LULC), and four spectral indices—Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Normalized Difference Water Index (NDWI), and Toposoil Grain Size Index (TGSI). These layers were derived from multi-source satellite data (Landsat 8, Sentinel-2, SRTM DEM) and integrated within a GIS environment. A feedforward ANN model was developed to process these non-linear relationships. The model architecture featured an input layer with ten neurons (one for each factor), two hidden layers (32 and 16 neurons), and an output layer with five neurons using a Softmax function to classify pixels into five GWPZ categories: Very Good, Good, Moderate, Poor, and Very Poor. The model was trained on 70% of the data, with the remainder used for validation and testing.
The resultant GWPZ map shows that only 21.44% of the MRB area comprises 'Good' to 'Very Good' potential zones, while a concerning 62.08% falls into 'Moderate' to 'Very Poor' categories. Spatial analysis indicates that high-potential zones are primarily associated with gentle slopes, fractured rock formations with high lineament density, and agricultural lands. In contrast, steep slopes, urban areas, and impermeable surfaces correlate with poor potential.
The model's performance was rigorously validated. Quantitative validation using the Area Under the Receiver Operating Characteristic Curve yielded an AUC score of 0.850, indicating excellent predictive accuracy. Spatial validation using 350 well locations showed a strong correlation: shallower water tables were predominantly found in predicted 'Good' and 'Very Good' zones. Statistical tests, including the Kruskal-Wallis H test, confirmed significant differences in actual groundwater depths across the five ANN-predicted classes, reinforcing the model's hydrogeological validity.
The study concludes that the ANN-based approach, leveraging freely available satellite data, offers a superior, objective, and scalable alternative to traditional methods like the Analytic Hierarchy Process (AHP). This framework is particularly valuable for data-scarce regions, providing a critical tool for policymakers to identify recharge zones, prioritize conservation efforts, and promote sustainable groundwater extraction. The methodology directly supports the United Nations Sustainable Development Goals (SDGs), particularly Goal 6 (Clean Water and Sanitation), by enhancing water security in vulnerable semi-arid regions.
Sources:
Scientific Reports
https://www.nature.com/articles/s41598-025-31640-8 .
Provided by the IKCEST Disaster Risk Reduction Knowledge Service System
Comment list ( 0 )
