Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Sep 8;197(10):1090.
doi: 10.1007/s10661-025-14554-w.

Delineation of groundwater potential zones using data-driven approaches: towards achieving sustainable groundwater management in drought-prone region of Eastern India

Asish Saha  1 , Subodh Chandra Pal  2
Affiliations

Delineation of groundwater potential zones using data-driven approaches: towards achieving sustainable groundwater management in drought-prone region of Eastern India

Asish Saha et al. Environ Monit Assess. .

Abstract

To a large extent, the food security and ecological balance of a region, particularly in agriculturally dominated areas, largely depend on the sustainable use and management of groundwater resources. However, in recent times, both natural and human-driven factors have heavily impacted the lowering of groundwater resources. Therefore, the present study has been carried out in a drought-prone region of Birbhum district, part of the red-lateritic agro-climatic zone of West Bengal, Eastern India, to delineate groundwater potential zones (GWPZs). In this regard, 12 hydrological and environmental factors were selected after a multicollinearity test, i.e., elevation, slope, curvature, geomorphology, geology, lineament density, distance from river, topographic wetness index (TWI), groundwater level, rainfall, land use land cover, and soil types for modeling groundwater potentiality. To fulfill the objective, standard machine learning (ML) algorithms like "random forest (RF)," "support vector regression (SVR)," "maximum-entropy (Max-Ent)," and the ensemble approach of RF-Max-Ent have been applied. To validate the obtained result, five statistical techniques, i.e., area under curve (AUC), sensitivity, specificity, F-score, and Kappa coefficient, have been selected. The ranking and relative importance of all factors revealed that elevation, rainfall, TWI, and soil type are the most influential factors for groundwater potentiality in this study. The result of the evaluation metric indicates that the ensemble of RF-Max-Ent is the most suitable model to delineate GWPZ in this study site, as AUC is 0.893 in validation, followed by RF, Max-Ent, and SVR. Additionally, the rank value in the Friedman rank test and chi-squared test for RF-Max-Ent is 3.824 and 32.121, respectively. Overall, the findings revealed that a sizeable section of the study area has moderate to very good groundwater potential. The findings of this study can significantly support achieving sustainable development goals and help to improve groundwater levels in this region through appropriate groundwater policy planning.

Keywords: Data-driven approaches; Drought-prone region; Groundwater potential; Maximum-entropy; Red-lateritic agro-climatic zone.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

References

    1. Agboola, G., Beni, L. H., Elbayoumi, T., & Thompson, G. (2024). Optimizing landslide susceptibility mapping using machine learning and geospatial techniques. Ecological Informatics, 81, Article 102583. https://doi.org/10.1016/j.ecoinf.2024.102583 - DOI
    1. Ahmad, D.M., Kam, J., 2024. Disparity between global drought hazard and awareness. npj Clean Water 7, 1–8. https://doi.org/10.1038/s41545-024-00373-y
    1. Anchima, S. J., Gokul, A., Senan, C. P. C., Danumah, J. H., Saha, S., Sajinkumar, K. S., Rajaneesh, A., Johny, A., Mammen, P. C., & Ajin, R. S. (2023). Vulnerability evaluation utilizing AHP and an ensemble model in a few landslide-prone areas of the Western Ghats, India. Environment, Development and Sustainability. https://doi.org/10.1007/s10668-023-04149-1 - DOI
    1. Arabameri, A., Pal, S. C., Rezaie, F., Nalivan, O. A., Chowdhuri, I., Saha, A., Lee, S., & Moayedi, H. (2021). Modeling groundwater potential using novel GIS-based machine-learning ensemble techniques. Journal of Hydrology: Regional Studies, 36, Article 100848. https://doi.org/10.1016/j.ejrh.2021.100848 - DOI
    1. Armanuos, A. M., Negm, A., Yoshimura, C., & Valeriano, O. C. S. (2016). Application of WetSpass model to estimate groundwater recharge variability in the Nile Delta aquifer. Arabian Journal of Geosciences, 9, 1–14.

MeSH terms

LinkOut - more resources