HWR/
Articles/
2512002701
  • Open Access
  • Article

AI-Driven Analysis of Saltwater Intrusion Vulnerability

  • Vahid Nourani *,   
  • Elnaz Bayat Khajeh,   
  • Sana Maleki,   
  • Nardin Jabbarian Paknejhad,   
  • Elnaz Sharghi

Received: 04 Aug 2025 | Revised: 30 Dec 2025 | Accepted: 31 Dec 2025 | Published: 09 Jan 2026

Abstract

Evaluating groundwater salinity is crucial, particularly in arid and semi-arid regions where access to fresh water is essential for various needs. In this study, the GALDIT method, which uses expert judgment to score six key parameters to assess vulnerability to seawater intrusion (SWI), was utilized to evaluate the susceptibility of the Salmas and Urmia aquifers. However, depending on expert judgment may lead to subjectivity and potential bias in assessing vulnerability. To address these limitations, different artificial intelligence-based models were applied to enhance model performance. In the Urmia aquifer, the vulnerability index obtained by GALDIT varied from 3.8 to 6.8, and in the Salmas aquifer, it ranged from 4.3 to 7.8. The difference in the GALDIT vulnerability index ranges primarily reflects distinct hydrogeological conditions in each area. A qualitative comparison between the GALDIT index maps and the observed Electrical Conductivity (EC) distribution highlighted notable spatial mismatches, suggesting that the GALDIT index alone may not fully capture the spatial variability of salinity levels. To assess vulnerability using AI-based models, parameters of GALDIT index were used as input, while observed EC values, as effective salinity indicators, were used as the model outputs. The results showed that all AI-based models outperformed the conventional, expert-based GALDIT index in predicting aquifer vulnerability. While the GALDIT model demonstrated limited correspondence with observed salinity patterns, the AI-based models—especially BO-ELM and Integrated Ensemble—provided significantly improved predictions. These models achieved the highest accuracy in both Urmia and Salmas Plains, with DC values approaching 0.99–1.0 and substantially reduced RMSE, effectively capturing the complex spatial variability of salinity in the aquifers. Although the proposed framework is demonstrated using the Urmia and Salmas aquifers, the methodology is transferable and can be applied to other coastal aquifers with similar hydrogeological settings through site-specific recalibration, provided sufficient data are available. 

References 

  • 1.

    Carreira, P.M.; Marques, J.M.; Nunes, D. Source of groundwater salinity in coastline aquifers based on environmental isotopes (Portugal): Natural vs. human interference. A review and reinterpretation. Appl. Geochem. 2014, 41, 163–175.

  • 2.

    Javadi, S.; Kardan Moghaddam, H.; Neshat, A. A new approach for vulnerability assessment of coastal aquifers using combined index. Geocarto Int. 2022, 37, 1681–1703.

  • 3.

    Aslam, R.A.; Shrestha, S.; Pandey, V.P. Groundwater vulnerability to climate change: A review of the assessment methodology. Sci. Total Environ. 2018, 612, 853–875.

  • 4.

    Machiwal, D.; Jha, M.K.; Singh, V.P.; et al. Assessment and mapping of groundwater vulnerability to pollution: Current status and challenges. Earth-Sci. Rev. 2018, 185, 901–927.

  • 5.

    Shirazi, S.M.; Imran, H.M.; Akib, S.; et al. Groundwater vulnerability assessment in the Melaka State of Malaysia using DRASTIC and GIS techniques. Environ. Earth Sci. 2013, 70, 2293–2304.

  • 6.

    Liggett, J.E.; Talwar, S. Groundwater Vulnerability Assessments and Integrated Water Resource Management. Streamline Watershed Manag. Bull. 2009, 13, 18–29.

  • 7.

    Taghavi, N.; Niven, R.K.; Paull, D.J.; et al. Groundwater vulnerability assessment: A review including new statistical and hybrid methods. Sci. Total Environ. 2022, 822, 153486.

  • 8.

    Mogaji, K.A.; Lim, H.S.; Abdullah, K. Modeling groundwater vulnerability prediction using geographic information system (GIS)-based ordered weighted average (OWA) method and DRASTIC model theory hybrid approach. Arab. J. Geosci. 2014, 7, 5409–5429.

  • 9.

    Nourani, V.; Khajeh, E.B.; Paknezhad, N.J.; et al. Temporal evaluation of seawater intrusion vulnerability in Shabestar Plain using GALDIT and AI techniques. Environ. Sci. Pollut. Res. 2025, 32, 10855–10876.

  • 10.

    Aller, L.; Bennett, T.; Lehr, J.H.; et al. DRASTIC: A standardized system for evaluating groundwater pollution potential using hydrogeologic setting. J. Geol. Soc. India 1987, 29, 23–37.

  • 11.

    Chachadi, A.G.; Lobo Ferreira, J.P.C. Sea Water Intrusion Vulnerability Mapping of Aquifers Using the GALDIT Method. 2001. Available online: https://repositorio.lnec.pt/jspui/handle/123456789/5798 (accessed on 12 September 2025).

  • 12.

    Civita, M. Le carte Della Vulnerabilità Degli Acquiferi All’inquinamento; Teoria e pratica; Pitagora Press: Bologna, Italy, 1994; p. 325.

  • 13.

    Stempvoort, D.V.; Ewert, L.; Wassenaar, L. Aquifer vulnerability Index: A GIS-compatible method for groundwater vulnerability mapping. Can. Water Resour. J. 1993, 18, 25–37.

  • 14.

    Emara, S.R.; Armanuos, A.M.; Shalby, A. Appraisal seawater intrusion vulnerability for the Moghra coastal aquifer, Egypt–application of the GALDIT index, sensitivity analysis, and hydro-chemical indicators. Groundw. Sustain. Dev. 2024, 25, 101166.

  • 15.

    Chang, S.W.; Chung, I.M.; Kim, M.G.; et al. Application of GALDIT in assessing the seawater intrusion vulnerability of Jeju Island, South Korea. Water 2019, 11, 1824.

  • 16.

    Ghorai, D.; Bhunia, G.S.; Shit, P.K. Coastal aquifer vulnerability for saltwater intrusion: A case study of Chennai Coast using GALDIT model and geoinformatics. In Groundwater and Society; Shit, P.K., Bhunia, G.S., Adhikary, P.P., et al., Eds.; Springer International Publishing: Cham, Switzerland, 2021; pp. 349–362. https://doi.org/10.1007/978-3-030-64136-8_16.

  • 17.

    Pisciotta, A.; Suozzi, E.; Tiwari, A.K. A modified GALDIT-NUTS index to assess Favignana Island aquifer vulnerability. Geocarto Int. 2022, 37, 11706–11731.

  • 18.

    Idowu, T.E.; Jepkosgei, C.; Nyadawa, M.; et al. Integrated seawater intrusion and groundwater quality assessment of a coastal aquifer: GALDIT, geospatial and analytical approaches. Environ. Sci. Pollut. Res. 2022, 29, 36699–36720.

  • 19.

    Nguyen, A.H.; Pham, K.Q.; Le, Q.H. Assessment of Pleistocene Aquifer Vulnerability to Saline Intrusion in the Coastal Region of Ba Ria-Vung Tau Province Using GIS and Entropy-GALDIT. Sustainability. 2023, 15, 8107.

  • 20.

    Goswami, S.; Rai, A.K. Identifying intrusion of seawater in coastal aquifers by modified GALDIT (M-GALDIT) index. Groundw. Sustain. Dev. 2024, 25, 101173.

  • 21.

    Nourani, V.; Najafi, H.; Maleki, S.; et al. Z-number based assessment of groundwater vulnerability to seawater intrusion. J. Hydrol. 2024, 632, 130859.

  • 22.

    Torkashvand, M.; Neshat, A.; Javadi, S.; et al. New hybrid evolutionary algorithm for optimizing index-based groundwater vulnerability assessment method. J. Hydrol. 2021, 598, 126446.

  • 23.

    Moazamnia, M.; Hassanzadeh, Y.; Nadiri, A.A.; et al. Vulnerability indexing to saltwater intrusion from models at two levels using artificial intelligence multiple model (AIMM). J. Environ. Manag. 2020, 255, 109871.

  • 24.

    Barzegar, R.; Razzagh, S.; Quilty, J.; et al. Improving GALDIT-based groundwater vulnerability predictive mapping using coupled resampling algorithms and machine learning models. J. Hydrol. 2021 Jul; 598:126370.

  • 25.

    Bordbar, M.; Neshat, A.; Javadi, S.; et al. Improving the coastal aquifers’ vulnerability assessment using SCMAI ensemble of three machine learning approaches. Nat. Hazards 2022, 110, 1799–1820.

  • 26.

    Gharekhani, M.; Nadiri, A.A.; Khatibi, R.; et al. A study of uncertainties in groundwater vulnerability modelling using Bayesian model averaging (BMA). J. Environ. Manag. 2022, 303, 114168.

  • 27.

    Aryafar, A.; Khosravi, V.; Zarepourfard, H.; et al. Evolving genetic programming and other AI-based models for estimating groundwater quality parameters of the Khezri plain, Eastern Iran. Environ. Earth Sci. 2019, 78, 69.

  • 28.

    Sadikoglu, F.; Nourani, V.; Maleki, S.; et al. Application of Artificial Neural Network to Improve DRASTIC-Based Groundwater Vulnerability Assessment. In Proceedings of the 12th World Conference “Intelligent System for Industrial Automation” (WCIS-2022), Tashkent, Uzbekistan, 25–26 November 2022; Volume 718, pp. 273–281. https://doi.org/10.1007/978-3-031-51521-7_35.

  • 29.

    Shahbazi, A.; Aydin, Y.; Semiz, G.D.; et al. The compounding effects of agricultural expansion and snow drought on Lake Urmia’s drying crisis. Sci. Rep. 2025, 15, 38132.

  • 30.

    Chachadi, A.G.; Lobo Ferreira, J.P. Assessing aquifer vulnerability to seawater intrusion using the GALDIT method: Part 2—GALDIT indicators description. In Proceedings of the Fourth Inter-Celtic Colloquium on Hydrology and Management of Water Resources, Guimarães, Portugal, 11–14 July 2005. Available: https://www.aprh.pt/celtico/PAPERS/26.PDF (accessed on 22 November 2025).

  • 31.

    Fakhri, M.; Moghaddam, A.A.; Nadiri, A.A.; et al. Incorporating hydraulic gradient and pumping rate into GALDIT framework for salinity hazard assessment in coastal aquifers: A case study of Urmia Plain, Iran. Research Square 2024, https://doi.org/10.21203/rs.3.rs-4186756/v.

  • 32.

    Ghorbani, A.; Abbas Novinpour, E.; Ahangari, M. Identification of land subsidence areas in Salmas Plain using GARDLIF framework and learning machines. Hydrogeology 2025, in press. https://doi.org/10.22034/hydro.2025.56975.1296.

  • 33.

    Hemmati, F.; Khanri, S.; Alizadeh, A. Assessment of land subsidence variations in the Urmia Plain aquifer using differential interferometric synthetic aperture radar (DInSAR). J. Hydrogeomorphol. 2025. https://doi.org/10.22034/hyd.2025.67902.1798.

  • 34.

    Sheikholeslami, R.; Jahangiri, F. An uncertainty-informed water quality index: Incorporation of data uncertainty into water quality assessment. Environ. Model. Softw. 2026, 196, 106760.

  • 35.

    Sundaram, V.L.K. Vulnerability assessment of seawater intrusion and effect of artificial recharge in Pondicherry coastal region using GIS. Indian. J. Sci. Technol. 2008, 1, 1–7.

  • 36.

    Gupta, T.K.; Raza, K. Optimizing Deep Feedforward Neural Network Architecture: A Tabu Search Based Approach. Neural Process Lett. 2020, 51, 2855–2870.

  • 37.

    Nourani, V. Investigating the Ability of Artificial Neural Network (ANN) Models to Estimate Missing Rain-gauge Data. J. Environ. Inform. 2012, 19, 38–50.

  • 38.

    Nourani, V.; Sayyah Fard, M. Sensitivity analysis of the artificial neural network outputs in simulation of the evaporation process at different climatologic regimes. Adv. Eng. Softw. 2012, 47, 127–146.

  • 39.

    Sharghi, E.; Nourani, V.; Najafi, H.; et al. Emotional ANN (EANN) and Wavelet-ANN (WANN) approaches for Markovian and seasonal based modeling of rainfall-runoff process. Water Resour. Manag. 2018, 32, 3441–3456.

  • 40.

    Fijani, E.; Nadiri, A.A.; Asghari Moghaddam, A.; et al. Optimization of DRASTIC method by supervised committee machine artificial intelligence to assess groundwater vulnerability for Maragheh–Bonab plain aquifer, Iran. J. Hydrol. 2013, 503, 89–100.

  • 41.

    Torres, J.F.; Hadjout, D.; Sebaa, A.; et al. Deep learning for time series forecasting: A survey. Big Data. 2021, 9, 3–21.

  • 42.

    Ketkar, N. Deep Learning with Python; Springer: Berkeley, CA, USA, 2017.

  • 43.

    Lahmiri, S.; Bekiros, S. Deep Learning Forecasting in Cryptocurrency High-Frequency Trading. Cogn. Comput. 2021, 13, 485–487.

  • 44.

    Menares, C.; Perez, P.; Parraguez, S.; et al. Forecasting PM2.5 levels in Santiago de Chile using deep learning neural networks. Urban. Clim. 2021, 38, 100906.

  • 45.

    Amirshahi, B.; Lahmiri, S. Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrencies. Mach. Learn. Appl. 2023, 12, 100465.

  • 46.

    Behfar, N.; Booij, M.J.; Nourani, V. Assessing rainfall-runoff models for climate change: Simple and differential split-sample tests for conceptual and artificial intelligence models. Hydrol. Sci. J. 2024, 69, 861–877.

  • 47.

    Jang, J.S.R. ANFIS: Adaptive-network-based fuzzy inference system. IEEE Trans. Syst. Man. Cybern. 1993, 23, 665–685.

  • 48.

    Jang, J.S.R.; Sun, C.T.; Mizutani, E. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence; Prentice Hall: Upper Saddle River, NJ, USA, 1997.

  • 49.

    Vapnik, V.N. Statistical learning theory. New York: Wiley; 1998.

  • 50.

    Smola, A.J.; Schölkopf, B. A tutorial on support vector regression. Stat. Comput. 2004, 14, 199–222.

  • 51.

    Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn. 1995, 20, 273–297.

  • 52.

    Sharghi, E.; Nourani, V.; Behfar, N. Earthfill dam seepage analysis using ensemble artificial intelligence based modeling. J. Hydroinform. 2018, 20, 1071–1084.

  • 53.

    Huang, G.B.; Zhu, Q.Y.; Siew, C.K. Extreme learning machine: Theory and applications. Neurocomputing 2006, 70, 489–501.

  • 54.

    Huang, G.B.; Zhou, H.; Ding, X.; et al. Extreme learning machine for regression and multiclass classification. IEEE Trans. Syst. Man. Cybern. B Cybern. 2012, 42, 513–529.

  • 55.

    Mockus, J. On Bayesian methods for seeking the extremum. In IFIP Technical Conference on Optimization Techniques; Springer: Berlin/Heidelberg, Germany, 1974; pp. 400–404.

  • 56.

    Shahriari, B.; Swersky, K.; Wang, Z.; et al. Taking the human out of the loop: A review of Bayesian optimization. Proc. IEEE. 2016, 104, 148–175.

  • 57.

    Doveton, J.H. A Course on Log Analysis: Remote Sensing in the Subsurface. J. Geol. Educ. 1978, 26, 22–26.

  • 58.

    Amoozegar, A.; Warrick, A.W. Hydraulic Conductivity of Saturated Soils: Field Methods. In SSSA Book Series; Klute, A., Ed.; Soil Science Society of America: Madison, WI, USA; American Society of Agronomy: Madison, WI, USA, 2018; pp. 735–770. https://doi.org/10.2136/sssabookser5.1.2ed.c29.

  • 59.

    Boulton, N. The drawdown of the water-table under non-steady conditions near a pumped well in an unconfined formation. J. Proc. Inst. Civ. Eng. 1954, 3, 564–579.

  • 60.

    Huan, H.; Wang, J.; Teng, Y. Assessment and validation of groundwater vulnerability to nitrate based on a modified DRASTIC model: A case study in Jilin City of northeast China. Sci. Total Environ. 2012, 440, 14–23.

  • 61.

    Nakhaei, M.; Vadiati, M.; Mohammadi, K. Evaluation of vulnerability of Urmia Lake saline water intrusion to coastal aquifer using GALDIT model. Geosciences 2015, 24, 51–64.

  • 62.

    Azizi Mobaser, J.; Masud Lak, M.; Rasoulzadeh, A. Evaluation of intrinsic vulnerability of Urmia plain groundwater pollution using original DRASTIC and DRASTIC modified models. Iran-Water Resour. Res. 2019, 14, 220–235.

  • 63.

    Maleki, S.; Nourani, V.; Najafi, H.; et al. Z-numbers based novel method for assessing groundwater specific vulnerability. Eng. Appl. Artif. Intell. 2023, 122, 106104.

  • 64.

    Amiri, V.; Nakhaei, M.; Lak, R.; et al. Geophysical, isotopic, and hydrogeochemical tools to identify potential impacts on coastal groundwater resources from Urmia hypersaline Lake, NW Iran. Environ. Sci. Pollut. Res. 2016, 23, 16738–16760.

Share this article:
Download PDF
DOI
10.53941/hwr.2026.100004
Issue
Volume 1, Issue 1
How to Cite
Nourani, V.; Khajeh, E. B.; Maleki, S.; Paknejhad, N. J.; Sharghi, E. AI-Driven Analysis of Saltwater Intrusion Vulnerability. Hydrology and Water Resources 2026, 1 (1), 4. https://doi.org/10.53941/hwr.2026.100004.
RIS
BibTex
Copyright & License
article copyright Image
Copyright (c) 2026 by the authors.