Temporal evaluation of seawater intrusion vulnerability in Shabestar Plain using GALDIT and AI techniques

被引：0
作者：
Vahid Nourani [1 ]
Elnaz Bayat Khajeh [3 ]
Nardin Jabbarian Paknezhad [1 ]
Dominika Dąbrowska [1 ]
Elnaz Sharghi [2 ]
机构：
[1] Center of Excellence in Hydroinformatics, Faculty of Civil Engineering, University of Tabriz, Tabriz
[2] Faculty of Natural Sciences, University of Silesia, Bedzinska 60, Sosnowiec
[3] World Peace University, Sht. Kemal Ali Omer Sok.
来源：
Environmental Science and Pollution Research | 2025年 / 32卷 / 17期
基金：
美国国家科学基金会;
关键词：
Artificial intelligence; Coastal aquifer; GALDIT Index; Groundwater vulnerability; Seawater intrusion; Sensitivity analysis;
D O I：
10.1007/s11356-025-36338-y
中图分类号：
学科分类号：
摘要：
Groundwater contamination, with seawater intrusion (SWI) being the most widespread form particularly in coastal areas, has become a pressing global environmental challenge. Groundwater serves as a vital freshwater resource, particularly in arid and semi-arid regions, making its efficient management essential. In this study, the GALDIT method—an index-based approach that evaluates the vulnerability of aquifers by scoring six key parameters based on expert judgment (groundwater occurrence (G), aquifer hydraulic conductivity (A), groundwater elevation above sea level (L), distance from the shoreline (D), impact of existing seawater intrusion (I), and aquifer thickness (T))—was employed to assess the vulnerability of the Shabestar aquifer to SWI. The study employs the GALDIT method to map aquifer vulnerability for 2002, 2012, and 2022, enabling a temporal comparison of changes over time. The final GALDIT index map, categorized into low, moderate, and high vulnerability classes, revealed an increase in very high vulnerability areas from 10.9% in 2002 to 17.8% in 2022, alongside a decrease in moderate vulnerability areas from 56.4 to 37.3%, indicating a deteriorating condition of the aquifer. However, the reliance on expert judgment introduces potential subjectivity and bias in the vulnerability assessment. To mitigate these limitations, AI-based models, namely artificial neural networks (ANNs) and random forest (RF), were applied to enhance model performance. The GALDIT parameters served as input for the AI models, while observed electrical conductivity (EC), a key indicator of water salinity, and total dissolved solids (TDS), an indicator of drinking water quality, were used as output variables to estimate condition for the year 2022. Results demonstrated that the ANN model outperformed the RF model during verification, improving estimation accuracy by up to 10% and 9% in terms of the determination coefficient (DC), respectively. To further enhance model interpretability and identify the most influential parameters for EC and TDS estimation, a global, variance-based sensitivity analysis using the Sobol method was conducted. This analysis revealed that factors I and D were the most influential for EC, while factors I and T had the greatest impact on TDS in the study region. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.
引用
收藏
页码：10855 / 10876
页数：21
相关论文
共 67 条
[1]  
Aduck J., Mufur A., Fonteh M., A review of methods to assess groundwater vulnerability to pollution, AJEP, 13, pp. 93-107, (2024)
[2]  
Ali Khan M., Izhar Shah M., Faisal Javed M., Ijaz Khan M., Rasheed S., El-Shorbagy M.A., Roshdy El-Zahar E., Malik M.Y., Application of random forest for modelling of surface water salinity, Ain Shams Eng J, 13, (2022)
[3]  
Alnuwaiser M.A., Javed M.F., Khan M.I., Ahmed M.W., Galal A.M., Support vector regression and ANN approach for predicting the ground water quality, J Indian Chem Soc, 99, (2022)
[4]  
Anbari M.J., Zarghami M., Nadiri A.-A., An uncertain agent-based model for socio-ecological simulation of groundwater use in irrigation: a case study of Lake Urmia Basin, Iran, Agric Water Manag, 249, (2021)
[5]  
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, 14, 5, pp. 220-235, (2019)
[6]  
Barzegar R., Razzagh S., Quilty J., Adamowski J., Kheyrollah Pour H., Booij M.J., Improving GALDIT-based groundwater vulnerability predictive mapping using coupled resampling algorithms and machine learning models, J Hydrol, 598, (2021)
[7]  
Barzegar R., Jafarzadeh F., Asghari Moghaddam A., Razzagh S., Cloutier V., Rosa E., Advancing groundwater vulnerability assessment in coastal regions: integrating machine learning and traditional frameworks, (2024)
[8]  
Bordbar M., Khosravi K., Murgulet D., Tsai F.T.-C., Golkarian A., The use of hybrid machine learning models for improving the GALDIT model for coastal aquifer vulnerability mapping, Environ Earth Sci, 81, (2022)
[9]  
Breiman L., Random Forest, Mach Learn, 45, pp. 5-32, (2001)
[10]  
Burri N.M., Weatherl R., Moeck C., Schirmer M., A review of threats to groundwater quality in the anthropocene, Sci Total Environ, 684, pp. 136-154, (2019)
1234567