Groundwater salinization risk assessment using combined artificial intelligence models
Oussama Dhaoui1,2, Isabel Margarida Antunes3, Ines Benhenda4
1Higher Institute of Water Sciences and Techniques, Applied Hydrosciences Laboratory, University of Gabes, University Campus, 6033, Gabes, Tunisia. dhaoui.oussama2013@gmail.com.
Environmental Science and Pollution Research International
|April 28, 2024
Summary
Artificial intelligence models, including artificial neural networks (ANN), improve groundwater salinization risk assessment in arid regions. ANN models show superior accuracy over traditional methods for predicting groundwater contamination.
Area of Science:
- Hydrogeology
- Environmental Science
- Artificial Intelligence
Background:
- Groundwater contamination risk assessment is vital for water resource management, especially in arid regions like Menzel Habib, Tunisia.
- The original DRASTIC vulnerability methodology has limitations in accurately reflecting groundwater salinization risk (GSR).
- Existing methods show a weak correlation between the DRASTIC Vulnerability Index (VI) and groundwater total dissolved solids (TDS).
Purpose of the Study:
- To develop and validate artificial intelligence (AI) models for assessing groundwater salinization risk (GSR).
- To enhance the original DRASTIC methodology by incorporating TDS-GSR indicators.
- To compare the performance of ANN, SVR, and MLR models in predicting GSR.
Main Methods:
- Application of artificial neural networks (ANN), support vector regression (SVR), and multiple linear regression (MLR) algorithms.
- Utilizing the seven parameters of the original DRASTIC model as inputs.
- Employing groundwater salinization risk (GSR) values derived from TDS as outputs for AI models.
Main Results:
- The original DRASTIC VI indicated low to moderate vulnerability (91-141) but showed a weak correlation (r < 0.5) with TDS.
- The ANN model demonstrated superior performance, achieving a correlation coefficient (r) of 0.89 and a Willmott Agreement Index (d) of 0.4 during training.
- ANN-based methodologies proved more robust and accurate than SVR, MLR, and the original DRASTIC model.
Conclusions:
- AI models, particularly ANN, offer a more accurate and robust approach to assessing groundwater salinization risk.
- Incorporating TDS-GSR indicators significantly improves groundwater vulnerability assessment compared to the original DRASTIC model.
- The findings provide valuable insights for managing groundwater contamination risks in arid environments.
Related Concept Videos
02:02Responses to Salt Stress
13.1K
Salt stress—which can be triggered by high salt concentrations in a plant’s environment—can significantly affect plant growth and crop production by influencing photosynthesis and the absorption of water and nutrients.
13.1K
01:18Steps in Outbreak Investigation
124
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
124
01:17Design Example: Analyzing Capacity Contours for Flood Risk Assessment
45
Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...
45