Quantification of Surface Water-Groundwater Exchanges by GIS Coupled with Experimental Gauging in an Alluvial Environment

Draoui, Yassyr; Lahlou, Fouad; Chao, Jamal; Mezouary, Lhoussaine El; Mazini, Imane Al; Hamidi, Mohamed Jalal El

doi:10.14569/ijacsa.2021.0120135

Cited by 5 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Improved spatial mapping of hydrodynamic characteristics allows for the identification of areas with varying levels of productivity and vulnerability [8,9]. Innovative aquifer characterization solutions are crucial for efficient monitoring, modeling, and management, particularly in the face of increasing abstraction pressures [7,[10][11][12][13].…”

Section: Fig 1 Geological and Location Maps Of El-haouz-mejjate Aquifermentioning

confidence: 99%

Machine Learning and Deep Learning Guided Assessment of Groundwater Reservoir Hydrodynamic Parameters: A Case Study of The El Haouz Aquifer

El Mezouary,

Hadri,

Kharrou

et al. 2024

E3S Web Conf.

View full text Add to dashboard Cite

The Plio-Quaternary aquifer in the EL-Haouz-Mejjate region of Morocco is critical for water supply, necessitating accurate characterization for sustainable management. This study pioneers machine learning (ML) and deep learning (DL) techniques to elucidate the aquifer’s properties. Supervised algorithms, including random forest, regression, support vector machines, Gaussian process regression and neural networks, are trained on available hydrogeological data. Diverse features capture complex input-output relationships to predict key hydrodynamic factors like hydraulic conductivity and transmissivity fields. Aquifer architecture attributes, including substratum depth, thickness, and height, are also estimated. Model outputs are validated with field measurements, demonstrating promising accuracy. Enhanced hydrodynamic insights improve the conceptual model and groundwater flow modeling confidence. Uncertainties are reduced through this data-driven approach, enabling optimized aquifer management. Overall, this work shows how useful it is to combine ML and DL with traditional hydrogeology in order to get a better understanding of complicated aquifer systems. The techniques pioneered provide a pathway for sustainable management of this vital water resource.

show abstract

Section: Fig 1 Geological and Location Maps Of El-haouz-mejjate Aquifermentioning

confidence: 99%

Machine Learning and Deep Learning Guided Assessment of Groundwater Reservoir Hydrodynamic Parameters: A Case Study of The El Haouz Aquifer

El Mezouary,

Hadri,

Kharrou

et al. 2024

E3S Web Conf.

View full text Add to dashboard Cite

show abstract

“…Therefore, these analytical solutions apply in principle only to specific cases (uniform flow, infinite or semi-infinite medium, low heterogeneity in particular). Their validation, therefore, requires recourse to in situ experiments (for example [27]) or to numerical simulations [6,[28][29][30][31][32][33]. The results of these different works show that these solutions can be applied to cases where the spatial variability of 𝐾ℎ is low.…”

Section: Groundwater Flow Equation Stochastic Approachmentioning

confidence: 99%

Applied Latin Hypercube stochastic method to quantify the uncertainty in groundwater equation model simulations

Mezouary

Mansouri

2021

E3S Web Conf.

View full text Add to dashboard Cite

It is accepted that digital models simplify the physical reality that is the object of the modeling. Hydrodynamic modeling is an approach with high uncertainties in this context. Indeed, the deterministic modeling approach assumes the existence of a functional relationship between the observed variables. The variables are observed by a series of measurements riddled with errors. Because of this, there is always a significant amount of uncertainty associated with a hydrogeological model. This uncertainty can be associated with the conceptual model or with the data and parameters associated with the different components of the model. Some model parameters such as hydraulic conductivity and recharge are particularly susceptible to uncertainty. Stochastic modeling of the hydrodynamics of a groundwater reservoir is an adequate response to allow us to take a step back on the significance of the results. The study is based on the development of a direct problem-solving model which represents the best estimate of the real hydrodynamic system. This model is used to make predictions. With a stochastic approach, a set of models is constructed where each model, as a whole, is considered to be equally likely. Each model is then used to make the prediction or simulate a given scenario. The MODFLOW-STOCHASTIC-GMS code allows us to do randomization simulations (Latin Hypercube method) and with parameter indicators.

show abstract

“…Widely used today as an alternative to the sewerage network of stormwater, which reduces the risk of flooding, contributes to the trapping of pollutants, and allows the settling of suspended matter loaded with pollutants [1][2][3]. Infiltration basins are also known to recharge the groundwater as well as other benefits [4][5][6][7]. Despite their beneficial characteristics, these systems are exposed in the long term by the risk of clogging, which reduces its hydraulic performance and limits the interception capabilities of water flows and pollutants.…”

Section: Introductionmentioning

confidence: 99%

A study of water infiltration basin and clogging using column experiments

2021

View full text Add to dashboard Cite

The clogging of infiltration basins is the main problem affecting the proper functioning of groundwater artificial recharge systems. In this study, several parameters have been varied to understand their impacts on water infiltration. The experimental results show that the effect of initial humidity is significant for less porous material such as silty soil (Hamri) and sand. The air bubbles are also an important factor to take into consideration since when trapped within porous structures, it forms a barrier for the displacement of water infiltration. The accumulation of suspended particles in stormwater can contribute to clogging by creating a light layer due to the finest particles, which remain in suspension for a long time. Finally, for the tested materials and experimental conditions, we observed that a combination of a silty soil and sand layer in the design of infiltration basins was more practical than a combination of sand and gravel. The latter, despite its high porosity, could release very fine particles; which would create a cement layer of clogging when deposited at the interface. This layer is an obstacle for water infiltration, thus rendering the device thus constructed unsuitably for groundwater recharge, by reducing its life.

show abstract

Quantification of Surface Water-Groundwater Exchanges by GIS Coupled with Experimental Gauging in an Alluvial Environment

Cited by 5 publications

References 16 publications

Machine Learning and Deep Learning Guided Assessment of Groundwater Reservoir Hydrodynamic Parameters: A Case Study of The El Haouz Aquifer

Machine Learning and Deep Learning Guided Assessment of Groundwater Reservoir Hydrodynamic Parameters: A Case Study of The El Haouz Aquifer

Applied Latin Hypercube stochastic method to quantify the uncertainty in groundwater equation model simulations

A study of water infiltration basin and clogging using column experiments

Contact Info

Product

Resources

About