Multi-well clustering and inverse modeling-based approaches for exploring geometry, petrophysical, and hydrogeological parameters of the Quaternary aquifer system around Debrecen area, Hungary.

Mohammed, MusaabA.A.; Szabó, Norbert P.; Flores, Yetzabbel G.; Szűcs, Péter

doi:10.1016/j.gsd.2024.101086

Cited by 5 publications

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The incised valley deposits, on the other hand, showed a more uniform distribution for the aquifer parameters with lower shale volume and higher effective porosity and hydraulic conductivity. The uniformity of this unit suggests a relative homogeneity, making it a potentially promising groundwater source 44 , 72 .…”

Section: Discussionmentioning

confidence: 98%

Assessing heterogeneous groundwater systems: Geostatistical interpretation of well logging data for estimating essential hydrogeological parameters

Mohammed,

Flores,

Szabó

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

This research presents an unsupervised learning approach for interpreting well-log data to characterize the hydrostratigraphical units within the Quaternary aquifer system in Debrecen area, Eastern Hungary. The study applied factor analysis (FA) to extract factor logs from spontaneous potential (SP), natural gamma ray (NGR), and resistivity (RS) logs and correlate it to the petrophysical and hydrogeological parameters of shale volume and hydraulic conductivity. This research indicated a significant exponential relationship between the shale volume and the scaled first factor derived through factor analysis. As a result, a universal FA-based equation for shale volume estimation is derived that shows a close agreement with the deterministic shale volume estimation. Furthermore, the first scaled factor is correlated to the decimal logarithm of hydraulic conductivity estimated with the Csókás method. Csókás method is modified from the Kozeny-Carman equation that continuously estimates the hydraulic conductivity. FA and Csókás method-based estimations showed high similarity with a correlation coefficient of 0.84. The use of factor analysis provided a new strategy for geophysical well-logs interpretation that bridges the gap between traditional and data-driven machine learning techniques. This approach is beneficial in characterizing heterogeneous aquifer systems for successful groundwater resource development.

show abstract

Section: Discussionmentioning

confidence: 98%

Assessing heterogeneous groundwater systems: Geostatistical interpretation of well logging data for estimating essential hydrogeological parameters

Mohammed,

Flores,

Szabó

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

Multi-step modeling of well logging data combining unsupervised and deep learning algorithms for enhanced characterization of the Quaternary aquifer system in Debrecen area, Hungary

Mohammed,

Szabó,

Szűcs

2024

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

In this research, a multi-step modeling approach is followed using unsupervised and deep learning algorithms to interpret the geophysical well-logging data for improved characterization of the Quaternary aquifer system in the Debrecen area, Hungary. The Most Frequent Value-Assisted Cluster Analysis (MFV-CA) is used to map lithological variations within the aquifer system. Additionally, the Csókás method is used to discern both vertical and horizontal fluctuations in hydraulic conductivity. MFV-CA is introduced to cope with the limitation of the conventional Euclidean distance-based k-means clustering known for its low resistance to outlying values, resulting in deformed cluster formation. However, the computational time and demands of MFV-CA are evident, making them costly and time-consuming. As a result, Deep Learning (DL) methods are suggested to provide fast characterization of the groundwater aquifers. These methods include Multi-Layer Perceptron Neural Networks (MLPNN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM), which are implemented for classification and regression. The classification categorized the inputs into three distinct lithologies trained initially by the results of MFV-CA. At the same time, the regression model offered a continuous estimations of hydraulic conductivity trained by the results of the Csókás model. The results demonstrated significant compatibility between the outcomes derived from the clustering and Csókás approaches and DL algorithms. Accordingly, the lithofacies and hydraulic conductivity variations across the main hydrostratigraphical units are mapped. This integration enhanced the understanding of the groundwater system, offering promising inputs for groundwater and development and management.

show abstract

Geophysical characterization of groundwater aquifers in the Western Debrecen area, Hungary: insights from gravity, magnetotelluric, and electrical resistivity tomography

Mohammed,

Szabó,

Alao

et al. 2024

Sustain. Water Resour. Manag.

View full text Add to dashboard Cite

The recent study followed a multi-methodological approach integrating gravity, magnetotelluric (MT), and electrical resistivity tomography (ERT) to investigate the geometry and hydrological characteristics of the main hydrostratigraphical units in the Western Debrecen area, Eastern Hungary. The integration of these methods aims to delineate potential zones for groundwater development and guide effective extraction strategies. In the gravity investigation, the Bouguer anomaly map undergoes spectral analysis for the separation of shallow and deep features, offering a preliminary indication of basement rock depth. Subsequently, gravity data inversion is employed to map variations in basement rock topography, revealing a basin structure, with sediment thicknesses extending up to 2 km. On the other hand, the MT data are modeled using the 1D Occam inversion algorithm to validate the results of the gravity data analysis. This inversion, constrained with lithological logs is further utilized to delineate the main hydrostratigraphical units in the study area. Accordingly, four units are identified, including the Nagyalföld Aquifer, Algyő and Endrődi Aquitards, the Badenian Aquifer, and the Pre-Neogene Aquitard. Consequently, Dar Zarrouk parameters based transmissivity and the hydraulic conductivity of the aquifer units are measured. The Nagyalföld aquifer showed a hydraulic conductivity that ranged between 7.9 and 11.9 m/day, while the Badenian aquifer showed an average hydraulic conductivity of 13.1 m/day. The ERT data are employed to map the spatial distribution of the depth to the water table. The shallow water table is observed in regions characterized by an elevated thickness of sedimentary rocks, attributed to their high specific capacity. Integrating these hydrogeophysical methods provided a comprehensive understanding of the subsurface hydrology and enabled better-informed decision-making for groundwater development.

show abstract

Multi-well clustering and inverse modeling-based approaches for exploring geometry, petrophysical, and hydrogeological parameters of the Quaternary aquifer system around Debrecen area, Hungary.

Cited by 5 publications

References 55 publications

Assessing heterogeneous groundwater systems: Geostatistical interpretation of well logging data for estimating essential hydrogeological parameters

Assessing heterogeneous groundwater systems: Geostatistical interpretation of well logging data for estimating essential hydrogeological parameters

Multi-step modeling of well logging data combining unsupervised and deep learning algorithms for enhanced characterization of the Quaternary aquifer system in Debrecen area, Hungary

Geophysical characterization of groundwater aquifers in the Western Debrecen area, Hungary: insights from gravity, magnetotelluric, and electrical resistivity tomography

Contact Info

Product

Resources

About