Sustainable Groundwater Research Articles

Evaluation of Groundwater Potential Zones Using GIS‐Based Machine Learning Ensemble Models in the Gidabo Watershed, Ethiopia

AbstractThe main objective of this study is to map and evaluate groundwater potential zones (GWPZs) using advanced ensemble machine learning (ML) models, notably Random Forest (RF) and Support Vector Machine (SVM). GWPZs are identified by considering essential factors such as geology, drainage density, slope, land use/land cover (LULC), rainfall, soil, and lineament density. This is combined with datasets used for training and validating the RF and SVM models, which consisted of 75 potential sites (boreholes and springs), 22 non‐potential sites (bare lands and settlement areas), and 20 potential sites (water bodies). Each dataset is randomly partitioned into two sets: training (70%) and validation (30%). The model's performance is evaluated using the area under the receiver operating characteristic curve (AUC‐ROC). The AUC of the RF model is 0.91, compared to 0.88 for the SVM model. Both models classified GWPZs effectively, but the RF model performed slightly better. The classified GWPZ map shows that high GWPZs are typically located within water bodies, natural springs, low‐lying regions, and forested areas. In contrast, low GWPZs are primarily found in shrubland and grassland areas. This study is vital for decision‐makers as it promotes sustainable groundwater use and ensures water security in the studied area.

Source identification of nitrate in groundwater of an agro-pastoral ecotone in a semi-arid zone, northern China: Coupled evidences from MixSIAR model and DOM fluorescence

In the extensive agro-pastoral ecotone of northern China, groundwater is a valuable resource, but it suffers from severe nitrate pollution. However, the extent of the contributions of agricultural and pastoral activities to nitrate accumulation in the groundwater of the region remains unclear. This study aimed to identify the main sources of groundwater nitrate in Chahannur Basin, a typical agro-pastoral ecotone in the semi-arid zone of northern China, using the MixSIAR model based on dual stable isotopes and dissolved organic matter (DOM) fluorescence. The hydrochemical and isotopic results showed that the groundwater has high concentrations of nitrate (up to 208.19 mg/L) with weak denitrification, and nitrate accumulation is mainly driven by mixed input from different sources. The MixSIAR model results indicated that the largest contributors to groundwater nitrate accumulation are manure & sewage, followed by soil nitrogen, chemical fertilizers, and atmospheric deposition. According to the DOM fluorescence characteristics, the groundwater is strongly affected by livestock and poultry waste, followed by soil humic substances. Moreover, the DOM fluorescence results further supported the MixSIAR model results based on the significant correlation between the contributions of nitrate sources and the percentages of fluorescent components, jointly confirming that the main source of nitrate in groundwater is manure and sewage, followed by soil nitrogen. These findings indicate that coupled evidences from the MixSIAR model and DOM fluorescence could be applied to identify the sources of nitrate in groundwater, and this coupling can provide valuable information for local authorities to achieve sustainable groundwater management.

Groundwater modelling for decision-support in practice: Insights from Sweden.

Groundwater is an essential resource for drinking water, food production, and industrial applications worldwide. Over-exploitation and pollution pose significant risks to groundwater sustainability. Groundwater models can be powerful tools for optimizing use, managing risks, and aiding decision-making. For this purpose, models should assimilate pertinent data and quantify uncertainties in outcomes. We examine applied modelling for characterization and decision support in Sweden from 2010 to 2023. We also review syllabi of water-related courses in Swedish higher education to assess the inclusion and extent of groundwater modelling education. We find that important academic advances in groundwater modelling over the past two decades have not translated into practical application within Sweden's industry, that uncertainty quantification is rarely undertaken, and that groundwater modelling remains a low priority in higher education. Based on these findings, we offer recommendations that, while informed by the Swedish context, hold relevance for educational institutions, industry, and decision-makers internationally.

Environmental Impact of Synthetic Dyes on Groundwater in Malaysia: Sources, Distribution, Transport Mechanisms, and Mitigation Strategies

Synthetic dyes, extracted from natural sources like insects, plants, coal, and ochre, have become prevalent due to their advantages over natural dyes. However, their production has led to increased environmental pollution, particularly in groundwater. Groundwater contamination from synthetic dyes occurs through advection, dispersion, and retardation. This review aims to highlight the environmental impacts of synthetic dyes on groundwater, elucidate the mechanisms of dye transport, and propose effective strategies for monitoring and mitigating contamination. Urban runoff carries dyes from surfaces such as roofs, parking lots, and roads into stormwater systems, while agricultural runoff transports dyes from products like soil conditioners, fertilizers, and seed coatings into water bodies. In groundwater, dyes move through the aquifer via advection, dispersion, and retardation, all influenced by groundwater flow and geological conditions. The advection process involves the bulk movement of groundwater carrying dissolved dyes, while dispersion causes dyes to spread and dilute over time and distance. Retardation, which involves the adsorption of dye molecules onto soil particles, slows dye movement, prolonging their presence in groundwater. Understanding the sources, distribution, and movement of synthetic dyes in groundwater is crucial for developing strategies to protect water resources and reduce environmental and health impacts. The extensive use of dyes in industrial and domestic activities necessitates comprehensive monitoring and management to ensure sustainable groundwater quality.

Sustainable groundwater regulation in typical irrigation areas of inland river basins based on ecological indicators and the MIKE-SHE hydrological model

Study regionThe study area is located in the Nukus irrigation area on the lower reaches of the Amudarya River in Uzbekistan. Study focusThe extensive agricultural land development has introduced a substantial amount of water resources into the irrigation area, leading to a significant rise in regional groundwater levels. Quantifying regional groundwater resource issues and achieving sustainable groundwater management under conditions of high spatiotemporal heterogeneity are key scientific issues for regional ecological protection. Thus, this study used the concept of ecological water level to quantify groundwater issues, used the MIKE-SHE hydrological model to conduct scenario simulations, formulated and subsequently evaluated a groundwater regulation plan with spatiotemporal attributes. New hydrological insights for the regionRegional sustainable development groundwater level should be within the range of 1.78–2.78 m. During the irrigation and non-irrigation periods, the groundwater levels in approximately 84.3 % and 72.2 % of the study area respectively exceeded the upper and lower ecological water level limits. Under the background of gradually increasing groundwater fluctuations, it will pose a serious threat to regional ecology. Therefore, this paper established a monthly-scale groundwater zoning control plan, which can make the area of regional groundwater within the ecological water level reach 87.53 %. All research not only contributes to the protection of the local ecological environment but also provides valuable insights for water resources management in other regions.

Integrated geophysical and GIS approaches for groundwater potential assessment: a case study of Aladja, Delta State, Nigeria

ABSTRACT This study explores the groundwater potential in Aladja, Udu, Local Government Area of Delta State, Nigeria, using an integrated approach combining electrical resistivity techniques with Remote Sensing (RS) and Geographic Information System (GIS) methods. The primary aim is to delineate aquifers and comprehensively assess groundwater resources. Methods include Vertical Electrical Sounding (VES) to gather resistivity data, RS and GIS for analyzing geological and hydrological parameters such as lineament density, drainage density, slope, soil type, and land use. The resistivity values ranged from 147 to 460.50 Ωm, with aquifer thicknesses varying between 6.50 and 36.30 m. The RS and GIS analysis indicated high groundwater potential in regions characterized by significant lineament density and moderate slopes. The study highlights the complementarity of VES and RS/GIS in groundwater exploration, revealing substantial groundwater resources in the northwestern regions of the study area. This approach underscores the importance of integrating these methods for a more accurate assessment of groundwater potential. The novelty of this study lies in validating RS and GIS findings with VES data, ensuring reliable groundwater potential mapping and effective resource management. This integrated methodology offers a robust framework for sustainable groundwater resource assessment and management in similar geological settings.

Assessing the role of stakeholders in sustainable groundwater resources management using power-interest matrix (PIM): in Hamedan-Bahar plain, Iran

IntroductionMoral Intelligence (MI) as a concept has gained importance Increasing water scarcity as a result of climate change and its coincidence with population growth, economic development, and the resulting rising demand has become an important challenge in most parts of the world. In numerous nations, such as Iran, frequent occurrences of droughts, combined with the extensive utilization of surface and groundwater resources, have resulted in numerous environmental detriments, including a decrease in groundwater levels, land subsidence, deterioration of water quality, and, more recently, the emergence of dust storms due to soil erosion and desertification. In this situation, stakeholders can play an efficient role in water management and the alleviation of water scarcity and its negative environmental externalities in the context of good water governance.MethodThis investigation endeavored to examine the functions and importance of individuals or groups with a vested interest in groundwater resources within the Hamedan-Bahar Plain. Additionally, it aimed to evaluate their influence and motivations through the utilization of the power-interest matrix (PIM) and important-performance matrix techniques. A total of 86 people were identified who could and were allowed to be interviewed through the snowball method. Then a 10-point scale questionnaire was used to rate the questions. To examine the power and interest of the stakeholders, the IPM test was carried out using the smart pls.3 software, and the results were classified based on the average values and the overall impact. The results reveal that 20 institutions and agencies have an effective role in the governance of groundwater resources in the Hamedan-Bahar plain. Furthermore, the analysis of the PIM revealed that the most powerful organizations that play the most important role in the management of the groundwater resources of the studied area are the regional water organization, the representatives of the parliament, and the governor, respectively.Results and discussionBased on the research findings, the governance “power” index of organizations and institutions with power (39.77%) and total impact (0.516) is higher and more effective than the value of benefits with power (36.13%) and total impact (0.48). Accordingly, paying attention to the role and influence of the power of stakeholders will be an important and effective point in the plans and strategies for groundwater resources in the Hamadan-Bahar plain. In the end, strategies are suggested to each stakeholder for better implementation of the programs and strategies.

Challenges and opportunities for enhancing groundwater data access and usability in low- and middle-income countries: insights and recommendations from WaSH researchers and practitioners

ABSTRACT Groundwater provides more than half of all water for drinking and irrigation worldwide. Monitoring and managing groundwater resources is essential to achieve the Sustainable Development Goals. However, groundwater resources need to be better monitored. We explored practical approaches to improve groundwater monitoring for informed decision-making, focusing on low- and middle-income country settings. Case studies from a 2023 UNC Water and Health Conference side event highlighted innovative approaches, including open-source data modeling, groundwater monitoring in humanitarian contexts, and using in situ sensors to monitor drought resilience. The case studies described field data integration, remote sensing, and technology (e.g., Modflow-USG, ModelMuse, Drought Resilience Impact Platform). Barriers to groundwater data use were identified by side event participants, including inadequate data access, insufficient collaboration and leadership, and challenges in integrating diverse data and technology. Side event recommendations included creating a central groundwater monitoring data repository, building greater hydrogeology capacity in the WaSH sector, and increasing funding for data collection and monitoring. We urge government leaders to develop regulations and build internal capacity for sustainable groundwater management. This comprehensive approach aims to address challenges and promote informed decision-making for the long-term sustainability of groundwater resources.

Assessment of groundwater quality in the eastern part of tehran plain: Implications for human health.

Groundwater quality is a critical concern for human health, particularly in urban areas like the eastern part of Tehran Plain, where geological features and anthropogenic activities contribute to contamination risks. This study aimed to assess the quality of groundwater in this region, focusing on its implications for public health. The objectives of the study were to identify factors influencing hydrogeochemistry, evaluate environmental risk based on metal(loid)s using water quality indices, and conduct a health risk assessment. Groundwater samples were collected and analyzed for chemistry, water quality, heavy metal contamination, and associated health risks. The results indicated a relatively stable pH condition and a wide variation in the concentration of dissolved solids. The Water Quality Index (WQI) was employed to evaluate the overall water quality, revealing that approximately 50% of the samples fell into the poor and very poor quality categories, with two samples deemed unsuitable for drinking. Heavy metal contamination varied across different metals, with some indicating low levels while others showed moderate to very high levels. Priority pollutants such as mercury and arsenic were identified as having a greater potential impact on water quality deterioration. Exposure and health risk assessments indicated a negligible risk associated with aluminum exposure but high risks associated with arsenic, chromium, and mercury exposure. Carcinogenic risk assessments for arsenic, chromium, and mercury exceeded acceptable thresholds, emphasizing the urgent need for further investigation into contamination sources and strategies for mitigation. These findings highlight the importance of continuous monitoring and sustainable groundwater management practices, providing valuable insights for other regions facing similar challenges in groundwater quality and public health.

Unraveling the synergistic interplay of sulfur and wheat straw in heterotrophic-autotrophic denitrification for sustainable groundwater nitrate remediation

Nitrate pollution in groundwater is a global environmental issue that poses significant threats to human health and ecological security. This study focuses on elucidating the mechanisms of heterotrophic-autotrophic cooperative denitrification (HAD) by employing wheat straw and elemental sulfur as electron donors in varying proportions. The research initially underscores that heterotrophic denitrification (HD) accelerates the denitrification process due to its high-energy metabolism. However, as readily degradable organic matter diminished, reliance on more complex substrates such as lignocellulose posed a challenge to HD. This marks a pivotal transition towards autotrophic denitrification (AD), which, despite a slower initial rate, exhibits a more sustained denitrification performance. A low proportion of heterotrophic denitrification layer (e.g., 3:1) at the bottom facilitating efficient and sustainable denitrification. HD is capable of simultaneous removal of nitrates and nitrites, whereas AD demonstrates a higher affinity for nitrates, with nitrite accumulation reaching 100% at high influent nitrate concentrations (100 mg/L). HD not only provides the necessary alkaline environment for AD but also reduces sulfate production, whereas AD utilizes the residual organic carbon and ammonia produced by HD. The heterotrophic layer is characterized by a diverse community, whereas the autotrophic layer is predominantly composed of Thiobacillus. By delineating the interactive mechanisms and characteristics of HAD, this study highlights the importance of balancing heterotrophic and autotrophic activities for the effective remediation of groundwater nitrates.

Source Minerals for the Release of Salinity in the Groundwater: A Case Study of Pratapgarh District, Uttar Pradesh, India

ABSTRACT The aim of this study is to determine the salinity of groundwater, identify the nature of its sources, and to understand the physicochemical conditions that cause high level of salinity to be discharged into groundwater. There are several factors that influence groundwater salinity, including water quality, soil type, irrigation techniques, and groundwater depth. A total of 40 ground water samples were collected from dug wells, tube wells, and hand pumps in salinity-affected areas and analysed using physicochemical variables. A total of 11 sediment samples were collected and analysed for lithology and mineralogy. Due to high level of cations and anions in the groundwater, the study area is highly contaminated. It was observed that the leaching of salt is highly dependent on sediment types and salt-bearing minerals. Attempts were also made to determine the various depth zones responsible for release of salt in shallow aquifers. For sedimentological and mineralogical studies, a piezometer was installed at a maximum depth of 33 m below the ground surface. Based on the results of the study, it was observed that groundwater chemistry is primarily influenced by water-rock interactions, ion exchange processes, weathering (carbonate and silicate), and evaporation. These research findings will contribute to more effective sustainable groundwater management in areas with water scarcity and it will also boost the Indian economy.

The effect of geology and agricultural development on the groundwater, West Minia, Egypt

Fifty groundwater samples were collected from the Oligocene sand and Middle Eocene limestone aquifers and analyzed for major ions and stable isotopes. Aquifer sediment samples were examined to determine hydraulic properties, and sixty-six well logs were investigated to understand the subsurface geology. The study reveals that lithofacies, mineral composition, and geologic structures significantly influence groundwater quality and behavior. Karst features in the Middle Eocene limestone aquifer create subsurface caves, leading to challenges such as abrupt salinization and well failure. In the Oligocene aquifer, groundwater is predominantly of the sodium chloride type. In the Middle Eocene aquifer, 80 % of samples are sodium chloride, with variations of sodium bicarbonate (10 %) and sodium sulfate (10 %) types. Remote sensing from 2013 to 2021 shows significant agricultural expansion, with vegetation increasing by over 227 km². This growth, driven by large agricultural projects, has led to substantial groundwater consumption, resulting in a 5-meter decline in water levels within just one year (from 2020 to 2021). The over-extraction poses a risk to the aquifers, threatening long-term sustainability. Understanding the region's geology is crucial for mitigating these issues and ensuring sustainable groundwater management.

Identifying Groundwater Recharge Sources and Mechanisms using Hydrochemistry and Environmental Stable Isotopes in High Arsenic Holocene Aquifers of Bangladesh

Und erstanding the sources and mechanisms of aquifer recharge is critical for water resource management. So far, this is the first comprehensive study to explore the sources and mechanisms of groundwater recharge applying stable environmental isotopes and hydrogeochemical properties in Southwestern Bangladesh. Water samples from the different sources (groundwater, surface (pond), river and rain water) of high arsenic (As) Holocene aquifers were used to investigate the chemical tracers and environmental stable isotopes (δ18O and δ2H) to explore the hydrogeological features, groundwater recharge sources, mechanisms and processes. The analytical results showed high As concentration in water samples observed 590.7 μg/L. High As groundwater was identified by a low pH value, medium HCO3- and TDS with low concentration of NO3- and SO42-. However, depleted δ2H and δ18O signatures indicated that local vertical rainfall is the key source to recharge groundwater in study area. The recharge process from pond seepage and irrigation return flow also contribute in groundwater recharge. Isotopic signatures suggested the vertical connectivity amongst the aquifers and significant vertical recharge. The reduced heavier isotope reveals extra recharging from floods of mountains and high altitude. Due to the heterogeneous and anisotropic structure of the aquifer system the spatial variability of δ2H and δ18O shows limited lateral connectivity. The combined analyses of δ2H isotope and Cl- ion showed that evaporation is the primary cause for groundwater discharge. Based on the spatial and vertical recharge processes of groundwater, present study provides a crucial baseline knowledge for establishing a sustainable groundwater management strategy. The findings from this study can guide the development of targeted groundwater management strategies and improvement of understanding the groundwater recharge sources and processes.

Urban Water Crisis in Kabul City: Key Challenges and Solutions

Water is an essential human need for survival. However, billions globally wake up daily with accessible and affordable clean water. Rapid population growth, urbanization, climate change, precipitation regime changes, industrial development, and environmental degradation increase pressure on urban water resources. As a result, water demand is continuously rising, leading to prominent shortages in many cities in developing and developed countries, regardless of their developmental condition. One such city facing significant water scarcity is Kabul, the capital of Afghanistan, where rapid urbanization has outpaced local water supply infrastructure, resulting in unsustainable exploitation of groundwater resources. This directly threatens the well-being of millions of residents in this city. In anticipation of the exhaustion of local water sources, Kabul will soon need to explore alternative water supply methods, such as inter-basin water transfers, to meet the growing demand. This paper aims to offer a broad overview of urban water crises, evaluating the key drivers of water shortages, exploring the specific water crisis facing Kabul, and analyzing previous research, reports, papers, flow data, groundwater data, maps/charts, field observations, surveys, GIS data, and statistical analysis as the methods for this work. So, to combat declining groundwater levels, a sustainable groundwater management approach is crucial. The approach includes water conservation methods, the implementation of efficient irrigation techniques, and the adoption of water pricing mechanisms.

Sustainable Groundwater Management Using Machine Learning-Based DRASTIC Model in Rurbanizing Riverine Region: A Case Study of Kerman Province, Iran

Sustainable Groundwater Management Using Machine Learning-Based DRASTIC Model in Rurbanizing Riverine Region: A Case Study of Kerman Province, Iran

Delineation of fresh groundwater potentiality zones in saline coastal aquifers, Southwest Bangladesh using remote sensing and GIS approaches.

Bay of Bengal in southern Bangladesh is a major source of water from coastal aquifers, but prone to contamination by seawater intrusion,making climate-vulnerable populations and economies unfit for potable, agricultural water, adopting crops, etc. The study area located in Khulna district lies in the southwestern coast of the country is among the most vulnerable due to its salinity issues. Therefore, this study identified fresh groundwater potential zones in the southwestern coastal zones of the country suited for community usage helping coastal peoples meet their demands. This study focused on twelve thematic layers employing remote sensing and GIS with analytical hierarchy process. Here, groundwater salinity is 84% brackish to saline over 70% of the region [electric conductivity: 295-16,295 micro-Siemens/cm]. However, groundwater chloride in 88% signifies a slightly to medium salty zone. The annual average rainfall reduced surface water infiltration in 75% of the area with little to very slightly soil salinity. The fresh groundwater resource zone has classified based on its potentiality as: very high (0.52%)-for drinking, agricultural irrigation, or industrial work; high (25%)-marginal salinity suitable for agricultural or industrial uses; low (11%)-low salinity, but usable for high salt tolerant crops in irrigation; and very low (64%)-very high groundwater salinity, and not suitable for human consumption and community uses. Finally, this study will help develop sustainable groundwater resources in the coastal region and a fresh groundwater supply plan in saline-prone areas.

Groundwater quality prediction and risk assessment in Kerala, India: A machine-learning approach

Despite its critical importance for health, agriculture, and the economy, and its key role in supporting climate change adaptation, groundwater quality remains vulnerable to contamination and is often neglected until significant deterioration. The groundwater resources of Kerala, one of the southernmost states of India, are under escalating stress and scarcity, despite a high well density with 62% of the population relying on groundwater from approximately 6.5 million open wells. This study investigates the detailed hydrogeochemistry and predicts groundwater quality zones of the state using machine-learning techniques viz, extreme gradient boosting (XGBoost), support vector regression (SVR), artificial neural network (ANN) and random forest (RF) regression. The hydrogeochemical analysis reveals varying groundwater quality across the state. Among the different machine learning models, RF shows higher goodness of fit (R2: 0.922) with minimal prediction error (root mean square error: 6.29 and mean absolute error: 3.12). The predicted groundwater quality was validated using the spatially distributed stiff diagrams, visually representing water composition trends of each well. The very good, good, moderate and poor groundwater quality zones occupy 31.7%, 40.4%, 20.4%, and 7.4% of the state aligning accurately with the groundwater quality scenario of the state. Additionally, groundwater drinking risk assessment was conducted, considering that 7.4% of the state experiences poor-quality groundwater. Integrating groundwater quality maps with population data, the study assessed potential health risks due to consuming untreated water. Nearly 0.59 million people across 252 local self-government bodies (LSGs) are susceptible to consuming poor quality groundwater, which may pose potential health risks. This observation provides valuable insights for sustainable groundwater management and public health safeguarding and the findings of the present study are useful for achieving sustainable development goal (SGD) 6 (clean water and sanitation) and long-term groundwater management in Kerala.

Sustainable Water Resource Planning for Alanda Micro Watershed Using Geospatial Techniques

Groundwater is a vital natural resource, especially in areas lacking surface water bodies. About one-third of the global population relies on it for drinking, irrigation and industrial purposes. However, excessive and unregulated exploitation has led to a rapid decline in water tables, emphasizing the need for sustainable groundwater management. The Alanda micro watershed in Barshitakli Taluka, Akola District, Maharashtra, spans 11.39 km², with a sub-humid climate and uneven monsoon rainfall averaging 780 mm. The region faces high water stress in summer, with dried bore wells and farmers relying on rain and groundwater for irrigation. The water resource development plan for Alanda micro watersheds integrates GIS, remote sensing and AHP to identify groundwater potential zones. The Alanda micro watershed soil and water conservation plans were developed using GIS, remote sensing and the AHP method. Thematic maps were overlaid in ArcGIS, applying weighted factors from a pairwise comparison matrix to identify groundwater potential zones. These zones, categorised as high, moderate and low potential, highlight that the largest area has moderate potential, suggesting good opportunities for conservation measures. The survey of the study area identified existing soil and water conservation structures, including 3 farm ponds, 1 check dam and a contour bund. Additional recommendations include 5 farm ponds, 4 check dams, contour trenches and bunding measures, along with agronomic practices for effective surface and groundwater management.

Optimizing Irrigation Systems for Water Efficiency and Groundwater Sustainability in the Coastal Nile Delta

This study investigates the replacement of traditional surface irrigation methods with modern irrigation systems (MIS) including horizontal sprinkler, central pivot, surface drip, and subsurface drip aimed at improving water efficiency in the Nile Delta, Egypt. The primary objectives were to determine the optimal agricultural area for implementing MIS and to assess the effects of these systems on groundwater quantity and quality in the region. To achieve this, the LINDO software was employed to optimize land allocation for each irrigation method. At the same time, the SEAWAT code was utilized to simulate saltwater intrusion (SWI) in the Nile Delta aquifer. The transition from traditional surface irrigation to MIS resulted in significant water savings, reaching 2.15 × 10^9 m³. However, groundwater modeling indicated a decrease in groundwater levels, leading to an 8 % increase in aquifer salinity due to reduced infiltration of recharge water. These findings underscore the urgent need to revise outdated irrigation practices and enhance water management strategies in the Nile Delta to mitigate salinity issues in coastal aquifers. This research's outcomes are crucial for decision-makers and stakeholders in selecting appropriate irrigation methods, particularly in arid and semi-arid regions, to ensure sustainable water use and agricultural productivity.

Robust estimation of hydrogeological parameters from wireline logs usingsemi-supervised deep neural networks assisted with global optimization-based regression methods

Understanding the distribution of hydrogeological properties of the aquifers is crucial for sustainable groundwater resource development. This research explores the application of deep autoencoder neural networks (AE-NN), assisted with global optimization methods for estimating hydrogeological parameters in the Quaternary aquifer system in the Debrecen area, Hungary. Traditional methods for estimating aquifer parameters typically depend on field experiments and laboratory analyses, which are both costly and time-consuming, and often fail to account for the heterogeneity of groundwater formations. In this study, deep AE-NN models are trained to extract latent space (LS) representations that capture key features from the available well logs, including spontaneous potential (SP), natural gamma ray (NGR), shallow resistivity (RS), and deep resistivity (RD). The LS log is then correlated with shale volume and hydraulic conductivity, as determined by the Larionov and Csókás methods, respectively. Regression analysis revealed a Gaussian relationship between the LS log and shale volume and a negative nonlinear relationship with hydraulic conductivity. Global optimization methods, including simulated annealing (SA) and particle swarm optimization (PSO), were used to refine the regression parameters, enhancing the predictive capabilities of the models. The results demonstrated that AE-NN assisted with global optimization methods can be effectively used to estimate shale volume and hydraulic conductivity, proposing a novel and independent approach for estimating hydrogeological parameters critical to groundwater flow and contaminant transport modeling.