Groundwater assessment is critical for addressing global and regional water security challenges, particularly in transboundary areas and conflict zones such as Ukraine. These regions often experience shifting water balance patterns due to excessive groundwater abstraction, damage to water infrastructure, and large-scale population displacement to safer border areas. Modeling transboundary groundwater storage and flows in such contexts is challenging due to uneven data availability across borders, inconsistent hydrogeological descriptions, restricted fieldwork, and limited local capacity to maintain data collection infrastructure. Effective water management in these areas requires pooling global expertise and resources, increasingly leveraging satellite observations, and fostering close collaboration among partner countries engaged in transboundary aquifer modeling.
The Groundwater Resilience Assessment through Integrated Data Exploration for Ukraine (GRANDE-U) project addresses these challenges through an organizational and technological framework uniting researchers from six countries—the U.S., Ukraine, Poland, Latvia, Lithuania, and Estonia. The project integrates physics-based and machine learning models for transboundary aquifers with downscaled satellite remote sensing data. Building on the foundations of the NSF-funded AccelNet Transboundary Groundwater Resilience project and the European EU-WATERRES project, GRANDE-U employs the following methodology:
- Developing a spatial database of water-related indicators for transboundary areas, including geology, water resources, land cover, monthly precipitation, evapotranspiration, runoff, soil moisture, and other characteristics at observation points and a 0.1"-0.25" grids covering the aquifer;
- Creating algorithms to downscale GRACE/GRACE-FO-based terrestrial water storage (TWS) and groundwater storage (GWS) data to resolutions of 0.25" and finer for specific regions with the best available hydrogeologic data sufficient for GRACE/GRACE-FO adjustment; and
- Developing machine learning models to describe GWS dynamics, utilizing as predictors the monthly averages organized in the spatial database.
Initial results highlight the application of various machine learning models for accurate TWS-GRACE prediction, emphasizing hyperparameter tuning and encoding spatial dependencies. As the database and algorithms evolve, these models aim to improve transboundary groundwater monitoring and management.
An additional novel component of the GRANDE-U collaboration involves analyzing global expertise in transboundary groundwater research. Using a co-authorship network analysis, the project identifies key contributors, emerging topics, knowledge gaps, and collaboration patterns across hydrogeological subdomains and related disciplines. The analysis tracks the formation and evolution of expertise clusters and explores subsets of the network based on environmental, socio-economic, and data-related issues mentioned in publication titles and abstracts. This network analysis is implemented on the SuAVE (Survey Analysis via Visual Exploration, suave.sdsc.edu) visual analytics platform, using OpenAlex, an open-access bibliographic database, to extract and tag relevant publications with keywords and aquifer names. The system provides interactive visualizations of the academic landscape and computes fragmentation and centrality measures for individual researchers and network subsets, offering valuable insights for enhancing international collaboration on transboundary groundwater issues.
GRANDE-U funding under the “International Multilateral Partnerships for Resilient Education and Science System in Ukraine” (IMPRESS-U) initiative, led by the U.S. National Science Foundation, is gratefully acknowledged.
How to cite: Zaslavsky, I., Samalavičius, V., Solovey, T., Brzezińska, A., Janica, R., Śliwińska-Bronowicz, J., Stradczuk, A., Bikše, J., Žaržojus, G., and Kunsakova, A.: Data-driven Modeling of Transboundary Aquifers in Conflict Zones: Challenges and Solutions from the GRANDE-U International Collaboration, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-7285, https://doi.org/10.5194/egusphere-egu25-7285, 2025.
Groundwater resources in hard-rock terrains are particularly susceptible to stress due to their intricate geological formations and limited recharge capacity. This study presents a novel methodology for assessing aquifer stress within the Barakar River Basin of the Chotanagpur Plateau, leveraging the integration of the Soil and Water Assessment Tool (SWAT) and advanced deep learning models. A comprehensive evaluation was conducted using 20 hydrogeological and socio-economic parameters, including precipitation, slope, land use, and aquifer lithology. Deep learning techniques, notably Convolutional Neural Networks (CNN), were utilised to classify aquifer stress zones into four categories: Low Stress, Moderate Stress, Semi-Critical, and Critical. The CNN model demonstrated superior performance, achieving an accuracy of 94% and effectively capturing aquifer conditions' spatial and temporal dynamics. Field validation via Electrical Resistivity Tomography (ERT) surveys substantiated the reliability of the model's predictions. Findings indicate that approximately 34% of the basin experiences moderate to critical stress levels, underscoring the urgency for targeted management strategies. This integrated approach offers a scalable and robust framework for sustainable groundwater management in hard-rock terrains, with significant implications for mitigating global water scarcity.
How to cite: Bera, A., Dutta, L., Kumar, R., and Pal, S. K.: Aquifer Stress Assessment in Hardrock Regions of the Chotanagpur Plateau Using Integrated SWAT and Deep Learning Models, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-803, https://doi.org/10.5194/egusphere-egu25-803, 2025.
Groundwater sustainability requires meeting current and future human needs while maintaining groundwater discharge and interactions with Groundwater-Dependent Ecosystems (GDE). The first step in including GDEs in water management policies is identifying their location and extent in the landscape. Approaches to mapping GDE include those based on expert knowledge and machine learning methods.
Meanwhile, Mexico is one of the countries currently facing major groundwater challenges due to intensive groundwater abstraction, land use change, and climate change, putting to risk the structure and function of GDEs. Therefore, GDE mapping is needed in Mexico to facilitate their inclusion in water management.
For this purpose, this study evaluated the performance of the Analytic Hierarchy Process (AHP) method and the Logistic Regression (LR) method to map GDEs using topographic, hydrogeological, structural, and vegetation variables obtained from remote sensing products and geospatial data in a study area located in Central Mexico. The two methods were compared by the AUC and ROC curve based on ground-truth data obtained from springs and groundwater-dependent wetland inventories.
The results show insights into each method's predictive power in identifying areas associated with GDEs, with AHP emphasizing the prioritization of criteria based on expert knowledge and LR revealing statistical relationships within the dataset.
The use of different explanatory variables and methods enables the development of distinct frameworks for GDE mapping, each with distinct strengths. Nevertheless, this study shows different approaches that can be successfully applied by decision-makers to map GDEs at local and regional scales and ease their inclusion into water management policies.
How to cite: Salgado Albiter, C., Olea Olea, S., Morales Casique, E., Ramírez-Serrato, N. L., and Medina Ortega, P.: Mapping potential groundwater-dependent ecosystems in Central Mexico: Expert knowledge and machine learning approaches, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-2936, https://doi.org/10.5194/egusphere-egu25-2936, 2025.
Estimating saturated hydraulic conductivity Kf from particle size distributions (PSD) is very common with empirical formulas, while the use of machine learning for that purpose is not yet widely established. We evaluate the predictive power of six machine learning algorithms, including tree-based, regression-based and network-based methods in estimating Kf from the PSD solely. We use a dataset of 4600 samples from the shallow Dutch subsurface for training and testing. The extensive dataset provides not only PSD, but also measured conductivities from permeameter tests. Besides training and testing on the entire data set, we apply the six algorithms to data subsets for the soil types sand, silt and clay. We further test different feature/target-variable combinations such as reducing the input to PSD-derived characteristic grain diameters d10 , d50 and d60 or estimating porosity from PSD. We test feature importance and compare results to Kf estimates from a selection of empirical formulas. We find that all algorithm can estimate Kf from PSD at high accuracy (up to R2/NSE of 0.89 for testing data and 0.98 for the entire data set) and outperform empirical formulas. Particularly, tree-based algorithms are well suited and robust. Reducing information in the feature variables to grain diameters works well for predicting Kf of sandy samples, but is less robust for silt and clay rich samples. d10 also shows to be the most influential feature here. An interesting, but not surprising outcome is that PSD is not a suitable predictor for porosity. Overall, our results confirm that machine learning algorithms are a powerful tool for determining Kf from PSD. This is promising for applications to e.g. deep-drilling data sets or low-effort and robust Kf -estimation of single samples.
How to cite: Zech, A., de Rijk, V., Buma, J., and Veldkamp, H.: Predicting saturated hydraulic conductivity from particle size distributions using machine learning, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-4425, https://doi.org/10.5194/egusphere-egu25-4425, 2025.
Preparing for drought conditions is complicated by the episodic nature of droughts and by our limited understanding of water systems’ response to extreme events. In this, models are useful tools to simulate a range of plausible to low likelihood drought conditions. Water managers may use these simulations to make plans and consider consequences for both normal and extreme drought events. However, critical in this is the representation of water system resilience to drought conditions and simulated management decisions to in/decrease drought resilience. Decision-making in groundwater management could herein benefit from a robust modelling approach that considers the complexity and uncertainty in water availability, dynamic impact of management and modelling setups available.
In this study, we have converted a lumped conceptual socio-hydrological model to an operational tool to support groundwater management in Great Britain by applying a response-based and a data-based model evaluation. In the response-based evaluation, we first examined the model consistency with our understanding of the system functioning, and the influence of modelled management scenarios on model predictions. In the data-based evaluation, we tested the accuracy of heavily influenced discharge and groundwater level predictions in three catchments representative of typical hydrogeological conditions and water management practices in Great Britain.
Results show consistent simulations across catchments and identified pointers for influential model parameters in drought conditions. Modelled water management interventions have varying influence on simulated model output. Most effective drought management scenarios have (elements of) integrated water storage use, which minimises shortages in water demand. The data-based analysis shows that calibration can be focused on either low flows or groundwater storage, with reasonable results for both model outputs. We provide a source-specific and ‘best overall’ calibration approach that capture groundwater levels and low flows, which also indicates how model parameters (dis)agree with open-source data and our model perception of the modelled water system.
How to cite: Wendt, D. E., Coxon, G., Salwey, S., and Pianosi, F.: SHOWER: A tool for groundwater drought management , EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-6890, https://doi.org/10.5194/egusphere-egu25-6890, 2025.
The Alcantara River basin, located in Sicily (Italy), encompasses an area of 606 km², including the northern slopes of Mount Etna, Europe's highest active volcano (3357 m a.s.l.). The river stretches for 55 km, originating from the Nebrodi Mountains at 1400 m a.s.l. and discharging into the Ionian Sea approximately 5.5 km south of Taormina (Messina). Groundwater significantly sustains the river’s flow. Irrigation and drinking water wells extract an average of 0.23 m³/s, while a drainage gallery collects water from three springs, supplying the Alcantara aqueduct with an average flow rate of 0.48 m³/s, as measured from January 2009 to December 2022.
To better understand the aquifer-river interactions and assess the impacts of groundwater extractions, the aquifer system was modeled using MODFLOW 6, a finite-difference numerical code developed by the U.S. Geological Survey (USGS). The study covered 14 years (2009–2022), leveraging monthly groundwater withdrawal records provided by the aqueduct operator. Hydraulic conductivity was calibrated using PEST, a software tool for parameter estimation and uncertainty analysis. Two scenarios were considered: (1) the current condition, including all known groundwater extractions, and (2) a hypothetical scenario without extractions. The model was validated by comparing observed and simulated discharge trends from the drainage gallery.
Simulation results revealed that groundwater extractions reduce natural spring discharge to the river by an average of 22%. This reduction shows significant seasonal variability, with the most pronounced impacts in spring and less severe effects in winter. Interestingly, despite this reduction, the midstream section of the river did not experience zero discharge, even during the driest periods (e.g., the summers of 2020 and 2021). This discrepancy suggests the influence of additional unaccounted factors, such as unauthorized or unrecorded water withdrawals, or potential hydrogeological changes induced by seismic activity.
These findings emphasize the need for systematic monitoring of groundwater and surface water resources. Enhanced monitoring would provide a deeper understanding of aquifer-river interactions, identify drivers of hydrological regime alterations, and inform strategies to optimize groundwater use and mitigate its impacts on river systems. Such efforts are essential for protecting the natural environment and ensuring the long-term availability of water resources.
How to cite: Silipigni, M., Di Salvo, C., Preziosi, E., Borzì, I., and Bonaccorso, B.: Hydrological Modeling of a Fractured Volcanic Aquifer to Analyze Interactions Between Anthropogenic Water Resource Usage and the Natural System, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-6734, https://doi.org/10.5194/egusphere-egu25-6734, 2025.
This study investigates the effects of groundwater extraction on saltwater movement in Berlin/Brandenburg's lower Spree catchment, a critical freshwater resource increasingly impacted by climate change and water scarcity. A high-resolution groundwater flow model was developed to simulate transient flow and saltwater dynamics. The model incorporates recharge data (1979–2019), pumping records (1994–2021), and a detailed geological framework derived from borehole data and cross-sections. Artificial neural networks (ANNs) were used to capture spatial heterogeneity, with the model discretized into ≈ 3.5 million active flow cells using a finite-difference approach with 100 m horizontal, 5 m vertical, and monthly temporal resolutions. The initial conditions determined through a spin-up period. Model calibration, supported by PEST, ensured robust performance in both steady-state and transient conditions.
Results reveal significant interactions between freshwater and saline zones, with prolonged extraction driving saltwater upconing. Scenario analyses highlight the sensitivity of saltwater movement to climate change, projecting accelerated saltwater intrusion under intensified pumping and reduced recharge conditions.
These findings underscore the need for adaptive groundwater management strategies, such as optimized pumping schedules and integrated management practices, and Managed Aquifer Recharge (MAR)to mitigate saltwater intrusion and ensure sustainable freshwater availability under changing climatic and resource pressures.
How to cite: Abdelrahman, A. A. A., Sauter, M., and Engelhardt, I.: Impact of groundwater extraction on saltwater movement in the lower Spree catchment under climate change and water scarcity, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-3175, https://doi.org/10.5194/egusphere-egu25-3175, 2025.
The Tulare Lake Basin (TLB) of California, a vital agricultural hub that covers the southern part of the Sierra Nevada and the Central Valley, is experiencing severe water scarcity due to climate change, rising water demand, and extensive groundwater depletion. This study leverages an integrated hydrological model to quantify Surface Water-Groundwater (SW-GW) interactions in the TLB. We focus on understanding seasonal water balance trends, variability in groundwater recharge, and the impact of snowmelt on groundwater storage. The integrated SWAT+gwflow model was calibrated and validated using observations of streamflow, evapotranspiration, snow water equivalent, and groundwater head. Our results revealed a decreasing trend in groundwater storage (-4.77 mm/year), with a greater deficit during prolonged droughts. Most of the groundwater fluxes have negative trends, including SW-GW exchange, saturated excess flow, and lateral flow. Boundary inflow exhibits a positive trend due to inflow from adjacent regions driven by hydraulic gradients caused by local groundwater depletion. Snowmelt emerged as a critical driver of groundwater recharge in the TLB, showing a stronger correlation in the spring (R2 >0.58) than fall and winter seasons (R2 < 0.5). These findings suggest exploring alternative means for groundwater recharge, as mountain snowpack is expected to decline in a warmer climate, such as capturing winter flood flows and the need for adaptive strategies to mitigate long-term water stress in the basin.
Keywords: Coupled Model; SW-GW Interactions; TLB
How to cite: Sinshaw, B. G., Viers, J. H., and Safeeq, M.: Modeling Surface Water - Groundwater Interactions in the Tulare Lake Basin, California, USA, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-7287, https://doi.org/10.5194/egusphere-egu25-7287, 2025.
Single-well push-pull tracer tests are broadly employed to estimate effective parameters for solute and heat transport in aquifers. Tracer recovery curves obtained from these tests serve as inputs for solving an inverse problem to infer effective transport parameters such as porosity, thermal and solute longitudinal dispersivities, and retardation factors. However, the inherent non-uniqueness of the inverse calibration problem and associated uncertainties in field measurements create a bottleneck for multiparametric calibration. To address these challenges, we employed a computationally efficient optimization framework based on surrogate modeling via Gaussian process regression (GPR) to approximate the objective function based on six effective transport parameters to be calibrated simultaneously, which yields plausible parameter combinations. For training and model evaluation, we implemented a 1D finite-difference (FD) representation of the advection-dispersion equation for sorbing tracers featuring an adaptive explicit time stepping scheme adhering to numerical stability criteria while minimizing numerical diffusion, where an analytical radial flow field serves as input based on well hydraulic properties. The FD model includes the measured input time series of temperature and concentration as transient boundary conditions, as well as well-bore storage to accurately model push-pull test conditions. We applied this framework to push-pull tests conducted in a sandy aquifer in Horonobe (Hokkaido, Japan) using heat and three solute tracers: uranine, lithium, and iodide. The confidence intervals for field measurements were included by using repeated under identical conditions tests. The surrogate model facilitates parameter optimization by balancing the exploration of high-uncertainty regions with the exploitation of high-probability regions through a weighted probability function. The posterior parameter distribution reveals reduced uncertainty intervals for porosity and both solute and thermal dispersivities while indicating low sensitivity for the solute retardation factor. The results demonstrate the necessity of high-precision measurements for concentration and highlight the value of utilizing multiple tracers to enhance calibration accuracy under parametric and measurement uncertainty. The developed framework highlights the benefit of using machine learning techniques combined with physics-based models to efficiently address stochastic parameter optimization under parametric uncertainty. The developed framework is a useful tool that enables time-efficient stochastic evaluation of computationally expensive models and optimization of push-pull tests.
How to cite: Petrova, E., Selzer, P., Kranz, S., Zeilfelder, S., Hebig, K. H., Machida, I., Marui, A., Blöcher, G., and Scheytt, T.: Surrogate model supported optimization of a multitracer push-pull test in Horonobe aquifer (Japan) under parametric uncertainty, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-5774, https://doi.org/10.5194/egusphere-egu25-5774, 2025.
Groundwater is becoming more important in sustainable water management, particularly in the context of climate change and intensive human interventions. Given that groundwater varies in space and time, it is important to predict both its dynamic processes and static patterns. However, lack of reliable groundwater data restricts the development of large-scale groundwater monitoring systems linking observations with modeling at spatial scales relevant for local decision making. In this study, we leverage existing physically-based modeling data and water table depth observations in the Contiguous United States (CONUS) and develop a machine learning-based downscaling tool to downscale 1-km modeling data to 1arcsec (~ 30 m). The modeling data were generated daily for the water year 2003 using ParFlow, a three-dimensional integrated hydrologic model. In addition, we input a range of meteorological, topographic, geological, and land use data, including daily precipitation and temperature, elevation, hydraulic conductivity, mean soil and clay contents, and land cover types. Based on tree-based machine learning models running on GPUs, the downscaling tool outputs a 1 arcsec water table depth map for the CONUS daily in a relatively short time. The resulting hyper-resolution water table depth map incorporates groundwater pumping and uncertainty, significantly advancing our understanding of groundwater dynamics across various scales, from the continental to small scales relevant to local decision-making. We also obtain the importance of input variables based on the results of the machine learning models, which is helpful for the future development of the groundwater monitoring system over the CONUS. While the downscaling tool is developed for the CONUS, it can be adapted to other regions with similar hydrogeological settings and substantial modeling data.
How to cite: Ma, Y., Tijerina-Kreuzer, D., Defnet, A., Condon, L., and Maxwell, R.: Advancing Large-Scale Hyper-Resolution Groundwater Modeling Using a Machine Learning-Based Downscaling Tool, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-13673, https://doi.org/10.5194/egusphere-egu25-13673, 2025.
Rapid population growth and agriculture development have led to unsustainable exploitation of groundwater, a trend likely to be exacerbated by future climate change. Managed Aquifer Recharge (MAR) emerges as a cost-effective strategy for replenishing depleted aquifers, thereby supporting long-term groundwater sustainability. However, the highly heterogeneous nature of groundwater processes necessitates fine spatial and temporal resolution models for designing and evaluating MAR. The high computational burden of physics-based model simulations constrains existing MAR studies to limited scenarios, missing opportunities to evaluate MAR potential across the full range of uncertainties from climate change, policy shifts, and infrastructure development. Recent advances in artificial intelligence offer a promising solution to the trade-off between high spatial-temporal precision and computational efficiency through surrogate models. In this study, we leverage recent advances in attention-based Graph Neural Networks (aGNN) to develop a surrogate model for MAR (GNN-MAR), which allows us to capture multi-scale network structures across river systems, groundwater flow, and MAR infrastructure. Trained on a high-resolution physics-based integrated surface water and groundwater model, GNN-MAR is tailored for two MAR approaches, i.e., in-channel recharge and agriculture MAR (Ag-MAR). We apply GNN-MAR to the Baoding Plain in the North China Plain, one of the world’s most severely groundwater depleted regions. The search for optimal MAR schemes is conducted within large ensembles generated under the XLRM (eXogenous uncertainties, policy Levers, Relationships, Measures) framework, which encompasses climate change scenarios, groundwater pumping policies (X), MAR schemes (L), GNN-MAR (R), and groundwater sustainability targets (M). The framework enables identification of MAR schemes robust to deep uncertainties. Our study provides valuable insights for the development of high-fidelity surrogate models for integrated surface-groundwater systems and demonstrate the potential of AI-based surrogate model for robust decision-making in groundwater recharge management.
How to cite: Guo, W., Li, M., Chen, H., and He, X.: Robust managed aquifer recharge (MAR) design aided by graph neural networks, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-7006, https://doi.org/10.5194/egusphere-egu25-7006, 2025.
Finding the initial state groundwater configuration of a catchment is one of the major challenges when simulating the hydrological cycle with an integrated hydrological model. The choice of this initial condition has a large impact on the results of the subsequent simulation, and it is often found by repeatedly running the hydrological model with constant atmospheric settings until the system equilibrates. These spin-up computations are computationally expensive and often require many years of simulated time, especially if the initial groundwater configuration before the spin-up computations is far from this steady state.
We hypothesize that existing large-scale groundwater simulations at steady state can be used to machine learn how steady-state depth-to-water tables (DTWTs) for groundwater depend on readily available data sources like large-scale conductivity and surface slopes. But how well can steady-state DTWTs be estimated by such ideas? How much computing speed can be gained with improved initializations of spin-up simulation? And how well does the estimation of improved initializations generalize across different geological settings and climate?
To answer these questions, we developed the machine learning emulator HydroStartML to accelerate the spin-up computation. HydroStartML is trained on converged steady-state DTWT distribution, and it generates a configuration of the DTWT of the respective watershed. This configuration is used as the starting configuration for spin-up computations. Doing so reduces the overall computational effort compared to the typical approach of initiating spin-up computations with a uniform DTWT across the whole catchment. HydroStartML is trained on the entire contiguous United States on spatially distributed patches with a fixed set of parameters.
Spin-up computations with these DTWT configurations as starting configurations converge faster and with a reduced computational effort compared to spin-up computations with other initial configurations. We found that HydroStartML is indeed able to generate DTWT configurations that are close to the steady state, even on unseen terrain. Although the generation of shallow DTWTs is possible with especially small errors, the strongest reductions in spin-up effort occurs in regions with deep DTWTs. This work opens the door for hybrid approaches that blend machine learning and traditional simulation, enhancing predictive accuracy and efficiency in hydrology for improving water resource management and understanding complex environmental interactions.
How to cite: Pawusch, L., Scheurer, S., Nowak, W., and Maxwell, R.: Development of a Combined Machine Learning and Physics-based Approach to Reduce Hydrologic Model Spin-up Time, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-10229, https://doi.org/10.5194/egusphere-egu25-10229, 2025.
Groundwater nitrate (NO3-) pollution is a pressing issue linked to agricultural practices, urbanization, and industrial activities. This study focuses on Taiwan’s groundwater nitrate nitrogen (NO3-N) contamination by integrating satellite remote sensing, groundwater monitoring, and various environmental factors using GIS. Data from 451 monitoring stations, sampled quarterly from 2020 to 2024, reveal that NO3-N concentrations generally range between 1–10 mg/L, while approximately 2% exceed Taiwan’s Drinking Water Quality Standards of 10 mg/L for NO3-N (equivalent to 44.3 mg/L NO3-). In this study, machine learning models, including Random Forest (RF), Multilayer Perceptron, and Support Vector Classifier, were employed to predict NO3-N contamination risk at three ranges of concentrations (<1, 1–10, >10 mg/L) using different feature combinations: (1) all features, (2) selective environmental factors, and (3) vegetation indices (VIs) alone. RF demonstrated the highest overall accuracy across all combinations, achieving 87% in Feature Combination I. For Feature Combination III, which only used VIs derived from remote sensing, RF achieved an OA of 68%, highlighting its potential for practical and efficient application without ground-based survey data. Key findings highlight the pivotal role of environmental variables, including VIs derived from Sentinel-2 multispectral imagery, terrain parameters from digital elevation models, and meteorological data in mapping contamination hotspots. Future work should integrate higher-resolution satellite imagery and more advanced parameters to improve model performance and decision-making accuracy.
How to cite: Hsu, Y.-C., Li, K.-Y., Podgorski, J., and Berg, M.: Remote Sensing-Driven Prediction of Groundwater Nitrate Risk: Insights from Machine Learning Applications in Taiwan, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-6502, https://doi.org/10.5194/egusphere-egu25-6502, 2025.
Groundwater is a critical source of drinking water and as demand increases on a global scale under climate change and population growth, a suitable quantity of clean groundwater must be ensured. Groundwater chemistry depends on environmental factors such as geology, climate, groundwater table and residence time, land use, and recharge source and rate. Geogenic compounds, such as arsenic (As), manganese (Mn), phosphorus (P), ammonium (NH4+), and iron (Fe), often occur in groundwater and are important determinants of groundwater quality. When exceeding recommended concentration limits in groundwater, these compounds can pose risks to human health and the environment, and cause problems in water treatment and distribution. In this study, we applied machine learning, i.e., classification algorithms and feature importance analysis, to investigate the spatial patterns of selected geogenic compounds and their governing factors. We used groundwater chemistry measurements from over 7,000 well intakes with mean depth of 47.8 m distributed across Denmark and 34 covariate maps including soil, geology, and hydrogeology information. Models are developed for As, Mn, total P, NH4+ and Fe, and achieve a balanced accuracy between 76% and 88%. The main results are prediction maps of 100 m resolution showing the probability of the selected geogenic compounds exceeding the concentration limits in groundwater recommended by Danish legislation. Our analysis advocates that the spatial variability of all selected compounds depends mostly on geological factors such as the thickness of Quaternary, accumulated clay deposits above chalk, and the depth to chalk formations. High concentrations of all studied geogenic compounds are predicted in areas with thick Quaternary and clay deposits, while low Mn and P predictions occur in areas where chalk is present at lower depths. Overall, we found that groundwater exceeds recommended concentration limits for As, Mn, P, NH4+ and Fe in 9.6%, 67.5%, 48.5%, 73.5% and 83% of Denmark’s area, respectively. Our results enhance the understanding of the processes driving groundwater quality in Denmark, which may be transferable to other domains with similar hydrogeological settings, e.g. northern America. The generated prediction maps can guide for identifying optimal locations for new wells and water treatment techniques, improving the overall groundwater resource management at national scale. Accordingly, this study shows how public high-quality databases can aid groundwater management.
How to cite: Xenakis, G. I., Jessen, S., Koch, J., and Kazmierczak, J.: Spatial machine learning predictions of geogenic compounds in groundwater, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-11772, https://doi.org/10.5194/egusphere-egu25-11772, 2025.
Meat production is a major contributor to global environmental degradation, including groundwater nitrate contamination driven by intensive fertilizer use and manure production. This study explores the environmental implications of substituting conventional meat products (beef, poultry, and pork) with alternative protein sources—plant-based, insect-based, and cultured meat—using the U.S. meat market as a baseline. Employing an eXtreme Gradient Boosting (XGBoost) model, we quantify the risk of groundwater nitrate exceedance and compare resource requirements such as fertilizer, water, and land use for conventional and alternative proteins.
Results indicate that a 10% substitution of meat protein with alternatives reduces fertilizer use by 3.4%, manure production by 10.7%, and water usage by 4.5%, leading to a 20% reduction in groundwater nitrate exceedance risk. Plant-based alternatives show the lowest environmental impact, while insect-based options demonstrate high feedstock efficiency. Cultured meat, despite its potential, currently exhibits higher resource demands due to production constraints. The study further highlights regional variations in substitution effects, driven by agricultural practices and climatic factors.
These findings underscore the environmental benefits of transitioning to sustainable protein sources, providing actionable insights for achieving Sustainable Development Goals (SDGs) related to water quality, food security, and climate resilience. This shift not only reduces environmental risks but also ensures the sustainable management of groundwater resources.
How to cite: Guo, Z. and Zhan, Y.: Shifting Protein Sources to Reduce Groundwater Nitrate Contamination: Insights from the U.S. Meat Market, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-2241, https://doi.org/10.5194/egusphere-egu25-2241, 2025.
Identifying contaminant sources is crucial for managing groundwater contamination, particularly in complex fracture networks. Traditional methods for source identification often face limitations such as sensitivity to data perturbations, reliance on simplified hydrological models, and challenges in handling the ill-posed nature of the inverse problem. This study introduces a novel application of Bayesian Evidential Learning (BEL) to quantify contaminant source uncertainty in fracture networks(Hermans et al., 2018; Thibaut et al., 2021).
BEL relies on learning a direct relationship between the target parameters (source location, release time, and concentration) and predictors (breakthrough curves (BTCs) and their statistical features). The learning step relies on the sampling of target parameters for which the release and transport of contaminant is simulated, and the resulting BTCs at the observation point extracted. The complexity of the training process was mitigated by incorporating falsification to classify the prior model(Yin et al., 2020). One-hot encoding then was employed to discretize potential source locations, enhancing the correlation between predictor and target using principal component analysis (PCA) and canonical correlation analysis (CCA) (Figure 1). Experimental data and numerical simulations of solute transport in fracture networks were then employed to validate the BEL framework (Figure 2).
Results demonstrate that BEL not only achieves accurate predictions on the source location, release time and concentration, but also provides robust uncertainty quantification for contaminant sources. These findings highlight BEL's potential as a powerful tool for improving source tracking and remediation strategies in groundwater systems. Future research should consider uncertainty in the fracture network and hydraulic properties of the fractures.
Figure 1. Multivariate analysis of training data. A. The explanatory power of data across different PCs in the PCA space. B-E are the bivariate distributions of predictor and target data in the CCA space.
Figure 2. Posterior distribution predictions for contaminant source information. Red lines correspond to test data
References
Hermans, T., Nguyen, F., Klepikova, M., Dassargues, A., & Caers, J. (2018). Uncertainty Quantification of Medium-Term Heat Storage From Short-Term Geophysical Experiments Using Bayesian Evidential Learning. Water Resources Research, 54(4), 2931–2948. https://doi.org/10.1002/2017WR022135
Thibaut, R., Laloy, E., & Hermans, T. (2021). A new framework for experimental design using Bayesian Evidential Learning: The case of wellhead protection area. Journal of Hydrology, 603, 126903. https://doi.org/10.1016/j.jhydrol.2021.126903
Yin, Z., Strebelle, S., & Caers, J. (2020). Automated Monte Carlo-based quantification and updating of geological uncertainty with borehole data (AutoBEL v1.0). Geoscientific Model Development, 13(2), 651–672. https://doi.org/10.5194/gmd-13-651-2020
How to cite: Miao, K., Huang, Y., Zhang, L., Guo, L., and Hermans, T.: Quantifying Groundwater Contaminant Source Uncertainty in Fracture Networks Combining Falsification and Bayesian Evidential Learning, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-11456, https://doi.org/10.5194/egusphere-egu25-11456, 2025.
Machine learning models, particularly Random Forests (RF), are increasingly used to regionalize environmental pollutants based on point measurements. Spatial variants of RF are emerging to account for geospatial data characteristics, such as spatial autocorrelation and non-stationarity. However, systematic comparisons of these spatial RF variants remain limited.
This study evaluates seven spatial RF variants and compares them to non-spatial RF, universal kriging (UK), a well-established geostatistical method, and multiple linear regression (MLR). Using nitrate concentrations in groundwater from two contrasting hydrogeological macro-regions in Germany, we assess predictive performance (mean absolute error) across varying prediction distances using spatial cross-validation.
The results show minor differences among spatial RF variants, except for the notably lower performance of Random Forest Spatial Interpolation (RFSI) at long prediction distances. Over short distances (within the practical range of spatial autocorrelation), spatial RF variants outperformed non-spatial RF and MLR. The RF-oob-OK method, which applies ordinary kriging on the out-of-bag errors, demonstrated consistently strong performance with acceptable computational efficiency. However, it did not substantially surpass UK in predictive performance.
Computationally manageable spatial RF variants, such as RF-oob-OK, represent viable alternatives to traditional geostatistical methods for spatial prediction of environmental pollutants, effectively exploiting both spatial predictors and autocorrelation.
How to cite: Frank, J., Suesse, T., Jiang, S., and Brenning, A.: Do spatial random forest variants improve the regionalization of environmental pollutants? - The case of groundwater nitrate concentration, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-18245, https://doi.org/10.5194/egusphere-egu25-18245, 2025.
Accurate prediction of the contaminant plumes in groundwater systems are critical for effective pollution management and risk assessment. Effective simulations for reliable predictions require two key pieces of information. The first is detailed knowledge of the aquifer system, including subsurface structures and the hydrogeological heterogeneity of hydraulic parameters. The second is data about the contaminant plume, including its source, spatial distribution, and concentration. However, acquiring and analyzing this data is often costly and labor-intensive due to the extensive collection efforts and complex processing techniques required.
To address these challenges, we developed an innovative machine learning prediction approach. The architecture of the model combines fully connected layers followed by convolutional layers. The training dataset for the machine learning model was generated using a numerical simulation model of groundwater flow and contaminant transport processes in a synthetic aquifer. Monitored contaminant concentration data were used as inputs to the machine-learning model, while contaminant plume distributions (e.g., concentration fields spanning from the initial contaminant release to 10 years in the future) served as outputs. The machine learning models are trained and evaluated under two scenarios: (1) assuming aquifer properties are well-known, (2) aquifer properties are unknown. According to the results, in scenario 1, the prediction of the contaminant field at various time is highly accurate: the predictions resemble the reference at high degree. In scenario 2, prediction accuracy decreased but remained effective: the predicted contaminant plume closely matched the overall structure of the reference distribution. The main advantage of this machine-learning approach is its capability to directly analyze monitoring data and predict the transient groundwater contaminant transport processes, the labor-intensive steps of aquifer characterization and initial contaminant field determination are eliminated. Moreover, the results not only forecast future evolution but also allow for historical tracing, all the way back to its initial release point, thus it provides a comprehensive understanding of the contaminant's lifecycle.
How to cite: Wang, C., Dou, Z., Yang, Y., Chen, Z., Hu, R., Zhao, Y., and Wang, J.: A Machine Learning Approach for Predicting Contaminant Plume Evolution in Groundwater systems, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-20774, https://doi.org/10.5194/egusphere-egu25-20774, 2025.
Amid escalating water scarcity and the pressing need for sustainable water management, especially in arid and semi-arid regions, this study emphasises the importance of developing precise and efficient geospatial methods to evaluate groundwater potential in complex karst landscapes. This research focuses on Khuzestan Province in southwestern Iran, employing advanced Machine Learning (ML) techniques—namely, Artificial Neural Networks (ANN) and Support Vector Machines (SVM)—to map groundwater potential zones. The goal is to enhance resilience and promote sustainable water resource management in the region. A comprehensive array of topographic, geological, hydrographic, edaphic, and meteorological data was collected, processed, and integrated into a Geographic Information System (GIS) database to establish key conditioning factors for predictive modelling. After conducting a spatial multicollinearity analysis, the selected input variables included elevation, slope, aspect, multiple topographic indices, relief energy, heat load index, drainage density, lithostratigraphic units, fracture density, land use/cover, NDVI, and precipitation. Hydrogeological data, such as water-table depth and spring locations, obtained from official records, were also integrated to assess the performance of modelling outputs. Two predictive models—using ANN and SVM—were developed to generate groundwater potential maps for the study area. Both models demonstrated high predictive accuracy, highlighting unique strengths in capturing the complex spatial patterns of karst environments. This methodological approach shows promise as a reliable, globally applicable framework for groundwater potential mapping in similar karst regions. By offering valuable insights for hydrogeologists and policymakers, this approach supports enhanced groundwater exploration strategies and fosters sustainable water management in water scarcity regions.
How to cite: Pourmorad, S., Kabolizade, M., Ferreira, R., Mohammadi, S., and Antonio -Dimuccio, L.: Comparative Analysis of ANN and SVM for Groundwater Potential Mapping in Karst Terrains of Southwestern Iran, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-640, https://doi.org/10.5194/egusphere-egu25-640, 2025.
Fluctuation of shallow groundwater (GW) characteristic in plains and lowlands is regulated by recharge from precipitation and groundwater evapotranspiration under natural conditions. Here a simple 1D (pointwise) model is presented that is capable of reproducing the dynamics of shallow GW levels at monthly, weekly or even daily time scale at the location of groundwater level monitoring wells using precipitation and potential evapotranspiration as input variables. The model utilizes the empirical curve describing the dependence of GW evapotranspiration on the depth of water table, revealed by analyzing historical measured GW level and evapotranspiration time series in the Great Hungarian Plain. Besides GW levels, the model calculates groundwater recharge and evapotranspiration. Soil and hydrological parameters of the model are calibrated based on measured GW levels.
Potential fields of application of the model are shown through Hungarian examples: 1) Using precipitation and potential evapotranspiration data of various climate models, expected alterations of shallow GW levels due to climate change can be predicted. 2) By comparing measured and simulated GW levels, alterations in GW levels and fluctuation due to anthropogenic activity (e.g. GW abstractions) can be revealed. 3) Data gaps in measured GW level time series can be filled by the model. 4) Extending the time series of measured GW levels into the past allows for historical analyses, e.g. the temporal changes of GW supply of dependent ecosystems.
How to cite: Ács, T., Kozma, Z., Decsi, B., and Simonffy, Z.: Modelling shallow groundwater fluctuation based on water table depth – groundwater evapotranspiration relationship, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-16851, https://doi.org/10.5194/egusphere-egu25-16851, 2025.
Groundwater recharge is a key input in groundwater resources management. However, it is not directly measurable, and even the parameters for indirect estimation are difficult to obtain and verify. We developed a hydrological model that facilitates reliable calibration of specific yield of an aquifer, thus enabling groundwater recharge estimation by the water table fluctuation method. The novel soil moisture deficit model is based on existing bucket models. It features two parallel soil water reservoirs which capture all incoming precipitation. Groundwater recharge is generated only when the reservoirs are overfilled after satisfying evapotranspiration. The only input data required are easily measurable (and typically available) time series of precipitation and air temperature, and long-term record of water table fluctuations in wells for calibration. The model parameters, most importantly specific yield, are calibrated by comparing the modelled water table to the observed water table. The calibrated specific yield and the observed water table levels then serve as inputs for water table fluctuation method for estimation of groundwater recharge. The model was tested on 9 wells in the lowland along the river Elbe (Czech Republic). The wells are situated in highly permeable alluvial aquifers with unconfined water table. The wells were selected for the study because decades of water table records are available, and their water table exhibits multi-year fluctuations. The values of specific yield obtained by model calibration ranged from 5% to 17%, which is realistic for the studied aquifer type. The results were compared to a previous study conducted in the Czech Republic, in which the long-term mean groundwater recharge was estimated. Our results lie within the range indicated for the sites. Furthermore, the presented method provides the temporal distribution of groundwater recharge, thus broadening the knowledge of groundwater recharge dynamics. Besides this, the method can potentially be used to estimate the groundwater recharge under future climate conditions.
Acknowledgements
The study was supported by project SS02030040 "PERUN - Prediction, Evaluation and Research for Understanding National sensitivity and impacts of drought and climate change for Czechia", co-financed with state support of the Technology Agency Czech Republic as part of the Program Environment for Life. We would like to thank Mgr. Tomáš Ondovčin, Ph.D. for consultation of saturated zone modelling, and Mgr. Martin Lanzendörfer, PhD. and Ing. Jan Černý for aid with mathematical formulation of the SMD model.
How to cite: Šabatová, K. and Bruthans, J.: Calibration of the water table fluctuation method based on groundwater recharge model using easily available data, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-8737, https://doi.org/10.5194/egusphere-egu25-8737, 2025.
The interaction between surface water and groundwater plays a crucial role in effective water resource management. In Saxony, Eastern Germany, lakes and reservoirs contribute significantly to the public water supply, alongside groundwater to a lesser extent. Despite growing attention to comprehensive studies of the region's water resources, the complex dynamics between streamflow and groundwater levels remain insufficiently explored. This research aimed to address this gap by providing a detailed analysis of these interactions using time series data.
To bridge this gap, the research framework integrated preprocessing techniques, feature-based characterization and clustering of groundwater level time series, and Convergent Cross-Mapping (CCM) applied to coupled groundwater level and discharge datasets. CCM, which uses time series data to identify causal relationships within dynamic systems, their direction and strength, was used to study the interactions between groundwater and streamflow in different regions of Saxony, Germany. Data from 597 groundwater level and 190 discharge time series have been used. The study also employed R, MATLAB, and QGIS for data processing and analysis, based on publicly available GitHub repositories and official documentation from previous studies.
The results revealed significant spatial variability in groundwater-stream interactions, with high levels of interaction identified in catchments such as the Elbe and Schwarze Elster, and lower levels of interaction in urban and agricultural areas. In regions such as Lausitz, geological and soil factors strongly influenced the streamflow-groundwater dynamic, with more complex interactions in areas with loess and highland soils. Factors like land cover and soil type played a significant role, as urbanization and land use changes can reduce groundwater recharge rates and disrupt natural water pathways. These findings underscore the importance of spatially distributed data for understanding the drivers of water system behavior and regional water resource management.
In conclusion, this study demonstrated the value of integrating time series data analysis methods, such as CCM, to enhance the understanding of hydrological dynamics in Saxony. The results provided insights into areas of high groundwater-streamflow interaction, highlighted the role of influencing factors, and emphasized the need for spatially detailed hydrological assessments to inform future water resource management strategies in the region.
How to cite: Vela Castillo, M. A., Hartmann, A., and Liu, Y.: Assessing Surface-Groundwater Interactions Using Time-Series Clustering and Convergent Cross Mapping: A Case Study of Saxony, Germany, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-18480, https://doi.org/10.5194/egusphere-egu25-18480, 2025.
The Yellow River basin (YRB) is the second-largest river basin in China , flowing through arid regions. The development and utilization of water resources, including irrigation, urban water supply, and industrial use, face significant challenges (Lin et al., 2019;Qu et al., 2020). Although groundwater resources are abundant, they are constrained by excessive extraction and declining water tables (Lin et al., 2020), posing substantial challenges for water resource management, especially as the global water scarcity issue becomes increasingly prominent. It is challenging to estimate groundwater level at a regional or catchment scale due to its natural heterogeneity.
Here, we use a large sample of groundwater observations, together with datasets from the Global Land Data Assimilation System (GLDAS) and the Gravity Recovery and Climate Experiments (GRACE), to build a machine learning approach — random forest— for predicting regional groundwater levels in the Yellow River Basin of China.
We demonstrated the robustness of this model, with an R² of 0.95 at calibration mode and R² of 0.91±0.009 at a 10-fold cross-validation mode with 100 repetitions. Compared to the spatial predictability, its temporal predictability is less accurate, with R² value of 0.72 for a test period of April-May in 2023. The spatial distribution maps of the groundwater levels in Yellow River Basin showed strong seasonal declines in fall and winter, with severe decreases concentrated in the middle and lower reaches. Overall, this paper shows that it is promising to estimate regional groundwater levels based on machine learning with a large sample of groundwater observations, providing a robust and comprehensive data foundation for groundwater analysis.
References
Lin, M., Biswas, A., & Bennett, E. M. (2019), Spatio-temporal dynamics of groundwater storage changes in the yellow river basin. Journal of Environmental Management, 235, 84-95. https://doi.org/10.1016/j.jenvman.2019.01.016.
Lin, M., Biswas, A., & Bennett, E. M. (2020), Socio-ecological determinants on spatio-temporal changes of groundwater in the yellow river basin, china. Science of The Total Environment, 731, 138725. https://doi.org/10.1016/j.scitotenv.2020.138725.
Qu, S., Wang, L., Lin, A., Yu, D., Yuan, M., & Li, C. a. (2020), Distinguishing the impacts of climate change and anthropogenic factors on vegetation dynamics in the yangtze river basin, china. Ecological Indicators, 108, 105724. https://doi.org/10.1016/j.ecolind.2019.105724.
Keywords:Random forest model; Groundwater level depth; GLDAS; GRACE
How to cite: Cao, Y. and Zhang, Y.: Estimating regional groundwater level by fusing satellite, model and large-sample observations inputs, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-5408, https://doi.org/10.5194/egusphere-egu25-5408, 2025.
The development of purely data-driven approaches for groundwater level prediction is crucial for sustainable groundwater management, offering the ability to predict groundwater levels across numerous monitoring wells and large geographical regions. Especially in arid regions, groundwater resources are under pressure, as seen in areas like Brandenburg, Germany, which is characterized as the driest federal state with the highest number of lakes. Here, data-driven approaches can enable fast and accurate seasonal groundwater level predictions, supporting local authorities in managing sustainable utilization.
Unlike traditional numerical models, which are computationally expensive and require complex parameterization when applied to large geographical areas, data-driven models provide a scalable solution. Recent studies have demonstrated the potential of machine learning (ML) approaches, particularly different deep neural network architectures, to provide accurate groundwater level predictions. In these studies, recurrent neural networks, such as Long Short-Term Memory networks (LSTMs), as well as recently developed architectures like the Temporal Fusion Transformer (TFT), which combines LSTMs with the self-attention mechanisms, and Neural Hierarchical Interpolation for Time Series Forecasting (N-HiTS), which is a time-series decomposition algorithm based on multilayer perceptrons (MLPs), have been used. Another recently developed architecture, the Time-series Dense Encoder (TiDE), which is based on MLPs and residual blocks, has further expanded the toolkit for time-series prediction.
In this study, we evaluate and compare the performance of four deep learning (DL) architectures (LSTM, TFT, N-HiTS, and TiDE) in predicting groundwater levels up to 16 ahead, using a wealth of spatial and temporal information for over 1,000 monitoring wells across Brandenburg. Input features to our models include historical groundwater level measurements, climatic variables, and static physical characteristics, such as groundwater recharge and land cover. Our analysis identifies the environmental conditions under which these models achieve a good predictive performance accuracy and assesses their ability to capture varying groundwater dynamics, thereby testing their alignment with hydrogeological system understanding. Furthermore, we assess whether the static features enhance the models performance and facilitate generalization across monitoring wells with similar static features levels, which we test through ablation studies and spatial out-of-sample cross-validation.
Our findings provide valuable insights into the strengths and limitations of different DL architectures for groundwater level prediction, highlighting their potential to support sustainable groundwater management in regions facing water scarcity.
How to cite: Kunz, S., Wetzel, M., Engel, M., and Broda, S.: Deep Learning Models for Seasonal Groundwater Level Prediction, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-15537, https://doi.org/10.5194/egusphere-egu25-15537, 2025.
Groundwater which is the most valuable resource available on the Earth`s surface and is used for drinking, irrigation, livestock, etc is depleting day by day. Groundwater level prediction faces complex challenges to sustainably manage this vital resource. Predicting groundwater level is crucial for water resource management. Here this study explores the use of some hybrid machine learning models such as SVM-FFA, SVM-PSO and compared with the stand alone SVM approach. Then introducing an innovative approach for predicting groundwater level with improved accuracy and to enhance the performance of the model and face the challenges developed during the process. This work investigates hybrid machine learning techniques to improve the accuracy of groundwater levels predictions, which are constrained in conventional hydrological models. The study uses long time series of monthly data from 2008-2024 taking precipitation, evaporation, temperature, and relative humidity as input features from Balipatana block of Khordha district of Odisha, India. In this analysis, performance metrices like Root Mean Square Error (RMSE), Coefficient of determination (R2), Mean Absolute Error (MAE) and Willmott Index (WI) were employed. It is found that the value of RMSE, R2, MAE, WI are 8.5832, 95.6756, 10.9438, 94.2981; 13.2287, 93.0073, 15.9084, 91.6327; 21.9627, 88.2165, 24.1689, 86.8491 in case of SVM-FFA, SVM-PSO and SVM respectively. The results demonstrates that the SVM-FFA models performs much better than the SVM-PSO and standalone methos in improving their accuracy and their robustness. With high prediction exactness and strategic versatility, the proposed model proved a powerful selection for forecasting groundwater levels.
How to cite: Biswakalyani, C., Samantaray, S., and Satapathy, D. P.: Prediction of Groundwater Level Using Hybrid SVM-FFA Approach, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-1501, https://doi.org/10.5194/egusphere-egu25-1501, 2025.
Groundwater is an important water resource that is widely used worldwide for agricultural, industrial, and domestic purposes. In the case of Jeju Island, located in southern South Korea, groundwater is an indispensable water resource that accounts for 82% of the total water supply. Therefore, scientific prediction and management of groundwater levels are very important for the sustainable use of groundwater by citizens. This study additionally used precipitation data from the Baekrokdam Climate Change Observatory located on the summit of Jeju Island in artificial intelligence (AI) models to accurately predict one-month-ahead future groundwater levels for the mid-mountainous areas of Jeju Island, where groundwater levels are highly variable. In other words, the AI models compared and analyzed the improvement effect of the monthly groundwater level prediction performance for 1) using precipitation data from two rainfall stations, groundwater withdrawal data from two groundwater sources, and groundwater level data from two monitoring wells in the study area, and 2) adding precipitation data from Baekrokdam Climate Change Observatory. The study subjects are two groundwater level monitoring wells located at 435-471m above mean sea level in the southeast of Jeju Island. The AI models used to predict groundwater levels are Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM), a deep learning AI model.
As a result, when the Baekrokdam precipitation data were not used, the two AI models showed excellent groundwater level prediction performance with Nash-Sutcliffe efficiency (NSE) values of 0.871 or higher. The LSTM model showed relatively higher prediction performance for high and low groundwater levels than the ANN model. This means that the LSTM model adequately incorporates the seasonal effects of wet and dry periods into groundwater level simulations. The more volatile the observed groundwater level, the more difficult it is for the AI models to interpret the characteristics of groundwater level fluctuations, and the lower the performance of predicting future groundwater levels. When additional Baekrokdam precipitation data were used, the two AI models showed improved groundwater level prediction performance by having NSE values of 0.907 or higher. This means that the additional use of precipitation data located in the uppermost region provides more information to help interpret groundwater levels, allowing AI models to better interpret the characteristics of groundwater level fluctuations. In addition, the use of Baekrokdam precipitation data was more helpful in improving groundwater level prediction for the monitoring well, which has highly variable groundwater levels that are difficult to predict, and the ANN model with relatively low groundwater level prediction performance. When additional Baekrokdam precipitation data was used for a specific monitoring well, the groundwater level prediction performance of the ANN model was improved to a level comparable to that of the LSTM model, which is a deep learning AI, even with a relatively simple ANN model structure. This is an example of how important it is to use additional useful data in research using AI models.
How to cite: Shin, M.-J., Kim, J.-H., Kang, S.-Y., Moon, S.-H., Kim, J.-W., Koh, H.-J., and Moon, S.-H.: Impact of using additional precipitation data from the uppermost region on improving the performance of AI models in predicting groundwater levels, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-166, https://doi.org/10.5194/egusphere-egu25-166, 2025.
One major challenge in reliable groundwater level forecasting is to correctly account for the amount and rate of precipitation percolating through the unsaturated zone prior to reaching the aquifer. Especially under a changing climate already impacting weather and climate extremes globally, increased frequency of heatwaves, heavy precipitation, and drought periods will have significant impact on recharge patterns through soil hydraulic properties and unsaturated zone dynamics. However, as soon as groundwater predictions concern long-term environmental changes, extrapolations beyond the short-term often lack to fully account for increased frequency of extreme events under climate change. Consequently, estimates and forecasts overlook the actual impacts of weather extremes, particularly imprinting themselves in changes in the hydraulic connection between groundwater and soil surface.
We used weekly groundwater level data (1990 – 2024) from over a hundred measuring wells, well distributed over the federal state of Brandenburg, Germany, to train a deep neural network, that is able to predict groundwater level development under the impacts of climate change. To account for the soil hydraulic properties, we included soil moisture from different depths as a proxy for the amount and timing of water percolating through the vadose zone.
We show that purely climatic inputs, such as air temperature and precipitation are not sufficient to explain regional groundwater level development, as suggested by previous studies. Instead, including soil moisture turns out be the factor with the highest impact (feature importance) on the entire regional model, increasing the explained variance for most sites, while being able to reduce the model error constantly (RSME). Our findings demonstrate that future predictions of groundwater level can be enhanced by integrating the effects of climate on soil moisture into predictive models.
How to cite: Eckert, M.-C. and Rudolph, A.: The Impact of Soil Moisture on Groundwater Level Forecasting Using Deep Neural Networks: Evidence from Brandenburg, Germany, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-2148, https://doi.org/10.5194/egusphere-egu25-2148, 2025.
Understanding the impact of hydrological uncertainty on soil slope stability is crucial for assessing slope failure risks in heterogeneous terrains. This study aims to investigate how heterogeneity in hydraulic properties influences slope stability and groundwater dynamics.
A total of 3,500 realizations of hydraulic conductivity fields were generated, with heterogeneities inclined at a 20-degree dip to mimic realistic subsurface conditions. To generate stochastic hydraulic conductivity fields, we employed a Gaussian random field model with specified mean, variance, and spatial correlation lengths. These fields were transformed into log-normal distributions to represent the natural variability of hydraulic conductivity in soils. Similarly, saturated water content was also generated as a random field to account for its spatial variability and its correlation with hydraulic conductivity heterogeneity. Using FEMWATER, we simulated unsaturated and saturated flow processes for each realization, capturing the spatial and temporal variability of water movement within the slope. Uncertainty analysis was then performed to evaluate the statistical properties of the flow and groundwater levels, including variance, covariance, and cross-variance.
The results highlight the variability in groundwater flow patterns and the envelope of groundwater levels under stochastic conditions. The uncertainty analysis revealed significant influences of hydraulic conductivity on flow behavior, characterized by variance, covariance, and cross-variance. These findings provide a comprehensive understanding of the stochastic behavior of hydrological processes in heterogeneous slopes and contribute to a more robust framework for predicting slope stability under uncertain hydrological conditions.
How to cite: Vu, P. T., Kuo, C.-Y., Ni, C.-F., Lee, I.-H., Lin, Y., and Tran, T. K. T.: Hydrological uncertainty in stochastic heterogeneous soil slope, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-5170, https://doi.org/10.5194/egusphere-egu25-5170, 2025.
A physics-informed neural network (PINN) is developed to predict groundwater level (GL) fluctuations based on precipitation time-series data, integrating both physics-based principles and data-driven learning to improve the prediction accuracy and robustness. The proposed PINN model embeds the governing equations of groundwater flow dynamics within a gated recurrent unit (GRU), ensuring that predictions adhere to physical laws while leveraging historical data patterns. The model’s performance is evaluated against two benchmark models: (i) a purely physics-based linear reservoir model and (ii) a data-driven GRU model. The results demonstrate that the PINN model outperforms both benchmarks, particularly under reduced time resolution, maintaining stable accuracy through its integration of physics-based information. Quantitative metrics, including the root mean squared error (RMSE) and correlation coefficient (CC), confirm the superior predictive capability of the PINN model, indicating its resilience to data limitations and noise in real-world monitoring data. As such, this study underscores the advantages of incorporating physics information into neural networks, and demonstrates that the PINN approach provides robust predictions even with limited data, which makes it ideal for complex aquifer systems and endows it with significant potential for supporting real-world groundwater management.
How to cite: Jeong, J. and Jeong, J.: Development of Physics-informed Recurrent Neural Network to Predict Actual Groundwater Level Fluctuation according to Precipitation Time-series Event, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-5434, https://doi.org/10.5194/egusphere-egu25-5434, 2025.
Groundwater plays a critical role in the global water cycle, serving as a primary source of freshwater for agriculture, industry, and domestic use.However, overexploitation of groundwater resources, coupled with the impacts of climate variability, has led to severe consequences. In agriculturally intensive regions, groundwater pumping for irrigation constitutes a significant portion of total water use. Variations in pumping practices, crop types, and irrigation methods result in pronounced spatial and temporal differences in groundwater extraction. Inefficient irrigation practices further exacerbate water losses, underscoring the need for data-driven approaches to enhance water-use efficiency. Machine learning techniques have emerged as transformative tools for groundwater level prediction. Temporal Convolutional Networks (TCN), a deep learning model, are particularly well-suited for this purpose due to their ability to capture long-range temporal dependencies in time-series data with superior computational efficiency. This approach not only ensures improved computational performance and scalability but also makes TCN more resilient to missing or proxy data, such as using power consumption as a substitute for direct pumping volume measurements, enhancing its real-world applicability. In this study, monthly groundwater level records from 2007 to 2023 from nine monitoring wells in a high-density agricultural area were collected, along with precipitation, and pumping data. In the absence of direct pumping volume measurements, power consumption data from pumping wells were utilized as a proxy for groundwater discharge. According to the registered purposes of these wells, they were classified into 14 groundwater usage categories, including irrigation for different crops, aquaculture, and livestock. The TCN model demonstrated robust predictive performance, with RMSE, MAE, and R² values ranging from 0.938–2.966 m, 0.797–2.477 m, and 0.66–0.891, respectively, during training, and 0.523–2.697 m, 0.426–2.288 m, and 0.821–0.842, respectively, during testing. Results from SHAP analysis revealed that precipitation and groundwater pumping for rice irrigation were the dominant factors influencing groundwater level variation. These findings emphasize strong generalization capability, computational efficiency, and ability to learn complex temporal relationships of TCN model. The interpretability and adaptability of TCN model make it an invaluable tool for improving agricultural water management practices, addressing the challenges of groundwater sustainability and climate variability. Furthermore, by incorporating downscaled meteorological forecasts from IPCC AR6 into this developed model, coupled with projected power consumption patterns of pumping wells, the model can efficiently predict future groundwater level variations. This approach has significant implications for policy-making related to groundwater and surface water resource management, promoting sustainable agricultural development and resource conservation.
How to cite: Wang, S.-W., Chen, Y.-Y., and Chen, W.: Data-driven groundwater level prediction in agricultural areas using temporal convolutional networks, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-5562, https://doi.org/10.5194/egusphere-egu25-5562, 2025.
This study addresses the escalating challenges associated with high near-surface groundwater levels in Lemvig Municipality, focusing on two distinct sites: an agricultural field and an urban area, both of which are experiencing issues with near-surface groundwater levels. The research aims to develop a comprehensive understanding of groundwater dynamics and their response to precipitation events in these areas.
A network of 82 IoT groundwater loggers, distributed across the two areas with distances between boreholes as close as 30 meters, monitors the near-surface groundwater levels at intervals down to every 15 minutes. The high-resolution data enables the calculation of weekly reconstructed groundwater tables and estimation of flow patterns for both locations, identifying regions at risk of flooding from high groundwater levels. The study also examines the areas response to rainfall events and hence their vulnerability to extreme precipitation. An estimation of the necessary data density required to perform the analyses will be provided, ensuring that the results are adequate for stakeholders to implement targeted climate adaptation and management of the near-surface groundwater.
Due to the high near-surface groundwater levels the water utility sewer-system in the two areas experiences at present an excessive water inflow, particularly during the winter months. Data from the areas have already been used to confirm infiltration into the sewer-network and to identify areas where sewers are likely situated below the groundwater table. This information is crucial for managing the water supply and mitigating the impacts of high groundwater levels. The data gathered in this study is thus already offering valuable insights into effective groundwater management and climate adaptation strategies.
The study will proceed with developing a process-based hydrological model and use data driven techniques to investigate the potential of enhancing prediction accuracy for different scenario calculations.
How to cite: Mathiasen, R. F., Andersen, T. R., and Rasmussen, M.: Integrating Data-Driven Approaches and High-Resolution Data for Enhanced Groundwater Management in Lemvig Municipality, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-8584, https://doi.org/10.5194/egusphere-egu25-8584, 2025.
This work aims at reliably modeling water table fluctuations, in an operational groundwater management perspective. It is based on a large set of ca 100 piezometers, representative of the hydrogeological diversity of French groundwater exploitations (mostly aquifers presenting dual-porosity dynamics, often located in the phreatic domain).
This study, a component of the Water Resources Forecast SUEZ’s project, partially funded by the French Ecological Transition Agency (ADEME’s innov’eau initiative), compares several approaches for the modelling of daily piezometric head and its fluctuations induced by recharge:
- a conceptual model (derived from an existing rainfall-runoff hydrological model, whose ability to reproduce piezometric time-series — through one of its conceptual reservoirs);
- a classic AI approach (a non-parametric and data-based method using random forest algorithms applied to data-engineered features, e.g. rolling sums of meteorological inputs);
- a few hybrid approaches resulting from various combinations of the two previous solutions.
All the above mentioned methods use daily meteorological data (precipitation and evapotranspiration time series) as inputs for the modeling chain. Model efficiency is assumed at the daily step using the Nash-Sutcliffe efficiency criterion, over three distinct 5-years periods where observed piezometric time-series are available.
Based on our results, we discuss the potential of using hybrid models for short-, medium- and long-term operational forecasting.
How to cite: Grech, G., Sakarovitch, C., Malaize, A., and Andréassian, V.: Hybrid modelling of piezometric head – a large sample test, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-12241, https://doi.org/10.5194/egusphere-egu25-12241, 2025.
Clustering of groundwater level data is crucial for water resource management, as it increases the efficiency of models in distinctly predicting specific hydrogeological patterns in aquifer systems. Traditional methods mostly rely on spatial or time series distance metrics, neglecting the impact of external inputs (rainfall, evapotranspiration, etc.) on aquifer systems. This study introduces an innovative machine learning-based approach to model aquifer systems at the piezometer level. While our flexible methodology accommodates any model and input, we selected a random forest model for its lightweight nature and interpretability. This model-based technique enables the clustering of similar aquifers based on model parameters. By leveraging the decision trees feature importances, we derive the rainfall response time distribution of the aquifer at the piezometer level, facilitating a quantitative analysis of the local aquifer dynamics. Additionally, we demonstrate that, by selecting analogous distributions using a simple similarity measure, the predictive performance of groundwater level global forecasting models is significantly enhanced.
How to cite: Breuillard, H., Laurencelle, M., Wang, S., Mato, C., Dupraz, S., and Dantal, Y.: A Novel Machine Learning-based Method for Groundwater Modelling involving Aquifer Rainfall Time Response Analysis and Clustering of Groundwater Wells, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-13850, https://doi.org/10.5194/egusphere-egu25-13850, 2025.
In semi-arid regions characterized by little and erratic precipitation and ephemeral river flow, groundwater is commonly the only perennial source of freshwater sustaining ecosystems and freshwater withdrawals for agricultural, domestic and industrial uses. However, the renewability of groundwater in these regions is associated with substantial uncertainty. Focused recharge, groundwater replenishment via seepage from surface drainage during high river flow, has been shown to contribute substantially to groundwater storage. Yet, the relative contributions of focused and diffuse recharge, as well as their dependence on rainfall variability and climate change, remain underexplored at catchment scale. This study employs a data-driven approach to estimate annual groundwater recharge in the semi-arid Hout/Sand catchment (7,722 km2), Limpopo, South Africa, utilizing data from 105 boreholes spanning 1955-2023. The Water Table Fluctuation method is used to derive annual recharge estimates from individual groundwater hydrographs. The recharge estimates are used to train a Light Gradient-Boosting Machine (LightGBM) model employing physiographic and climatic predictors, which generates a fully distributed annual recharge map at a 100 m resolution for each year of the 69-year study period. The results show recharge rates exceeding 1,000 mm/year in wells near riverbeds, highlighting the dominance of focused recharge. Annual recharge maps demonstrate significant spatial variability, with high recharge values concentrated along river networks. Among the predictors in the LightGBM model, proximity to rivers emerged as the most critical factor. Total annual recharge exhibits strong inter-annual variability, closely correlated with total annual rainfall. However, preliminary findings indicate a decline in annual recharge after 2015 despite increasing annual rainfall, suggesting a decoupling of the recharge-rainfall relationship. A key limitation of the study is the bias introduced by the high concentration of wells near riverbeds characterized by high recharge rates. To address this, we aim to incorporate synthetic data points representing diffuse recharge into the model training. Focused recharge may provide a buffering effect against climate change, as more intense rainfall events could enhance recharge along the river networks. Future work will focus on quantifying the relative contribution of focused recharge to total recharge at the catchment scale, its temporal evolution, and its correlation with rainfall variability to assess the impact of climate change on groundwater recharge.
How to cite: Bjerre, E., Koch, J., K. Dalum, W., G. Villholth, K., O. Sonnenborg, T., and H. Jensen, K.: Groundwater Recharge Variability in a Semi-Arid South African Catchment under Climate Change: Insights from Long-Term Observations and Machine Learning, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-8231, https://doi.org/10.5194/egusphere-egu25-8231, 2025.
Groundwater level (GWL) monitoring datasets are essential for effective groundwater resource management and understanding the potential impacts of climate change. However, these datasets frequently contain gaps and irregular measurement intervals, posing challenges for time series analyses that depend on consistent sampling. As a result, GWL datasets with substantial gaps are frequently excluded from further analysis, leading to a loss of temporal and spatial coverage, regional representativity, and potentially valuable insights. Addressing this issue requires effective and interpretable imputation techniques to fill missing values while preserving the physical realism of the reconstructed data. Traditional statistical imputation methods and advanced machine learning algorithms, such as missForest, have been used to address data gaps. While these approaches often yield effective imputations, they lack physical interpretability, particularly for extreme events, which is crucial for understanding the variability and resilience of groundwater systems under changing environmental conditions. This study proposes a novel hybrid imputation approach that combines physical modeling with statistical adjustments. First, GWL data are simulated using Pastas, an open-source framework that leverages hydrometeorological variables and impulse response functions to model GWL time series. These simulations serve as a physically consistent basis for imputing missing values. In the second step, a linear scaling approach is applied to scale the simulated GWL to match the observed start and end point of each gap, ensuring consistency with observations. The hybrid method was tested on data from 213 monitoring wells across Sweden, encompassing diverse temporal resolution and gap characteristics. This process generated continuous daily time series spanning 34 years (1990–2023), enabling the evaluation of long-term groundwater dynamics across Sweden (future work). Validation focused on the ability to capture extreme GWL events. While Pastas-only simulations performed well in reproducing seasonal GWL variability, they failed to accurately capture extremes. The hybrid technique demonstrated significant improvements in representing extreme variability, offering a robust solution for handling irregular and incomplete datasets. Additionally, the study provides insights into regional data characteristics, such as variations in gap patterns and hydrometeorological drivers, offering valuable information for groundwater modeling and analysis. The proposed method not only enhances the reliability of GWL datasets but also supports better decision-making in groundwater resource management. The work is a contribution to the Water4All GroundedExtremes project.
How to cite: Nair, A. S., Tallaksen, L. M., Bjørbæk, T. A., and Collenteur, R.: Gap-filling groundwater level time series of irregular temporal resolution using physical modeling (Pastas) and simple statistical scaling, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-10107, https://doi.org/10.5194/egusphere-egu25-10107, 2025.
This study aims to improve the regionalization of groundwater head dynamics using static environmental features. Recent machine- and deep learning studies have explored the use of these features for spatial and temporal imputation (Haaf et al., 2023) or improvement of global models (e.g., Chidepudi et al. (2024); Heudorfer et al. (2024); Nolte et al. (2024)). While physiographic features, including geology, land cover, anthropogenic factors, and topography, have been identified as important predictors of groundwater dynamics at regional and watershed scales (Haaf et al., 2020; Haaf et al., 2023; Rinderer et al., 2017; Zhao et al., 2023), there is still a lack of understanding on how to leverage static features to achieve significant model improvement for groundwater time series regionalization (e.g., Heudorfer et al., 2024; Nolte et al., 2024).
In this study, we use a data-driven, static feature-based approach to regionalize groundwater head duration curves and reconstruct them based on similar donor sites (Haaf et al., 2023). We evaluate the similarity of static features compared to the geographical proximity of donor sites. The data set consists of more than 150 ten-year, daily groundwater head time series in the upper Danube catchment and more than 60 static features at each site.
Our findings suggest that geographical proximity, related to both physiographic and climatic similarity, is the best default approach for selecting donor sites for regionalization. However, in specific cases where the nearest donor sites were located in different hydrogeological regimes, static features significantly improve regionalization. The study demonstrates the potential for improving the regionalization of groundwater dynamics using spatial features in diverse hydrogeological settings. Further research on larger and more diverse data sets is warranted to allow for robust feature selection strategies.
References
Chidepudi, S. K. R., Massei, N., Jardani, A., Dieppois, B., Henriot, A., & Fournier, M. (2024). Training deep learning models with a multi-station approach and static aquifer attributes for groundwater level simulation: what’s the best way to leverage regionalised information? EGUsphere, 2024, 1-28. https://doi.org/10.5194/egusphere-2024-794
Haaf, E., Giese, M., Heudorfer, B., Stahl, K., & Barthel, R. (2020). Physiographic and Climatic Controls on Regional Groundwater Dynamics. Water Resources Research, 56(10). https://doi.org/10.1029/2019wr026545
Haaf, E., Giese, M., Reimann, T., & Barthel, R. (2023). Data‐Driven Estimation of Groundwater Level Time‐Series at Unmonitored Sites Using Comparative Regional Analysis. Water Resources Research, 59(7). https://doi.org/10.1029/2022wr033470
Heudorfer, B., Liesch, T., & Broda, S. (2024). On the challenges of global entity-aware deep learning models for groundwater level prediction. Hydrol. Earth Syst. Sci., 28(3), 525-543. https://doi.org/10.5194/hess-28-525-2024
Nolte, A., Haaf, E., Heudorfer, B., Bender, S., & Hartmann, J. (2024). Disentangling coastal groundwater level dynamics in a global dataset. Hydrol. Earth Syst. Sci., 28(5), 1215-1249. https://doi.org/10.5194/hess-28-1215-2024
Rinderer, M., McGlynn, B. L., & van Meerveld, H. J. (2017). Groundwater similarity across a watershed derived from time-warped and flow-corrected time series. Water Resources Research, 53(5), 3921-3940. https://doi.org/10.1002/2016wr019856
Zhao, F.-H., Huang, J., & Zhu, A. X. (2023). Spatial prediction of groundwater level change based on the Third Law of Geography. International Journal of Geographical Information Science, 37(10), 2129-2149. https://doi.org/10.1080/13658816.2023.2248215
How to cite: Haaf, E. and Zhang, Y.: Improving the Regionalization of Groundwater Head Dynamics with static environmental features, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-4204, https://doi.org/10.5194/egusphere-egu25-4204, 2025.
Understanding and predicting groundwater contaminant transport is inherently challenging due to uncertainties in both field-specific properties and contaminant-related parameters. These uncertainties pose challenges for effective environmental management, including project planning, non-invasive long-term monitoring, and remediation efforts. To address this, we propose a framework that combines geophysical monitoring, surrogate-assisted Bayesian inference, and dimensionality reduction techniques to quantify and reduce these uncertainties and aid in decision making processes. For the implementation of Bayesian inference, our work focuses on electrical resistivity tomography, a geophysical method that is particularly well-suited for the abovementioned purpose due to its sensitivity to variations in fluid content and temperature.
The proposed approach addresses two major computational challenges. First, Bayesian inference requires extensive model runs, which can become computationally prohibitive for large domains with fine grids, multiple processes, and multiple time steps. To mitigate this, we use surrogate models that approximate the full physics-based model using input-output data pairs, significantly reducing computational costs. Second, the high-dimensional nature of ERT data complicates both surrogate training and Bayesian inference. High output dimensions lead to increased training times, larger data requirements, and difficulties in likelihood estimation due to the "curse of dimensionality." To overcome this, we incorporate dimension reduction techniques into the framework.
Our main focus is to evaluate how surrogate modeling approximations and dimension reduction strategies influence the accuracy and efficiency of Bayesian inference when using ERT measurements for contaminant transport applications. We apply our framework on a 2D synthetic non-reactive contaminant transport scenario, integrating ERT measurements while accounting for uncertainties in both field-specific and contaminant-related parameters. This methodology provides a practical tool for subsurface engineering, offering improvements in planning, parameter estimation, and long-term monitoring to enhance contaminant transport predictions and remediation strategies.
How to cite: Morales Oreamuno, M. F., Menzel, N., Oladyshkin, S., Wagner, F. M., and Nowak, W.: Surrogate-assisted Bayesian inference with ERT data for contaminant transport modelling in the subsurface, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-12561, https://doi.org/10.5194/egusphere-egu25-12561, 2025.
The GALDIT method is one of the most prevalent methodologies for assessing seawater intrusion vulnerability. However, the subjectivity of the vulnerability assessment framework and the complexity of the factors influencing seawater intrusion pose challenges to accurate mapping of vulnerability assessment. Hence, this paper proposes a new vulnerability assessment model for seawater intrusion based on the GALDIT method, incorporating machine learning techniques (Artificial Neural Networks, ANN, and Random Forests, RF) and triangular fuzzy membership functions (FMF). The new modelling framework introduces “Water yield property of the aquifer” for representing the influence of geological structures on groundwater storage status and adds a "Land Use type" factor to characterize the impact of human activities, and is referred to as "WALDIT_LU". This framework was tested in a coastal aquifer in Shandong Province, China. The results show that the thematic maps improved by the FMF method are more objective and better suited for regions with extensive data ranges or scales than those produced by the original GALDIT method. Hydrochemical validation results indicate a significant enhancement in the accuracy of vulnerability maps created by the WALDIT_LU-ANN and WALDIT_LU-RF models compared to the original GALDIT model. The Spearman’s rank correlation coefficient values obtained between the GALDIT, WALDIT_LU-ANN, WALDIT_LU-RF and the Cl- ion were 0.291, 0.426 and 0.477, respectively. The equivalent ratio values using the TDS as the parameter were 0.275, 0.737 and 0.811, respectively. The optimised factor weights for the WALDIT_LU-RF model are more reasonable with factor weights of 25.52% (I), 14.47% (A), 14.38% (D), 12.49% (T), 11.73% (LU), 10.68% (W), and 10.73% (L). It is concluded that the new framework incorporating the WALDIT_LU index provides a more comprehensive consideration of the factors influencing seawater intrusion. Additionally, the new model reduces subjectivity and enhances the reliability of mapping seawater intrusion vulnerability.
How to cite: Cheng, J., Bai, Y., and Zhao, X.: An improved GALDIT method combined with machine learning for assessing aquifer vulnerability to seawater intrusion in the Shandong Peninsula, China, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-16463, https://doi.org/10.5194/egusphere-egu25-16463, 2025.
Offshore freshened groundwater (OFG) represents a significant potential resource, with global volumes estimated at 10⁵–10⁶ km³. However, the scarcity of subsurface data on continental shelves poses challenges to understanding OFG systems' offshore extent, depth, and freshwater volume. Addressing these gaps, the OPTIMAL project leverages global geomorphological and sea-level datasets to develop machine learning models for OFG prediction and characterization. We present the results of the first stage of the project, including surrogate model design and parameter space definition. A suite of surrogate models was developed to capture key geological and geomorphological parameters influencing OFG systems. These 2D continental shelf profiles were defined by five parameters derived from open-source global datasets including shelf width, shelf-break depth, coastal unconsolidated sediment thickness and offshore aquifer properties. Numerical modeling of marine transgressive and regressive cycles was applied to these models to generate a training dataset encompassing OFG system realizations and associated parameter spaces. Initial ML models trained on this dataset demonstrate the feasibility of using surrogate models to overcome data scarcity issues in OFG characterization. Future work will refine these models, with a binary classification system to identify OFG presence and a multi-output regression for resource feasibility ranking. These results highlight the potential of integrating data-driven approaches to improve our understanding of OFG systems, providing a scalable framework for predicting OFG distribution and characteristics at both global and local scales.
How to cite: Thomas, A. T., Zamrsky, D., Oude Essink, G. H. P., Bierkens, M. F. P., and Micallef, A.: Offshore Freshened Groundwater prospecting using Machine Learning, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-18009, https://doi.org/10.5194/egusphere-egu25-18009, 2025.
The Geological Survey of the Netherlands has extensively mapped the subsurface of the Netherlands, including a series of temperature measurements in the late 1970s and early 1980s. Over 500 temperature-depth profiles have been obtained in piezometers up to depths of few hundreds of meters. These nationally distributed measurements provide an important historical baseline relevant for drinking water quality, and subsurface energy systems. For this purpose, isothermal maps covering the Netherlands were produced for various depths.
Since these temperature-depth data were collected, substantial changes in ground surface temperatures have occurred as a result of both land-use change and global warming. In order to quantify subsurface temperature changes, and to evaluate whether the old temperature maps need to be updated, we repeated a small subset of the original temperature measurements, spread over the Netherlands in the same piezometers where historical data were obtained. This study discusses the first results of this new survey by comparing the modern data to the historical ones in relation to changes in climate and land use.
How to cite: Fokker, E., Korevaar, Z., Bense, V., and Zaadnoordijk, W. J.: Temperature evolution in the shallow subsurface of the Netherlands, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-19207, https://doi.org/10.5194/egusphere-egu25-19207, 2025.
Groundwater is the primary source of Estonia’s drinking water, but its vulnerability remains under-characterized across regions that lack detailed mapping. Current assessments rely on a modified DRASTIC method based on field-based geological mapping, which so far covers only about a third of Estonia. The EU Water Framework Directive and the ongoing development of a new nationwide, data-driven risk assessment methodology have highlighted the need for alternative approaches to assess groundwater vulnerability – particularly in areas where existing maps are outdated or unavailable.
This study introduces a further adaptation of the modified DRASTIC method, leveraging Estonia’s extensive database of drilled wells to evaluate groundwater vulnerability on a national scale. Drilled well logs contain detailed information on local geological and hydrogeological conditions, which, once interpreted, inform DRASTIC parameter values.
A Python-based data processing workflow, incorporating a natural language processing routine, will be used to automatically extract and classify thousands of unique Quaternary sediment descriptions. Subsequently, a combination of Python and open-source GIS tools will be used to develop a semi-automated geospatial model to compute vulnerability indices for each individual drilled well site. The model’s performance will be evaluated in regions with established vulnerability maps to ensure calibration against existing field-based results. Finally, a customized kriging-based interpolation method will be used to generate region-wide vulnerability surfaces from the data points, which will undergo further validation and refinement by comparison with known maps.
Preliminary results indicate that well-based vulnerability scores align closely with those produced by the current, more detailed DRASTIC methodology, suggesting this approach could be a viable alternative for assessing groundwater vulnerability in unmapped areas. Using data from drilled wells allows for the flexible inclusion of multiple layers of Quaternary deposits, rather than limiting assessments to the uppermost layer. This enables the consideration of deep layers of clays and silts, potentially offering more accurate assessments compared to the current method in some areas. However, findings also suggest that certain DRASTIC parameters may require adjusted weightings or redefinition to better capture local variability.
By integrating digital drilled well logs with open-source GIS and coding tools, this methodology provides a practical alternative for large-scale groundwater vulnerability mapping in areas where other relevant spatial datasets are not available. The approach offers a broad coverage and leverages an already available, constantly growing dataset, possibly enabling continuous, near-automatic vulnerability reassessments using the most up-to-date data. This study reaffirms the value of modifying established methodologies like DRASTIC to account for new data formats, providing a flexible framework for improving groundwater management practices.
How to cite: Hints, L., Männik, M., Aunap, R., and Marandi, A.: Leveraging Drilled Well Data into a Modified DRASTIC Framework for Groundwater Vulnerability Mapping in Estonia, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-20739, https://doi.org/10.5194/egusphere-egu25-20739, 2025.
The increasing risks of flood and drought events, driven by climate change and urbanization, are particularly pronounced in Flanders, Belgium, where vulnerability to hydrological extremes is high. This study focuses on a significant land-based agricultural and fruit production area in Flanders, which is highly vulnerable to droughts and floods. We use a data-driven, distributed hydrological model, coupling AquaCrop with a simplified groundwater model, to simulate interactions between surface and groundwater, and to simulate the land use and management impact on catchment runoff and groundwater recharge. We conducted a detailed sensitivity analysis on the model parameters and calibrated the model with focus on the validity of actual local physical processes. Furthermore, we project future water allocation under multiple climate scenarios to quantify the spatial and seasonal distribution of flood and drought impacts in both current and future climates. The outcomes provide a research basis for subsequent evaluations of possible land-based climate adaptation actions and propose a comprehensive action plan in close consultation of the local stakeholders.
How to cite: Wang, T., Brangers, I., and Willems, P.: Integrated flood-drought climate change impact analysis and adaptation planning – case of Herk-Mombeek catchment, Belgium, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-20741, https://doi.org/10.5194/egusphere-egu25-20741, 2025.
