HS8.2.11
Data-driven groundwater modeling: methods, applications & challenges

HS8.2.11

EDI
Data-driven groundwater modeling: methods, applications & challenges
Convener: Raoul CollenteurECSECS | Co-conveners: Tanja Liesch, Ezra HaafECSECS, Mark Bakker
Presentations
| Fri, 27 May, 10:20–11:50 (CEST)
 
Room 2.31

Presentations: Fri, 27 May | Room 2.31

Chairpersons: Raoul Collenteur, Ezra Haaf
10:20–10:23
10:23–10:29
|
EGU22-4809
|
ECS
|
Virtual presentation
Moritz Gosses and Thomas Wöhling

Estimating the effects of climate change on water resources is an important topic for researchers in hydrological sciences. Climate model outputs can be used as inputs for calibrated numerical groundwater models to predict the effect of different climate scenarios on groundwater levels. Unfortunately, spatially explicit numerical models are spatially constrained, data-hungry, and difficult to set-up and to calibrate. Furthermore, the involved model run-times make proper uncertainty analysis of the model predictions computationally expensive.
Machine-learning (ML) tools have become recognized as a powerful alternative for numerical models for different applications in hydrological science, but come with their own challenges. They have been successfully used for the prediction of groundwater levels in single bores based on historical data, but their application for estimating groundwater levels for climate scenarios is still a matter of active research.
To identify the potential of ML techniques for this application, two different ML algorithms have been applied to predict groundwater levels for several climate scenarios at a number of groundwater wells with long-term historical data time series. The two ML algorithms are (i) multi-layer perceptrons (MLP) with a closed feedback loop and (ii) long short-term memory (LSTM) networks. For each observation well, several thousand versions of these ML models with differing setups are trained to historical, monthly data time series up to 2015 and then applied for the estimation of monthly groundwater levels. These estimations are computed by using climate model outputs for different scenarios, as well as artificially generated scenarios, as drivers for the ML models to test their sensitivity and plausibility to those input data series. The high quantity of model versions for each bore are utilized to generate mean groundwater level estimates and accompanying uncertainty bands via Bayesian Model Averaging (BMA).
Both ML techniques are able to match the historical data time series for the different bores with small uncertainty, but differ in their ability to predict long-term groundwater levels from climate change and artificial scenarios. The long-term simulations of the MLP models show believable trends and appropriate uncertainty bands, while the LSTM networks seem to underestimate the uncertainty of their future predictions.

How to cite: Gosses, M. and Wöhling, T.: Long-term prediction of groundwater levels for climate scenarios with machine-learning tools, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-4809, https://doi.org/10.5194/egusphere-egu22-4809, 2022.

10:29–10:35
|
EGU22-12740
|
Presentation form not yet defined
|
Joan Campanyà i Llovet, Ted McCormack, and Owen Naughton

Climate change will have a major impact on Ireland’s water resources. It will pose significant risks to water management and exacerbate existing pressures in terms of water supply, quality, flooding and drought. Early detection of these pressures in hydrological regimes is key to informing adaptation strategies and minimizing adverse environmental and societal impacts. In response to this risk, a framework was developed to enable short-term forecasting of groundwater levels, and to quantify and analyse the impact that climate change will have on Irish groundwater systems.

A key element of the framework is the use of robust hydrological models to simulate groundwater levels. The framework was developed in Python, with a particular focus on groundwater flooding, and incorporates two modelling approaches: 1) mathematical transfer functions (combination of exponential decay, gamma distribution, and linear decay functions), and 2) a physically based lumped model (reservoir model). For both modelling approaches, precipitation data is converted to effective rainfall based on soil moisture deficit and evapotranspiration data, and the model parameters are calibrated using a Bayesian Markov Chain Monte Carlo algorithm.

The framework was tested and implemented with synthetically generated groundwater level time series, and with a selection of 12 groundwater dependent wetlands covering a wide range of hydrological behaviours. The tested approaches have proof successful to: 1) produce viable numerical models for those systems, with Nash-Sutcliffe Efficiency (NSE) and Kling-Gupta Efficiency (KGE) values between 0.85 and 0.98 for most of the sites calibration and validation datasets, and 2) inform on how the groundwater systems operate (i.e. multiple outflows, changes in catchment area). The models are now used for forecasting groundwater levels and assessing the potential impact of climate change in ecologically important wetlands.

The outputs of this project will improve the national ability to understand how groundwater resources respond to climatic stresses and improve the reliability of adaptation planning and predictions in the groundwater sector.

How to cite: Campanyà i Llovet, J., McCormack, T., and Naughton, O.: A framework for modelling groundwater floods and its applications for forecasting and assessing the impact of climate change in groundwater systems: examples from Ireland, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-12740, https://doi.org/10.5194/egusphere-egu22-12740, 2022.

10:35–10:41
|
EGU22-2662
|
ECS
|
On-site presentation
|
Andrea Manzoni, Monica Riva, Giovanni Porta, and Alberto Guadagnini

We discuss the definition and implementation of an integrated groundwater and surface water flow modeling framework focused on the Po River basin (Italy; with an extension of about 72.000 km2). At such a scale, it is possible to characterize global (space‐time) patterns of groundwater response in a way that is typically overshadowed when considering analyses at the scale of a single aquifer. We create a georeferenced three-dimensional platform that unifies the diverse types of data available in the basin area. The data collected merge streams of information from a variety of sources, including, e.g., climate satellite data, soil properties and land use data, and lithological/sedimentological information. In this context, we consider two key inputs of the large-scale groundwater model: i) the estimation recharge rates and ii) the reconstruction of the subsurface architecture. We then focus on the latter element and analyze the most critical steps associated with data collection, organization, and interpretation. We obtain an operational model of the domain upon relying on lithological and sedimentological information to reconstruct the spatial distribution of subsurface geomaterials which we integrated within a machine learning approach based on Artificial Neural Networks. Results are compared with available geological interpretations in the area. We discuss feedbacks between (a) the characterization of the system, as driven by domain discretization, that aims at considering a high-resolution hydrogeological reconstruction and (b) computational efficiency. Our results are discussed in the framework of future developments of the study with a view to establishing a physically-based three-dimensional characterization of large-scale groundwater flow accounting for a variety of processes taking place across multiple scales.

How to cite: Manzoni, A., Riva, M., Porta, G., and Guadagnini, A.: Data-driven reconstruction of the main traits of the large-scale Po River basin subsurface system, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-2662, https://doi.org/10.5194/egusphere-egu22-2662, 2022.

10:41–10:47
|
EGU22-6263
|
ECS
|
On-site presentation
Vincent Wolfs, Tim Franken, Cedric Gullentops, Johan Lermytte, and Jan Corluy

The summers of 2017 to 2020 were characterized by exceptional dry spells throughout Europe. Climate models show that such periods of drought could occur more frequently and become even more extreme in the future. The recent periods of intense droughts lead to significant ecological, economic and even societal damages in Flanders (Belgium). During these summers, receding groundwater levels were observed throughout Flanders that reached historical low levels. To monitor low ground water levels and to support a proactive drought management, the Flemish government developed an operational ground water indicator. This indicator gives an overview of the current phreatic ground water levels combined with a prediction for the next month for a selected number of phreatic wells. To increase the spatial resolution of the indicator, we developed a novel data driven regional ground water model for phreatic aquifers.

The ML model combines a gradient boosting decision tree model (CatBoost) with a Long Short Term Memory (LSTM) network. CatBoost is used to model the average ground water depth at each location. This value is passed to the LSTM network that predicts the temporal evolution of the groundwater at each location around its average. The training dataset for the CatBoost model contains the average groundwater depth of 5.673 wells spread across Flanders and a large set of explanatory variables related to soil texture, distance to a drainage, geology, topography, meteorology and land use. The model performance is evaluated using cross-validation which showed the model generalizes well with a mean absolute error of 69cm. The most important explanatory variables for the model are the thickness of the phreatic aquifer, the vertical distance to closest drain, the topographic index and the precipitation surplus.

The training dataset for the LSTM model contains 408 wells that have sufficiently long and reliable observations for training. The input data to the LSTM consists of rainfall and evapotranspiration up to 10 years prior to each observation, combined with the same explanatory variables as the CatBoost model. A single regional LSTM model is trained on all 408 wells simultaneously. The resulting model is accurate with a median RMSE of 20cm for the validation data, outperforming the currently used SWAP models [1]. The ML model is however less performant in simulating the higher ground water depths during summer and shows a consistent bias towards lower ground water depths during long dry spells.

[1] Kroes, J.G., J.C. van Dam, R.P. Bartholomeus, P. Groenendijk, M. Heinen, R.F.A. Hendriks, H.M. Mulder, I. Supit, P.E.V. van Walsum, 2017. SWAP version 4; Theory description and user manual. Wageningen, Wageningen Environmental Research, Report 2780

How to cite: Wolfs, V., Franken, T., Gullentops, C., Lermytte, J., and Corluy, J.: A regional data driven model for simulating phreatic ground water levels in Flanders, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-6263, https://doi.org/10.5194/egusphere-egu22-6263, 2022.

10:47–10:53
|
EGU22-7384
|
ECS
|
Presentation form not yet defined
H.M. Mehedi Hasan, Kuei-Hua Hsu, Annette Eicker, Laurent Longuevergne, and Andreas Güntner

Groundwater is the most important freshwater source considering its abundance, demand, quality, and accessibility. However, estimation of groundwater storage variations is notoriously difficult due to the lack of information on physical aquifer properties, the connectivity among other water storages, the scarcity of observations at regional scales and high uncertainty associated with the observations if available. In the current study, we tried to improve the simulations of groundwater storage variations of a global hydrological model with a simple bucket-type groundwater module – the WaterGAP Global Hydrological Model (WGHM) – in four French river basins. Sensitive model parameters were calibrated against in-situ streamflow observations and GRACE-based observations of total water storage anomalies in a multi-criterial calibration framework. A regional data set of in-situ observations of groundwater levels and deduced basin-average groundwater storage variations (see Hsu et al., this meeting) was used for validation of the calibration results. In a second setup, the in-situ groundwater observations were introduced as additional observations into the calibration framework.  We found significant improvement in the simulated groundwater dynamics in terms of their seasonal signals and amplitudes after calibration. Overestimated negative groundwater trends in a few river basins caused by overestimated human groundwater use in the original model could also be corrected by the calibration approach. In an additional calibration experiment, specific yield was introduced into WGHM as a new calibration parameter and its calibrated values were compared to those obtained from regionalizing the hydrogeological information.

How to cite: Hasan, H. M. M., Hsu, K.-H., Eicker, A., Longuevergne, L., and Güntner, A.: Improved groundwater simulations by multi-criteria calibration of a global hydrological model in the river basins of France, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-7384, https://doi.org/10.5194/egusphere-egu22-7384, 2022.

10:53–10:59
|
EGU22-7734
|
ECS
|
On-site presentation
Ainur Kokimova, Raoul Collenteur, and Steffen Birk

Alluvial aquifers and springs play a vital role in the water supply of Austria as the main source of drinking water. One such example is the Grazer Feld Aquifer, located in an urban and semi-urban setting in southeast Austria. Urbanisation imposes stresses on aquifers leading to quantitative and qualitative groundwater problems. These problems are commonly addressed by numerical groundwater models. In these models, natural and anthropogenic processes need to be carefully represented. Calibration to groundwater level data disturbed by human activities will fail or produce erroneous parameter estimates if the disturbance is not adequately considered by the model. As a consequence, such model likely result in erroneous predictions and assessments. To account for relevant drivers in the system and examine groundwater level data for the calibration of a numerical groundwater model, we test the application of the time series analysis as an additional and preliminary step in a general numerical groundwater modeling framework. The results of time series models (TSM) contribute to the understanding of spatiotemporal aquifer dynamics and main driving forces as advocated by Bakker and Schaars (2019).

The objective of this study is twofold. First, time series models were set up and calibrated for each monitoring well in the aquifer, using the stresses identified in the initial hydrogeological assessment (precipitation, evapotranspiration, and river levels). Second, we create a calibration data set that flags groundwater level observations that were caused by human temporal activities (e.g., pumping, irrigation, and/or dam construction). This is achieved by constructing TSMs and conducting a visual and spatial investigation on model results. The process differentiates good fit models from no-good fit models. Then, models, not delivering a good fit, are checked for missing driving forces by engaging local stakeholders. Once the process is characterized, the period with unexplained groundwater level change is marked. The groundwater level fluctuations of 115 out of 149 observation wells are found to be reasonably simulated by considering recharge from precipitation and, if applicable, river stages as driving forces. For 34 observation wells, however, the models perform less accurately, suggesting other factors, such as construction activities and temporary groundwater abstraction, influencing groundwater level fluctuations during the part or the entire simulation period. Estimated recharge is found to be higher in urban and semi-urban areas compared to agricultural fields. The results from this study will be used in the future development of a numerical groundwater model for the entire aquifer.

How to cite: Kokimova, A., Collenteur, R., and Birk, S.: Data-driven time series modeling to support groundwater model development for the Grazer Feld Aquifer, Austria, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-7734, https://doi.org/10.5194/egusphere-egu22-7734, 2022.

10:59–11:05
|
EGU22-7999
|
ECS
|
On-site presentation
Marta Jemeļjanova, Jānis Bikše, and Andis Kalvāns

Recent years have seen several major groundwater drought instances in Europe, increasing the interest in their research and future predictions. Modeling methods can be used to explore groundwater drought risk in near and medium term future using climate projection data sets as an input. Therefore an optimal modeling approach has to be chosen according to the available data and modeling capacity of the historic series. 

We  explore two approaches for modeling groundwater level time series: Transfer function-noise models with Impulse response functions (TFN-IRF) and machine learning (ML). In both approaches, daily meteorological variables are used as an input and models are calibrated against historical groundwater level observations. 

TFN-IRF input parameters are daily precipitation and potential evapotranspiration. Other time series data, such as groundwater abstraction, can be added to potentially increase the fit. Machine learning models can, in addition to the aforementioned, benefit from a wider variety of site parameters, including derived parameters (e.g., meteorological indices), however at the expense of increased data collection effort. In addition, the obscure input data interpretation in ML methods can erode the trust in these models. In this study, only the most basic meteorological parameters - precipitation, temperature - and derived parameters such as potential evapotranspiration were used. 

We draw from an extensive groundwater level monitoring database of more than one thousand monitoring wells from three Baltic countries. The study provides an insight into differences between the two modelling approaches, keeping in mind the limitations of future projection data.

This research is funded by the Latvian Council of Science, project “Spatial and temporal prediction of groundwater drought with mixed models for multilayer sedimentary basin under climate change”, project No. lzp-2019/1-0165.

How to cite: Jemeļjanova, M., Bikše, J., and Kalvāns, A.: Comparison of Impulse response function and Machine learning models for use in groundwater level short to medium term future projections in the Baltic states, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-7999, https://doi.org/10.5194/egusphere-egu22-7999, 2022.

11:05–11:11
|
EGU22-9995
|
Presentation form not yet defined
Mark Bakker, Martin Vonk, Raoul Collenteur, and Frans Schaars

Time series analysis with response functions is a versatile approach to analyze measured head series in observation wells. In such an analysis, the response function of the groundwater does not change with time. This approach works well when the groundwater recharge is a linear function of the measured rainfall and evaporation, as was shown through the analysis of synthetic time series generated with a saturated groundwater model where the groundwater recharge is applied directly to the saturated zone. In this research, the method was evaluated for situations where the groundwater recharge cannot be approximated well as a linear function of the measured rainfall and evaporation. Synthetic time series were generated with a two-dimensional saturated/unsaturated zone model (Hydrus2D) and analyzed with response functions. Performance of the time series model was improved through inclusion of a new root zone model consisting of a single reservoir. Reservoir inflow is measured rainfall. Reservoir outflow is evaporation and groundwater recharge, where the evaporation is a function of the amount of water stored in the root zone and the recharge is a function of both the amount of water stored in the root zone and the groundwater table. The new root zone model is a promising tool for the analysis of head series in areas with thick unsaturated zones and/or high potential evaporative fluxes.

How to cite: Bakker, M., Vonk, M., Collenteur, R., and Schaars, F.: Time series analysis of synthetic time series generated with a saturated/unsaturated zone model, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-9995, https://doi.org/10.5194/egusphere-egu22-9995, 2022.

11:11–11:17
|
EGU22-9975
|
ECS
|
Virtual presentation
|
Shubham Goswami and Sekhar Muddu

Assessment of specific yield becomes crucial for an effective groundwater management in hard-rock aquifers in semi-arid regions, especially in southern India with its high dependence on groundwater for irrigation. Specific yield is an important parameter influencing water table fluctuations in groundwater and land-surface models as uncertainties associated with specific yield estimation are passed on to recharge estimation. In southern India, contemporary groundwater levels are heavily influenced by groundwater pumping and are spatially heterogeneous. Comparatively homogeneous natural groundwater levels in the upper weathered zone were observed in the earlier decades of 1970s and 1980s because of relatively lower pumping. Specific yield values estimated for the duration prior to 1990 are representative of upper bounds of specific yield values because of shallower water tables, hence we have selected the duration from 1980-1990 for this study. The existing water table fluctuation methodology by Maréchal et al. (2006) and Groundwater resource Estimation Committee (GEC, 2015) estimates specific yield based on net groundwater level decline during dry season corresponding to known or estimated groundwater draft. This methodology is not feasible for zero draft scenarios prevailing during 1980-1990. An alternate approach is required to account for discharge which was more dominant process to affect groundwater fluctuations when they are shallow. A physically based lumped model for unconfined aquifers, AMBHAS-1D is used in this study which is based on Park and Parker (2008) model. The model is applied on monthly groundwater levels at 100 sites tapping into a geologically homogeneous region of granitic gneissic aquifer in the Upper Cauvery River basin of Karnataka, India. Specific yield values are estimated for each of the 100 sites and a specific yield map for the region is prepared. Even though it is granitic gneissic rock in general, we observed a high variability in estimated specific yield of more than 10 orders of magnitude which can be associated with degree of fracturation, long-term rainfall trends, variation of water level and topographic impacts. Major area of Hassan and Mandya districts of Karnataka state have very low estimated specific yield (<=0.05%) indicating poor fracturing in those regions. Clusters of relatively high specific yield (>1%) are observed in south western part of Mysore district, Mysore city and southern part of Tumkur district depicting weathered upper zone.

References:

GEC (2015). Report of the Ground water resource Estimation Committee, Ministry of Water Resources, Govt. of India, New Delhi.

Maréchal, J. C., Dewandel, B., Ahmed, S., Galeazzi, L., & Zaidi, F. K. (2006). Combined estimation of specific yield and natural recharge in a semi-arid groundwater basin with irrigated agriculture. Journal of Hydrology, 329(1–2), 281–293. https://doi.org/10.1016/j.jhydrol.2006.02.022

Park, E., & Parker, J. C. (2008). A simple model for water table fluctuations in response to precipitation. Journal of Hydrology, 356(3–4), 344–349. https://doi.org/10.1016/j.jhydrol.2008.04.022

How to cite: Goswami, S. and Muddu, S.: Estimation of specific yield of hard-rock aquifers in Upper Cauvery River basin region in India by application of AMBHAS-1D groundwater model, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-9975, https://doi.org/10.5194/egusphere-egu22-9975, 2022.

11:17–11:23
|
EGU22-10170
|
ECS
|
On-site presentation
|
Raoul Collenteur, Christian Moeck, Mario Schirmer, and Steffen Birk

Many countries maintain nationwide groundwater networks to monitor the status of their groundwater resources. To assess the current water availability as well as help forecast future changes, it is fundamental to understand and predict groundwater dynamics observed in the individual monitoring wells. Nationwide monitoring networks typically cover multiple aquifer systems with different degree of environmental complexity. Understanding these aquifer systems is challenging, as the development of physically-based, distributed groundwater models is time-consuming and costly. As an attractive alternative, statistical and conceptual lumped-parameter models may be applied to analyze monitoring networks. The advantage of these models over physically-based models is that the conceptual parameterization is relatively simple and computation is efficient, while typically results are robust.

In this study, we analyze the long-term groundwater-monitoring network of Switzerland using conceptual, lumped-parameter models implemented in the Pastas software package. The 29 monitoring wells in the network are situated in unconsolidated aquifers across Switzerland, ranging from high altitude alpine aquifers to pre-alpine aquifers systems on the Swiss plateau. Given the very diverse topography in Switzerland, snowmelt processes affect some aquifers, while groundwater-surface water interactions are important in the valleys. The models are used to identify and quantify which driving forces (e.g., precipitation, river levels) control the groundwater dynamics, and how fast the groundwater systems respond to changes in these stresses. The results show that precipitation and evaporation explain large parts of the observed dynamics, while about half of the monitoring wells in the network appear to be influenced by river level fluctuations. Explicitly accounting for snow processes in the recharge generating process is found to improve the simulation of the water table dynamics for only a few wells in high-altitude aquifers. The models developed in this study lead to a better understanding of the observed groundwater dynamics across Switzerland and will be used in future studies to explore the sensitivity of the groundwater resources to climatic changes.

How to cite: Collenteur, R., Moeck, C., Schirmer, M., and Birk, S.: Analysis of nationwide groundwater monitoring networks using lumped groundwater models: a case study of Switzerland, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-10170, https://doi.org/10.5194/egusphere-egu22-10170, 2022.

11:23–11:29
|
EGU22-11932
|
ECS
|
On-site presentation
|
Alberto Casillas-Trasvina, Bart Rogiers, Koen Beerten, Laurent Wouters, and Kristine Walraevens

Environmental tracers are naturally occurring widespread substances in a hydrogeological system that can be used to identify flow pathways, travel times, groundwater age, and recharge rates. However, these are not typically included during the numerical model inversion process. Recent work has broadened their use in a quantitative way by incorporating them in formal solutions of the inverse problem to estimate hydraulic properties and groundwater fluxes. This is commonly done with numerical codes that at least enable one-way coupling of the different processes, i.e., groundwater flow and solute-transport. Helium-4, carbon-14 and temperature-depth profile measurements represent a valuable source of information which can be exploited to support performance assessment studies. For the Neogene aquifer in Flanders, groundwater flow and solute transport models have been developed in the framework of safety and feasibility studies for the underlying Boom Clay Formation as potential host for geological disposal of radioactive waste. However, the simulated fluxes by these models are still subject to large uncertainties, as they are typically constrained by hydraulic heads only. While the evaluation of candidate host formations continues, the use of age tracers (e.g. 4He) as additional (unconventional) state variable for inverse conditioning is being explored. Current methodological developments to integrate such additional unconventional observations will allow i) to test our current understanding and corresponding models of the system, and ii) to potentially decrease the uncertainties associated with model outcomes by a joint inversion approach. From previous campaigns, a total of 18 4Herad observations have been collected at selected sites across the Nete catchment. Furthermore, the accumulation of 4Herad by in situ production and crustal flux is included in the inversion of the 4He-transport model, where the uncertainty of groundwater flow and transport model parameters is evaluated. Additionally, a Latin hypercube sampling (LHS) design is done with parameters drawn from prior distributions. The corresponding simulation results are used to construct a neural network surrogate model  to be used for uncertainty quantification using Bayesian inference. Here, we will present the first results and interpretations of Helium-4 as potential additional state variable for inverse conditioning, and constraining groundwater flow and solute transport models at the catchment scale.

How to cite: Casillas-Trasvina, A., Rogiers, B., Beerten, K., Wouters, L., and Walraevens, K.: Joint inversion of radiogenic Helium-4 and hydraulic head observations with a neural network surrogate: Application for the Neogene aquifer, Belgium, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-11932, https://doi.org/10.5194/egusphere-egu22-11932, 2022.

11:29–11:35
|
EGU22-7893
|
ECS
|
On-site presentation
Annika Nolte, Ezra Haaf, Benedikt Heudorfer, Steffen Bender, and Jens Hartmann

Distinguishing between natural and anthropogenic impacts on groundwater systems at regional scale is not straightforward using current data-driven and traditional numerical groundwater models. This limits their benefit for groundwater level predictions and thus future-oriented groundwater resource management. We propose an approach to leverage the large amount of information and variability in the characteristics of groundwater hydrographs and environmental factors to obtain generalized insights into the influences of natural and anthropogenic factors on specific patterns in groundwater hydrographs using data-driven regionalization of groundwater level dynamics. In our approach, we focus on coastal regions that are often under water stress due to the water demands of growing coastal populations building on a data set containing several thousand wells in Europe, North America, South Africa, and Australia.

The approach comprises construction and comparison of multiple unsupervised machine learning cluster models based on a) groundwater level dynamics information, aggregated into groundwater hydrograph features, and b) selected environmental drivers that potentially influence natural groundwater recharge and discharge processes. Environmental descriptors were extracted at well locations from available global map products. We discuss the extent to which our selection of features can express the range of dynamics in representative groundwater hydrographs of clustered basins. Furthermore, we compare the similarity of anthropogenic factors within and between clusters in order to test our hypothesis that hydrograph patterns differ in response to natural processes but irrespective of anthropogenic influences. This would contribute to our understanding of natural processes in coastal groundwater systems.

How to cite: Nolte, A., Haaf, E., Heudorfer, B., Bender, S., and Hartmann, J.: Analysis of hydrogeological behavior of coastal aquifers based on clusters of groundwater hydrograph features and environmental drivers, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-7893, https://doi.org/10.5194/egusphere-egu22-7893, 2022.

11:35–11:41
|
EGU22-7920
|
ECS
|
On-site presentation
Jānis Bikše, Andis Kalvāns, Inga Retike, and Marta Jemeļjanova

Regular and gapless observations are necessary to perform a range of statistical analysis on the parameter of interest. Groundwater level (GWL) hydrographs  are often recorded at irregular frequencies and have time periods without any observations. As a result, groundwater level hydrographs have missing values. Typically groundwater hydrographs are removed from further analysis if large gaps are present, while each groundwater observation point is valuable and methods exist that can impute (fill in) the missing observations. 

This study aims to evaluate performance of machine learning methods to prepare gapless daily groundwater level hydrographs and to assess the imputation error according to various approaches. Filled groundwater level hydrographs will further be used  to identify typical groundwater level patterns in the Baltic region.

The performance of two machine learning imputation methods - missForest and missMDA - along with conventional approaches (linear interpolation, mean imputation) - were tested. A subset of the GWL observation data from Lithuania, Latvia and Estonia were used for the time period from 2011 to mid-2019 comprising 283 groundwater monitoring wells. Cluster analysis of the temporal distribution of actual missing values in the GWL time series provided 13 different gap patterns. Next a corresponding number of artificially generated gap distribution scenarios were defined. The performance of various gap-filing approaches were then evaluated by imputing each artificially generated gap pattern in each hydrograph. Results indicated that imputation performance varies among different clusters of missing value patterns, while generally the best performance was achieved by the missForest algorithm.

This research is funded by the Latvian Council of Science, project “Spatial and temporal prediction of groundwater drought with mixed models for multilayer sedimentary basin under climate change”, project No. lzp-2019/1-0165.

How to cite: Bikše, J., Kalvāns, A., Retike, I., and Jemeļjanova, M.: Performance analysis of missing data imputation methods for daily groundwater hydrographs using typical gap patterns, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-7920, https://doi.org/10.5194/egusphere-egu22-7920, 2022.

11:41–11:47
|
EGU22-12580
|
ECS
|
On-site presentation
|
Ezra Haaf, Raoul Collenteur, Tanja Liesch, and Mark Bakker

Groundwater level time series are the most common source of information on the dynamics of subsurface water resources. The modeling of such time series is of crucial importance to increase our understanding of the system and make predictions on future changes. This becomes ever more important with global challenges such as climate change and human over-exploitation of groundwater resources. Different types of models can be applied to model groundwater level time series, ranging from purely statistical models (black-box), through lumped conceptual models (grey-box), to physically based models (white-box). Traditionally, physically based, distributed models are predominantly used to solve groundwater problems. In recent years, the use of grey- and black-box models has been receiving increased attention. In this poster we will present the “Groundwater Time Series Modeling Challenge”, which aims to systematically compare different methodologies to model groundwater level time series. We challenge researchers to model a predefined set of groundwater time series observed in unconsolidated aquifers worldwide, set in a variety of physiographic and climatic conditions. Participating groups are free to use the model of their choice, but are required to use the same forcing data and periods for calibration. Model performance will be centrally assessed by the organizers using non-public validation data set, which will be made public after the challenge. A more detailed description of the rules for this challenge and all groundwater and forcing data is available in a GitHub repository at https://github.com/gwmodeling/challenge. The results of the challenge will be presented at the General Assembly of the EGU in 2023 and reported in a peer-reviewed paper. With this challenge, we hope to increase the awareness in the groundwater community about all the different types of models that are available to model groundwater level time series.

How to cite: Haaf, E., Collenteur, R., Liesch, T., and Bakker, M.: Presenting the Groundwater Time Series Modeling Challenge, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-12580, https://doi.org/10.5194/egusphere-egu22-12580, 2022.

11:47–11:50