Groundwater Hydrological Model Simulation

A special issue of Water (ISSN 2073-4441). This special issue belongs to the section "Hydrology".

Deadline for manuscript submissions: closed (5 September 2022) | Viewed by 40955

Printed Edition Available!
A printed edition of this Special Issue is available here.

Special Issue Editor


E-Mail Website
Guest Editor
Institute of Environmental Geology and Geoengineering, Italian National Research Council, Roma, Italy
Interests: urban waters; groundwater modeling; groundwater mapping; urban flooding; flood risk map

Special Issue Information

Dear Colleagues,

Groundwater numerical modeling is an effective approach to simulating and analyzing the groundwater dynamics under varying conditions.

Regional models are commonly used to simulate the conditions of watersheds that vary due to climatic changes or anthropic modification. Local scale-models are widely used to investigate contaminant transport or to predict the effect of ground heat exchange on the groundwater temperature.

Despite their wide usage, numerical models need to be supported by correct conceptualization of the natural system, proper selection of the computer code and solver, and an effective calibration process.

This Special Issue aims to gather new contributions emphasizing different aspects of groundwater modeling, focusing on the latest developments and applications for water resources management, including the use of new computer tools, such as open source platforms for groundwater modeling or artificial intelligence to explore data and expedite the calibration process. Case studies involving the use of models by local government agencies are especially welcome. We invite you to submit your latest research works on subjects including, but not limited to, the following:

  • Regional groundwater models accounting for watershed modifications
  • Coupling surface water/groundwater models
  • Use of groundwater models to understand the impact of climate change on water resources
  • Groundwater models as tools to ensure the sustainable use of water resources
  • Local-scale groundwater models in urban areas
  • Open source software and tools to manage groundwater models
  • Integration of groundwater model results in GIS systems
  • Comparative studies among groundwater models and machine learning techniques
  • Machine learning techniques to improve model calibration

Looking forward to receiving your contribution.

Dr. Cristina Di Salvo
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Water is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • regional groundwater models
  • urban groundwater
  • model conceptualization
  • numerical modeling solver
  • numerical models calibration
  • open source platform
  • climate change
  • sustainable groundwater management
  • machine learning

Published Papers (12 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Editorial

Jump to: Research, Review

4 pages, 171 KiB  
Editorial
Groundwater Hydrological Model Simulation
by Cristina Di Salvo
Water 2023, 15(4), 822; https://doi.org/10.3390/w15040822 - 20 Feb 2023
Cited by 2 | Viewed by 2411
Abstract
The management of groundwater resources commonly involves challenges and complexities, which are taken on by researchers using a variety of different strategies [...] Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)

Research

Jump to: Editorial, Review

23 pages, 5528 KiB  
Article
Quantifying Groundwater Infiltrations into Subway Lines and Underground Car Parks Using MODFLOW-USG
by Davide Sartirana, Chiara Zanotti, Marco Rotiroti, Mattia De Amicis, Mariachiara Caschetto, Agnese Redaelli, Letizia Fumagalli and Tullia Bonomi
Water 2022, 14(24), 4130; https://doi.org/10.3390/w14244130 - 19 Dec 2022
Cited by 3 | Viewed by 2365
Abstract
Urbanization is a worldwide process that recently has culminated in wider use of the subsurface, determining a significant interaction between groundwater and underground infrastructures. This can result in infiltrations, corrosion, and stability issues for the subsurface elements. Numerical models are the most applied [...] Read more.
Urbanization is a worldwide process that recently has culminated in wider use of the subsurface, determining a significant interaction between groundwater and underground infrastructures. This can result in infiltrations, corrosion, and stability issues for the subsurface elements. Numerical models are the most applied tools to manage these situations. Using MODFLOW-USG and combining the use of Wall (HFB) and DRN packages, this study aimed at simulating underground infrastructures (i.e., subway lines and public car parks) and quantifying their infiltrations. This issue has been deeply investigated to evaluate water inrush during tunnel construction, but problems also occur with regard to the operation of tunnels. The methodology has involved developing a steady-state groundwater flow model, calibrated against a maximum groundwater condition, for the western portion of Milan city (Northern Italy, Lombardy Region). Overall findings pointed out that the most impacted areas are sections of subway tunnels already identified as submerged. This spatial coherence with historical information could act both as validation of the model and a step forward, as infiltrations resulting from an interaction with the water table were quantified. The methodology allowed for the improvement of the urban conceptual model and could support the stakeholders in adopting proper measures to manage the interactions between groundwater and the underground infrastructures. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

18 pages, 6072 KiB  
Article
Differentiating Nitrate Origins and Fate in a Semi-Arid Basin (Tunisia) via Geostatistical Analyses and Groundwater Modelling
by Kaouther Ncibi, Micòl Mastrocicco, Nicolò Colombani, Gianluigi Busico, Riheb Hadji, Younes Hamed and Khan Shuhab
Water 2022, 14(24), 4124; https://doi.org/10.3390/w14244124 - 18 Dec 2022
Cited by 12 | Viewed by 2335
Abstract
Despite efforts to protect the hydrosystems from increasing pollution, nitrate (NO3) remains a major groundwater pollutant worldwide, and determining its origin is still crucial and challenging. To disentangle the origins and fate of high NO3 (>900 mg/L) in [...] Read more.
Despite efforts to protect the hydrosystems from increasing pollution, nitrate (NO3) remains a major groundwater pollutant worldwide, and determining its origin is still crucial and challenging. To disentangle the origins and fate of high NO3 (>900 mg/L) in the Sidi Bouzid North basin (Tunisia), a numerical groundwater flow model (MODFLOW-2005) and an advective particle tracking (MODPATH) have been combined with geostatistical analyses on groundwater quality and hydrogeological characterization. Correlations between chemical elements and Principal Component Analysis (PCA) suggested that groundwater quality was primarily controlled by evaporite dissolution and subsequently driven by processes like dedolomitization and ion exchange. PCA indicated that NO3 origin is linked to anthropic (unconfined aquifer) and geogenic (semi-confined aquifer) sources. To suggest the geogenic origin of NO3 in the semi-confined aquifer, the multi-aquifer groundwater flow system and the forward and backward particle tracking was simulated. The observed and calculated hydraulic heads displayed a good correlation (R2 of 0.93). The residence time of groundwater with high NO3 concentrations was more significant than the timespan during which chemical fertilizers were used, and urban settlements expansion began. This confirmed the natural origin of NO3 associated with pre-Triassic embankment landscapes and located on domed geomorphic surfaces with a gypsum, phosphate, or clay cover. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

25 pages, 8392 KiB  
Article
Groundwater Modeling with Process-Based and Data-Driven Approaches in the Context of Climate Change
by Matia Menichini, Linda Franceschi, Brunella Raco, Giulio Masetti, Andrea Scozzari and Marco Doveri
Water 2022, 14(23), 3956; https://doi.org/10.3390/w14233956 - 5 Dec 2022
Cited by 2 | Viewed by 3424
Abstract
In the context of climate change, the correct management of groundwater, which is strategic for meeting water needs, becomes essential. Groundwater modeling is particularly crucial for the sustainable and efficient management of groundwater. This manuscript provides different types of modeling according to data [...] Read more.
In the context of climate change, the correct management of groundwater, which is strategic for meeting water needs, becomes essential. Groundwater modeling is particularly crucial for the sustainable and efficient management of groundwater. This manuscript provides different types of modeling according to data availability and features of three porous aquifer systems in Italy (Empoli, Magra, and Brenta systems). The models calibrated on robust time series enabled the performing of forecast simulations capable of representing the quantitative and qualitative response to expected climate regimes. For the Empoli aquifer, the process-based models highlighted the system’s ability to mitigate the effects of dry climate conditions thanks to its storage capability. The data-driven models concerning the Brenta foothill aquifer pointed out the high sensitivity of the system to climate extremes, thus suggesting the need for specific water management actions. The integrated data-driven/process-based approach developed for the Magra Valley aquifer remarked that the water quantity and quality effects are tied to certain boundary conditions over dry climate periods. This work shows that, for groundwater modeling, the choice of the suitable approach is mandatory, and it mainly depends on the specific aquifer features that result in different ways to be sensitive to climate. This manuscript also provides a novel outcome involving the integrated approach wherein it is a very efficient tool for forecasting modeling when boundary conditions, which significantly affect the behavior of such systems, are subjected to evolve under expected climate scenarios. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

23 pages, 4072 KiB  
Article
Simulation of Heat Flow in a Synthetic Watershed: The Role of the Unsaturated Zone
by Eric D. Morway, Daniel T. Feinstein and Randall J. Hunt
Water 2022, 14(23), 3883; https://doi.org/10.3390/w14233883 - 28 Nov 2022
Cited by 2 | Viewed by 1353
Abstract
Future climate forecasts suggest atmospheric warming, with expected effects on aquatic systems (e.g., cold-water fisheries). Here we apply a recently published and computationally efficient approach for simulating unsaturated/saturated heat transport with coupled flow (MODFLOW) and transport (MT3D-USGS) models via a synthetic three-dimensional (3D) [...] Read more.
Future climate forecasts suggest atmospheric warming, with expected effects on aquatic systems (e.g., cold-water fisheries). Here we apply a recently published and computationally efficient approach for simulating unsaturated/saturated heat transport with coupled flow (MODFLOW) and transport (MT3D-USGS) models via a synthetic three-dimensional (3D) representation of a temperate watershed. Key aspects needed for realistic representation at the watershed-scale include climate drivers, a layering scheme, consideration of surface-water groundwater interactions, and evaluation of transport parameters influencing heat flux. The unsaturated zone (UZ), which is typically neglected in heat transport simulations, is a primary focus of the analysis. Results from three model versions are compared—one that neglects UZ heat-transport processes and two that simulate heat transport through a (1) moderately-thick UZ and (2) a UZ of approximately double thickness. The watershed heat transport is evaluated in terms of temperature patterns and trends in the UZ, at the water table, below the water table (in the groundwater system), and along a stream network. Major findings are: (1) Climate forcing is the product of infiltration temperatures and infiltration rates; they combine into a single heat inflow forcing function. (2) The UZ acts as a low-pass filter on heat pulses migrating downward, markedly dampening the warming recharge signal. (3) The effect of warming on the watershed is also buffered by the mixing of temperatures at discharge points where shallow and deep flow converge. (4) The lateral extent of the riparian zone, defined as where the water table is near land surface (<1 m), plays an important role in determining the short-term dynamics of the stream baseflow response to heat forcing. Runoff generated from riparian areas is particularly important in periods when rejected infiltration during warm and wet periods generates extra runoff from low-lying areas to surface water. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

20 pages, 3526 KiB  
Article
Evaluation of Fresh Groundwater Lens Volume and Its Possible Use in Nauru Island
by Luca Alberti, Matteo Antelmi, Gabriele Oberto, Ivana La Licata and Pietro Mazzon
Water 2022, 14(20), 3201; https://doi.org/10.3390/w14203201 - 11 Oct 2022
Cited by 5 | Viewed by 4622
Abstract
A proper management of fresh groundwater lenses in small islands is required in order to avoid or at least limit uncontrolled saltwater intrusion and guarantee the availability of the resource even during drought occurrences. An accurate estimation of the freshwater volume stored in [...] Read more.
A proper management of fresh groundwater lenses in small islands is required in order to avoid or at least limit uncontrolled saltwater intrusion and guarantee the availability of the resource even during drought occurrences. An accurate estimation of the freshwater volume stored in the subsoil is a key step in the water management decision process. This study focused on understanding the hydrogeological system behaviour and on assessing the sustainable use of the groundwater resource in Nauru Atoll Island (Pacific Ocean). A first phase, concerning the hydrogeological characterization of the island, highlighted the occurrence of few drought-resilient freshwater lenses along the seashore. The second part of the study focused on the characterization of a freshwater lens found in the northern coastal area and identified such area as the most suitable for the development of groundwater infrastructures for water withdrawal. The characterization activities allowed quantifying the freshwater lens thickness and volume in order to assess the capability to satisfy the population water demand. A geo-electrical tomography survey was carried out, and a 3D density-dependent numerical model was implemented in SEAWAT. The model results demonstrated that in small islands freshwater can unexpectedly accumulate underground right along the seashore and not in the centre of the island as is commonly believed. Furthermore, the model can constitute a useful tool to manage the groundwater resources and would allow the design of sustainable groundwater exploitation systems, avoiding saltwater intrusion worsening. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

15 pages, 5836 KiB  
Article
ORGANICS: A QGIS Plugin for Simulating One-Dimensional Transport of Dissolved Substances in Surface Water
by Rudy Rossetto, Alberto Cisotto, Nico Dalla Libera, Andrea Braidot, Luca Sebastiani, Laura Ercoli and Iacopo Borsi
Water 2022, 14(18), 2850; https://doi.org/10.3390/w14182850 - 13 Sep 2022
Cited by 4 | Viewed by 2661
Abstract
Surface water in streams and rivers is a valuable resource and pollution events, if not tackled in time, may have dramatic impacts on aquatic ecosystems. As such, in order to prepare pollution prevention plans and measures or to set-up timely remedial options, especially [...] Read more.
Surface water in streams and rivers is a valuable resource and pollution events, if not tackled in time, may have dramatic impacts on aquatic ecosystems. As such, in order to prepare pollution prevention plans and measures or to set-up timely remedial options, especially in the early stages of pollution incidents, simulation tools are of great help for authorities, with specific reference to environmental protection agencies and river basin authorities. In this paper, we present the development and testing of the ORGANICS plugin embedded in QGIS. The plugin is a first attempt to embed surface water solute transport modelling into GIS for the simulation of the concentration of a dissolved substance (for example an organic compound) in surface water bodies including advection dispersion and degradation. This tool is based on the analytical solution of the popular advection/dispersion equation describing the transport of contaminants in surface water. By providing as input data the concentration measured at the entry point of a watercourse (inlet boundary condition) and the average speed of the surface water, the model simulates the concentration of a substance at a certain distance from the entry point, along the profile of the watercourse. The tool is first tested on a synthetic case. Then data on the concentration of the pharmaceutical carbamazepine monitored at the inlet and outlet of a vegetated channel, in a single day, are used to validate the tool in a real environment. The ORGANICS plugin aims at popularizing the use of simple modelling tools within a GIS framework, and it provides GIS experts with the ability to perform approximate, but fast, simulations of the evolution of pollutants concentration in surface water bodies. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

24 pages, 4998 KiB  
Article
Simulation of Heat Flow in a Synthetic Watershed: Lags and Dampening across Multiple Pathways under a Climate-Forcing Scenario
by Daniel T. Feinstein, Randall J. Hunt and Eric D. Morway
Water 2022, 14(18), 2810; https://doi.org/10.3390/w14182810 - 9 Sep 2022
Cited by 2 | Viewed by 1978
Abstract
Although there is widespread agreement that future climates tend toward warming, the response of aquatic ecosystems to that warming is not well understood. This work, a continuation of companion research, explores the role of distinct watershed pathways in lagging and dampening climate-change signals. [...] Read more.
Although there is widespread agreement that future climates tend toward warming, the response of aquatic ecosystems to that warming is not well understood. This work, a continuation of companion research, explores the role of distinct watershed pathways in lagging and dampening climate-change signals. It subjects a synthetic flow and transport model to a 30-year warming signal based on climate projections, quantifying the heat breakthrough on a monthly time step along connected pathways. The system corresponds to a temperate watershed roughly 27 km on a side and consists of (a) land-surface processes of overland flow, (b) infiltration through an unsaturated zone (UZ) above an unconfined sandy aquifer overlying impermeable bedrock, and (c) groundwater flow along shallow and deep pathlines that converge as discharge to a surface-water network. Numerical simulations show that about 40% of the warming applied to watershed infiltration arrives at the water table and that the UZ stores a large fraction of the upward-trending heat signal. Additionally, once groundwater reaches the surface-water network after traveling through the saturated zone, only about 10% of the original warm-up signal is returned to streams by discharge. However, increases in the simulated streamflow temperatures are of similar magnitude to increases at the water table, due to the addition of heat by storm runoff, which bypasses UZ and groundwater storage and counteracts subsurface dampening. The synthetic modeling method and tentative findings reported here provide a potential workflow for real-world applications of climate-change modeling at the full watershed scale. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

16 pages, 4574 KiB  
Article
A Stepwise Modelling Approach to Identifying Structural Features That Control Groundwater Flow in a Folded Carbonate Aquifer System
by Elisabetta Preziosi, Nicolas Guyennon, Anna Bruna Petrangeli, Emanuele Romano and Cristina Di Salvo
Water 2022, 14(16), 2475; https://doi.org/10.3390/w14162475 - 11 Aug 2022
Cited by 3 | Viewed by 1760
Abstract
This paper concerns a stepwise modelling procedure for groundwater flow simulation in a folded and faulted, multilayer carbonate aquifer, which constitutes a source of good quality water for human consumption in the Apennine Range in Central Italy. A perennial river acts as the [...] Read more.
This paper concerns a stepwise modelling procedure for groundwater flow simulation in a folded and faulted, multilayer carbonate aquifer, which constitutes a source of good quality water for human consumption in the Apennine Range in Central Italy. A perennial river acts as the main natural drain for groundwater while sustaining valuable water-related ecosystems. The spatial distribution of recharge was estimated using the Thornthwaite–Mather method on 60 years of climate data. The system was conceptualized as three main aquifers separated by two locally discontinuous aquitards. Three numerical models were implemented by gradually adding complexity to the model grid: single layer (2D), three layers (quasi-3D) and five layers (fully 3D), using an equivalent porous medium approach, in order to find the best solution with a parsimonious model setting. To overcome dry-cell problems in the fully 3D model, the Newton–Raphson formulation for MODFLOW-2005 was invoked. The calibration results show that a fully 3D model was required to match the observed distribution of aquifer outflow to the river baseflow. The numerical model demonstrated the major impact of folded and faulted geological structures on controlling the flow dynamics in terms of flow direction, water heads and the spatial distribution of the outflows to the river and springs. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

29 pages, 49573 KiB  
Article
Groundwater Potential Assessment Using GIS and Remote Sensing Techniques: Case Study of West Arsi Zone, Ethiopia
by Julla Kabeto, Dereje Adeba, Motuma Shiferaw Regasa and Megersa Kebede Leta
Water 2022, 14(12), 1838; https://doi.org/10.3390/w14121838 - 7 Jun 2022
Cited by 19 | Viewed by 9928
Abstract
Groundwater is a crucial source of water supply due to its continuous availability, reasonable natural quality, and being easily diverted directly to the poor community more cheaply and quickly. The West Arsi Zone residents remain surface water dependent due to traditional exploration of [...] Read more.
Groundwater is a crucial source of water supply due to its continuous availability, reasonable natural quality, and being easily diverted directly to the poor community more cheaply and quickly. The West Arsi Zone residents remain surface water dependent due to traditional exploration of groundwater, which is a tedious approach in terms of resources and time. This study uses remote sensing data and geographic information system techniques to evaluate the groundwater potential of the study area. This technique is a fast, accurate, and feasible technique. Groundwater potential and recharge zone influencing parameters were derived from Operational Land Imager 8, digital elevation models, soil data, lithological data, and rainfall data. Borehole data were used for results validation. With spatial analysis tools, the parameters affecting groundwater potential (LULC, soil, lithology, rainfall, drainage density, lineament density, slope, and elevation) were mapped and organized. The weight of the parameters according to percent of influence on groundwater potential and recharge was determined by Analytical Hierarchy Process according to their relative influence. For weights allocated to each parameter, the consistency ratio obtained was 0.033, which is less than 0.1, showing the weight allocated to each parameter is acceptable. In the weighted overlay analysis, from a percent influence point of view, slope, land use/cover, and lithology are equally important and account for 24% each, while the soil group has the lowest percent of influence, which accounts only 2% according to this study. The generated groundwater potential map has four ranks, 2, 3, 4, and 5, in which its classes are Low, Moderate, High, and Very High, respectively, based on its groundwater potential availability rank and class. The area coverage is 9825.84 ha (0.79%), 440,726.49 ha (35.46%), 761,438.61 ha (61.27%), and 30,748.68 ha (2.47%) of the study area, respectively. Accordingly, the western part of district is expected to have very high groundwater potential. High groundwater potential is concentrated in the central and western parts whereas moderate groundwater potential distribution is dominant in the eastern part of the area. The validation result of 87.61% confirms the very good agreement among the groundwater record data and groundwater potential classes delineated. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

16 pages, 3306 KiB  
Article
Minimizing Errors in the Prediction of Water Levels Using Kriging Technique in Residuals of the Groundwater Model
by Alireza Asadi and Kushal Adhikari
Water 2022, 14(3), 426; https://doi.org/10.3390/w14030426 - 29 Jan 2022
Cited by 3 | Viewed by 2849
Abstract
Groundwater monitoring and water level predictions have been a challenging issue due to the complexity of groundwater movement. Simplified numerical simulation models have been used to represent the groundwater system; these models however only provide the conservative approximation of the system and may [...] Read more.
Groundwater monitoring and water level predictions have been a challenging issue due to the complexity of groundwater movement. Simplified numerical simulation models have been used to represent the groundwater system; these models however only provide the conservative approximation of the system and may not always capture the local variations. Several other efforts such as coupling groundwater models with hydrological models and using geostatistical methods are being practiced to accurately predict the groundwater levels. In this study, we present a novel application of a geostatistical tool on residuals of the groundwater model. The kriging method was applied on the residuals of the numerical model (MODFLOW) generated by the TWDB (Texas Water Development Board) for the Edwards–Trinity (Plateau) aquifer. The study was done for the years 1995 through 2000 where 90% of the observation data was used for model simulation followed by cross-validation with the remaining 10% of the observations. The kriging method reduced the average absolute error of approximately 31 m (for MODFLOW simulation) to less than 5 m. Furthermore, the residuals’ average standard error was reduced from 9.7 to 4.7. This implies that the mean value of residuals over the entire period can be a good estimation for each year separately. The use of the kriging technique thus can provide improved monitoring of groundwater levels resulting in more accurate potentiometric surface maps. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Graphical abstract

Review

Jump to: Editorial, Research

31 pages, 1301 KiB  
Review
Improving Results of Existing Groundwater Numerical Models Using Machine Learning Techniques: A Review
by Cristina Di Salvo
Water 2022, 14(15), 2307; https://doi.org/10.3390/w14152307 - 25 Jul 2022
Cited by 17 | Viewed by 3629
Abstract
This paper presents a review of papers specifically focused on the use of both numerical and machine learning methods for groundwater level modelling. In the reviewed papers, machine learning models (also called data-driven models) are used to improve the prediction or speed process [...] Read more.
This paper presents a review of papers specifically focused on the use of both numerical and machine learning methods for groundwater level modelling. In the reviewed papers, machine learning models (also called data-driven models) are used to improve the prediction or speed process of existing numerical modelling. When long runtimes inhibit the use of numerical models, machine learning models can be a valid alternative, capable of reducing the time for model development and calibration without sacrificing accuracy of detail in groundwater level forecasting. The results of this review highlight that machine learning models do not offer a complete representation of the physical system, such as flux estimates or total water balance and, thus, cannot be used to substitute numerical models in large study areas; however, they are affordable tools to improve predictions at specific observation wells. Numerical and machine learning models can be successfully used as complementary to each other as a powerful groundwater management tool. The machine learning techniques can be used to improve calibration of numerical models, whereas results of numerical models allow us to understand the physical system and select proper input variables for machine learning models. Machine learning models can be integrated in decision-making processes when rapid and effective solutions for groundwater management need to be considered. Finally, machine learning models are computationally efficient tools to correct head error prediction of numerical models. Full article
(This article belongs to the Special Issue Groundwater Hydrological Model Simulation)
Show Figures

Figure 1

Back to TopTop