Impact of model complexity and multi-scale data integration on the estimation of hydrogeological parameters in a dual-porosity aquifer

Tamayo-Mas, E.; Bianchi, Marco; Mansour, Majdi

doi:10.1007/s10040-018-1745-y

Cited by 13 publications

(11 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Water Resources Research overly complex and computationally intensive, making the parameter estimation procedure required to develop accurate estimates infeasible (Becker et al, 2019;Faunt, 2009;Moeck et al, 2018;Seibert et al, 2019;Tamayo-Mas et al, 2018).…”

Section: 1029/2020wr028059mentioning

confidence: 99%

“…Integrating satellite data for estimating the different water balance components can be immensely challenging due to the varying spatial and temporal resolutions (Tamayo-Mas et al, 2018). Moreover, we lack methods to estimate several key parameters, such as recharge, GW inflow/outflow, and surface water withdrawals, to "close the loop" of the water balance and directly estimate GW withdrawals.…”

Section: Introductionmentioning

confidence: 99%

“…These roadblocks have limited our ability to estimate GW withdrawals except in the special cases noted previously. In addition, traditional approaches to calibrate physical models that incorporate these diverse data sets are challenging because the models quickly become overly complex and computationally intensive, making the parameter estimation procedure required to develop accurate estimates infeasible (Becker et al, 2019;Faunt, 2009;Moeck et al, 2018;Seibert et al, 2019;Tamayo-Mas et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Groundwater Withdrawal Prediction Using Integrated Multitemporal Remote Sensing Data Sets and Machine Learning

Majumdar

Smith

Butler

et al. 2020

Water Resources Research

View full text Add to dashboard Cite

Effective monitoring of groundwater withdrawals is necessary to help mitigate the negative impacts of aquifer depletion. In this study, we develop a holistic approach that combines water balance components with a machine learning model to estimate groundwater withdrawals. We use both multitemporal satellite and modeled data from sensors that measure different components of the water balance and land use at varying spatial and temporal resolutions. These remote sensing products include evapotranspiration, precipitation, and land cover. Due to the inherent complexity of integrating these data sets and subsequently relating them to groundwater withdrawals using physical models, we apply random forests-a state of the art machine learning algorithm-to overcome such limitations. Here, we predict groundwater withdrawals per unit area over a highly monitored portion of the High Plains aquifer in the central United States at 5 km resolution for the Years 2002-2019. Our modeled withdrawals had high accuracy on both training and testing data sets (R 2 ≈ 0.99 and R 2 ≈ 0.93, respectively) during leave-one-out (year) cross validation with low mean absolute error (MAE) ≈ 4.31 mm and root-mean-square error (RMSE) ≈ 13.50 mm for the year 2014. Moreover, we found that even for the extreme drought year of 2012, we have a satisfactory test score (R 2 ≈ 0.84) with MAE ≈ 9.72 mm and RMSE ≈ 24.17 mm. Therefore, the proposed machine learning approach should be applicable to similar regions for proactive water management practices. Plain Language Summary Groundwater is an essential component of global water resources and is the largest source of Earth's liquid freshwater. It is extensively used for drinking water and to support global food production. Consequently, groundwater consumption has significantly increased owing to the pressing demands for water, food, and energy primarily driven by the increasing global population. Despite its critical role in the water-food-energy nexus, very few regions in the United States or elsewhere actively monitor their groundwater withdrawals (extraction or pumping) for implementing sustainable water management solutions. We develop a novel approach combining water balance components and land use measured using openly available remote sensing products with a machine learning model to estimate groundwater withdrawals. This framework automatically learns the interrelationships among these variables and groundwater withdrawals. Our study area is a portion of the High Plains Aquifer in Kansas (central United States) where overpumping has caused substantial groundwater storage loss. Also, a large amount of groundwater pumping data are available for validation. The results indicate good accuracy even for extreme drought years. Thus, this approach should be applicable to similar regions having sparsely or moderately available groundwater pumping data, enabling water managers to proactively implement sustainable solutions addressing water security issues.

show abstract

Section: 1029/2020wr028059mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Groundwater Withdrawal Prediction Using Integrated Multitemporal Remote Sensing Data Sets and Machine Learning

Majumdar

Smith

Butler

et al. 2020

Water Resources Research

View full text Add to dashboard Cite

show abstract

“…In order to quantify the relative significance of climate change and hydraulic properties on borehole yields, the finite difference radial flow model COOMPuTe (Cylindrical grid Object Oriented Model for Pumping Test analysis (Mansour et al, 2007;Tamayo-Mas et al, 2018)) was used to simulate pumping water level values at a pumped borehole at the idealised site in the Kennet catchment. This model solves the implicit numerical form of the 3-D governing flow equation in porous media, which is expressed in cylindrical coordinates as (Mansour et al, 2007): Figure 4) that represents the spatial and temporal variation of the saturated thickness of the domain.…”

Section: Conceptual and Numerical Groundwater Flow Modelmentioning

confidence: 99%

Analysis of the impact of hydraulic properties and climate change on estimations of borehole yields

Ascott

Mansour

Bloomfield

et al. 2019

Journal of Hydrology

View full text Add to dashboard Cite

show abstract

“…The main advantage of this approach is that it is a computationally efficient way of including abstractions in regional groundwater models because it does not refine the model mesh around the borehole. However, is it often found that heterogeneity and hydrogeological complexity close to boreholes control their behaviour (Rushton & Rathod, 1988;Tamayo-Mas et al, 2018;Upton et al, 2019). Consequently, most studies that have aimed to simulate fluctuations in withinborehole water levels and their performance accurately have applied numerical 'radial flow' models (Rushton & Booth, 1976;Connorton & Reed, 1978;Rushton & Weller, 1985;Rathod & Rushton, 1991;Rushton, 2006;Konikow et al, 2009;Mathias & Todman, 2010;Mansour et al, 2011;Upton et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

An integrated modelling approach for assessing the effect of multiscale complexity on groundwater source yields

Upton

Jackson

Butler

et al. 2020

Journal of Hydrology

View full text Add to dashboard Cite

A new multi-scale groundwater modelling methodology is presented to simulate pumped water levels in abstraction boreholes within regional groundwater models, providing a robust tool for assessing the sustainable yield of supply boreholes and improving our understanding of groundwater availability during drought. A 3D borehole-scale model, which solves the Darcy-Forchheimer equation in cylindrical co-ordinates to simulate both linear and non-linear radial flow to a borehole in a heterogeneous aquifer, is embedded within a Cartesian grid, using a hybrid radial-Cartesian finite difference method. The local-scale model is coupled to a regional groundwater model, ZOOMQ3D, using the OpenMI model linkage software, providing a flexible and efficient tool for assessing the behaviour of a groundwater source within its regional hydrogeological context during historic droughts and under climate change. The advantages of the new method are demonstrated through application to a Chalk supply borehole in the UK.

show abstract

Impact of model complexity and multi-scale data integration on the estimation of hydrogeological parameters in a dual-porosity aquifer

Cited by 13 publications

References 65 publications

Groundwater Withdrawal Prediction Using Integrated Multitemporal Remote Sensing Data Sets and Machine Learning

Groundwater Withdrawal Prediction Using Integrated Multitemporal Remote Sensing Data Sets and Machine Learning

Analysis of the impact of hydraulic properties and climate change on estimations of borehole yields

An integrated modelling approach for assessing the effect of multiscale complexity on groundwater source yields

Contact Info

Product

Resources

About