Reference : Estimation of hydraulic conductivity and its uncertainty from grain-size data using G...
Scientific journals : Article
Engineering, computing & technology : Geological, petroleum & mining engineering
http://hdl.handle.net/2268/124959
Estimation of hydraulic conductivity and its uncertainty from grain-size data using GLUE and artificial neural networks
English
Rogiers, Bart [Katholieke Universiteit Leuven - KUL > Dept. of Earth and Environmental Sciences > Hydrogeologie > >]
Mallants, Dirk [Belgian Nuclear Research Centre (SCK•CEN) > Health and Safety > Institute for Environment > >]
Batelaan, Okke [Vrije Universiteit Brussel - VUB > Dept. of Hydrology and Hydraulic Engineering > > >]
Gedeon, Matej [> >]
Huysmans, Marijke [Katholieke Universiteit Leuven - KUL > Dept. of Earth and Environmental Sciences > Hydrogeologie > >]
Dassargues, Alain mailto [Université de Liège - ULg > Département Argenco : Secteur GEO3 > Hydrogéologie & Géologie de l'environnement >]
Jun-2012
Mathematical Geosciences
Springer
44
6
739-763
Yes (verified by ORBi)
International
1874-8961
1874-8953
Heidelberg
The Netherlands
[en] groundwater ; Early stopping ; cross-validation ; GLUE-ANN ; principal component analysis ; likelihood measures ; data-driven modelling ; sedimentary aquifer ; artificial neural networks ; generalized likelihood uncertainty estimation ; hydraulic conductivity
[en] Various approaches exist to relate saturated hydraulic conductivity (Ks) to grain-size data. Most methods use a single grain-size parameter and hence omit the information encompassed by the entire grain-size distribution. This study compares two data-driven modelling methods, i.e.multiple linear regression and artificial neural networks, that use the entire grain-size distribution data as input for Ks prediction. Besides the predictive capacity of the methods, the uncertainty associated with the model predictions is also evaluated, since such information is important for stochastic groundwater flow and contaminant transport modelling.
Artificial neural networks (ANNs) are combined with a generalized likelihood uncertainty estimation (GLUE) approach to predict Ks from grain-size data. The resulting GLUE-ANN hydraulic conductivity predictions and associated uncertainty estimates are compared with those obtained from the multiple linear regression models by a leave-one-out cross-validation. The GLUE-ANN ensemble prediction proved to be slightly better than multiple linear regression. The prediction uncertainty, however, was reduced by half an order of magnitude on average, and decreased at most by an order of magnitude. This demonstrates that the proposed method outperforms classical data-driven modelling techniques. Moreover, a comparison with methods from literature demonstrates the importance of site specific calibration.
The dataset used for this purpose originates mainly from unconsolidated sandy sediments of the Neogene aquifer, northern Belgium. The proposed predictive models are developed for 173 grain-size -Ks pairs. Finally, an application with the optimized models is presented for a borehole lacking Ks data.
SCK-CEN Mol
Researchers ; Professionals
http://hdl.handle.net/2268/124959
10.1007/s11004-012-9409-2
http://www.springerlink.com/content/1177570q5091l513/

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
publi220.pdfPublisher postprint1.88 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.