Document Detail


A hybrid artificial neural network-numerical model for ground water problems.
MedLine Citation:
PMID:  17760585     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Numerical models constitute the most advanced physical-based methods for modeling complex ground water systems. Spatial and/or temporal variability of aquifer parameters, boundary conditions, and initial conditions (for transient simulations) can be assigned across the numerical model domain. While this constitutes a powerful modeling advantage, it also presents the formidable challenge of overcoming parameter uncertainty, which, to date, has not been satisfactorily resolved, inevitably producing model prediction errors. In previous research, artificial neural networks (ANNs), developed with more accessible field data, have achieved excellent predictive accuracy over discrete stress periods at site-specific field locations in complex ground water systems. In an effort to combine the relative advantages of numerical models and ANNs, a new modeling paradigm is presented. The ANN models generate accurate predictions for a limited number of field locations. Appending them to a numerical model produces an overdetermined system of equations, which can be solved using a variety of mathematical techniques, potentially yielding more accurate numerical predictions. Mathematical theory and a simple two-dimensional example are presented to overview relevant mathematical and modeling issues. Two of the three methods for solving the overdetermined system achieved an overall improvement in numerical model accuracy for various levels of synthetic ANN errors using relatively few constrained head values (i.e., cells), which, while demonstrating promise, requires further research. This hybrid approach is not limited to ANN technology; it can be used with other approaches for improving numerical model predictions, such as regression or support vector machines (SVMs).
Authors:
Ferenc Szidarovszky; Emery A Coppola; Jingjie Long; Anthony D Hall; Mary M Poulton
Related Documents :
17224745 - Trained artificial neural network for glaucoma diagnosis using visual field data: a com...
16562995 - In silico prediction of buffer solubility based on quantum-mechanical and hqsar- and to...
18459185 - Dynamic decision support graph--visualization of ann-generated diagnostic indications o...
12906245 - Uncertainty in the output of artificial neural networks.
15749165 - Song learning in birds: diversity and plasticity, opportunities and challenges.
17108375 - Robust pose estimation from a planar target.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Ground water     Volume:  45     ISSN:  0017-467X     ISO Abbreviation:  Ground Water     Publication Date:    2007 Sep-Oct
Date Detail:
Created Date:  2007-08-31     Completed Date:  2008-01-03     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9882886     Medline TA:  Ground Water     Country:  United States    
Other Details:
Languages:  eng     Pagination:  590-600     Citation Subset:  IM    
Affiliation:
Department of Systems and Industrial Engineering, University of Arizona, Tucson, AZ 85721-0020, USA. szidar@sie.arizona.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Models, Theoretical*
Neural Networks (Computer)*
Water Movements
Water Supply*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Estimation of recharge from floods in disconnected stream-aquifer systems.
Next Document:  Fracture control of ground water flow and water chemistry in a rock aquitard.