Estimation of heterogeneous aquifer parameters from piezometric data using ridge functions and neural networks

Mantoglou, A

dc.contributor.author	Mantoglou, A	en
dc.date.accessioned	2014-03-01T01:18:57Z
dc.date.available	2014-03-01T01:18:57Z
dc.date.issued	2003	en
dc.identifier.issn	1436-3240	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/15280
dc.subject	Aquifer modelling	en
dc.subject	Inverse modelling	en
dc.subject	Model calibration	en
dc.subject	Neural networks	en
dc.subject.classification	Engineering, Environmental	en
dc.subject.classification	Engineering, Civil	en
dc.subject.classification	Environmental Sciences	en
dc.subject.classification	Statistics & Probability	en
dc.subject.classification	Water Resources	en
dc.subject.other	aquifer characterization	en
dc.subject.other	artificial neural network	en
dc.subject.other	calibration	en
dc.subject.other	heterogeneity	en
dc.subject.other	hydrological modeling	en
dc.subject.other	piezometer	en
dc.title	Estimation of heterogeneous aquifer parameters from piezometric data using ridge functions and neural networks	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/s00477-003-0155-3	en
heal.identifier.secondary	http://dx.doi.org/10.1007/s00477-003-0155-3	en
heal.language	English	en
heal.publicationDate	2003	en
heal.abstract	Inverse modeling aims to estimate transmissivity and other parameters needed by distributed aquifer models, using piezometric measurements. While these parameters are highly variable in space, the two-dimensional aquifer area is essentially empty of measurements (""curse of dimensionality""). To address this problem, a representation of the two-dimensional transmissivity map based on ridge functions and neural networks is introduced and applied to inverse aquifer modeling. The proposed representation has good expressive power, i.e. it is concise and convergences quickly as the number of parameters are increased, and it is expected to express complex transmissivity variations with relatively few parameters which can be estimated from the piezometric measurements. A simple regularization that can dampen erratic high frequency terms in the estimated parameters is suggested. Several examples indicate that the proposed parameterization can handle diverse types of transmissivity variations while it is particulary suited when the true transmissivity map exhibits specific sorts of heterogeneity with large anisotropies or abrupt changes along lines.	en
heal.publisher	SPRINGER-VERLAG	en
heal.journalName	Stochastic Environmental Research and Risk Assessment	en
dc.identifier.doi	10.1007/s00477-003-0155-3	en
dc.identifier.isi	ISI:000186542900007	en
dc.identifier.volume	17	en
dc.identifier.issue	5	en
dc.identifier.spage	339	en
dc.identifier.epage	352	en