The application of multivariate statistics and neural networks to the prediction of reservoir parameters using seismic attributes

Simple item page
dc.contributor.advisorLines, Laurence R.
dc.contributor.authorRussell, Brian Henderson
dc.date.accessioned2005-08-16T17:22:04Z
dc.date.available2005-08-16T17:22:04Z
dc.date.issued2004
dc.descriptionBibliography: p. 317-323en
dc.descriptionSome pages are in colour.en
dc.description.abstractIn this dissertation, I develop a number of new ideas for the statistical determination of reservoir parameters using seismic attributes, combining the classical techniques of multivariate statistics and the more recent methods of neural network analysis. I apply these techniques to both full seismic volumes and maps derived from intervals averaged through these volumes, using the Blackfoot dataset from central Alberta. In this dissertation I show that multilinear regression often provides too simple a solution to the parameter estimation problem, but that the traditional feedforward neural network often provides a solution that is overly complex. My proposed solution is to use radial basis function neural networks for the prediction of reservoir parameters, since this approach combines the power of the multilinear regression technique with the nonlinearity of neural networks. This conclusion is illustrated using both a model dataset that involves an A VO classification problem and the Blackfoot dataset that was mentioned earlier. In this dissertation, several new ideas are presented. First, I derive an improved regression formula for the prediction of S-wave sonic logs from combinations of other logs. Second, I apply a new approach to data clustering, called Mahalanobis clustering, to the interpretation of A VO crossplots and to the extraction of optimal clusters for the radial basis function neural network with centres. Finally, I develop a new approach that combines geostatistics with multiattribute transforms. This technique uses multivariate statistics and neural networks to improve the secondary dataset used in the collocated cokriging technique.
dc.format.extentxxv, 367 leaves : ill. ; 30 cm.en
dc.identifier.citationRussell, B. H. (2004). The application of multivariate statistics and neural networks to the prediction of reservoir parameters using seismic attributes (Doctoral thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca. doi:10.11575/PRISM/24453en_US
dc.identifier.doihttp://dx.doi.org/10.11575/PRISM/24453
dc.identifier.isbn061297717Xen
dc.identifier.lccAC1 .T484 2004 R87Aen
dc.identifier.urihttp://hdl.handle.net/1880/41947
dc.language.isoeng
dc.publisher.institutionUniversity of Calgaryen
dc.publisher.placeCalgaryen
dc.rightsUniversity of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.
dc.titleThe application of multivariate statistics and neural networks to the prediction of reservoir parameters using seismic attributes
dc.typedoctoral thesis
thesis.degree.disciplineGeology and Geophysics
thesis.degree.grantorUniversity of Calgary
thesis.degree.nameDoctor of Philosophy (PhD)
ucalgary.item.requestcopytrue
ucalgary.thesis.accessionTheses Collection 58.002:Box 1534 520492051
ucalgary.thesis.additionalcopyAC1 .T484 2004 R87 (Gallagher)en
ucalgary.thesis.notesUARCen
ucalgary.thesis.uarcreleaseyen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_Russell_2004.pdf
Size:
181.4 MB
Format:
Adobe Portable Document Format
Description:
Thesis
Download
Collections
Legacy Theses