University of California, San Diego
Campus Directory| Search
Daniel TartakovskyPublications › guadagnini-2006-support
› Publications › Teaching › Research group › Useful links

Cite Details

A. Guadagnini, D. M. Tartakovsky, B. E. Wohlberg and M. De Simoni, "Support Vector Machines for delineation of geologic facies from poorly differentiated data", in Proceedings of the XV International Conference "Computational Methods in Water Resources (CMWR 2006)" , edited by Philip J. Binning, Peter K. E.ngesgaard, Helge K. Dahle, George F. Pinder and William G. Gray, (Copenhagen, Denmark (, Jun 2006


The ability to delineate geologic facies and to estimate their properties from sparse data is essential for modeling physical and biochemical processes occurring in the subsurface. If such data are poorly differentiated, this challenging task is complicated further by preventing a clear distinction between different hydrofacies even at locations where data are available. We study the problem of facies delineation in geologic formations by means of the Support Vector Machine (SVM). To show the potential of the SVM, we randomly generate a two-dimensional porous medium composed of two heterogeneous materials, and then reconstruct boundaries between these materials from a few data points. We assess the performance and accuracy of the SVM-based facies delineation technique and assess in the presence of either well differentiated or poorly differentiated information about hydraulic parameters, such as hydraulic conductivity.

BibTeX Entry

author = {A. Guadagnini and D. M. Tartakovsky and B. E. Wohlberg and M. De Simoni},
title = {Support Vector Machines for delineation of geologic facies from poorly differentiated data},
year = {2006},
month = Jun,
urlpdf = {},
booktitle = {Proceedings of the XV {I}nternational {C}onference "{C}omputational {M}ethods in {W}ater {R}esources ({CMWR} 2006)" , edited by {P}hilip {J}. {B}inning, {P}eter {K}. {E.}ngesgaard, {H}elge {K}. {D}ahle, {G}eorge {F}. {P}inder and {W}illiam {G}. {G}ray},
address = {Copenhagen, Denmark (}