HR: 09:15h
AN: H21G-06 INVITED     [Abstracts]
TI: Subsurface Characterization with Support Vector Machines
AU: * Tartakovsky, D M
EM: dmt@ucsd.edu
AF: University of California, San Diego, EBU II, Room 577, Mail Code 0411, La Jolla, CA 92093 United States
AU: * Tartakovsky, D M
EM: dmt@ucsd.edu
AF: Los Alamos National Laboratory, MS B284, Los Alamos, NM 87545 United States
AU: Wohlberg, B
EM: brendt@t7.lanl.gov
AF: Los Alamos National Laboratory, MS B284, Los Alamos, NM 87545 United States
AU: Guadagnini, A
EM: alberto.guadagnini@polimi.it
AF: Politecnico di Milano, Piazza L. Da Vinci, 32, Milan, 20133 Italy
AB: A typical subsurface environment is heterogeneous, consists of multiple materials (geologic facies), and is often insufficiently characterized by data. 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. We demonstrate that the Support Vector Machine is a viable and efficient tool for lithofacies delineation, and compare it with a geostatistical approach. To illustrate our approach, and to demonstrate its advantages, we construct a synthetic porous medium consisting of two heterogeneous materials and then estimate boundaries between these materials from a few selected data points. Our analysis shows that the error in facies delineation by means of Support Vector Machines decreases logarithmically with increasing sampling density. We also introduce and analyze the use of regression Support Vector Machines to estimate the parameter values between points where the parameter is sampled.
DE: 1873 Uncertainty assessment (3275)
DE: 3245 Probabilistic forecasting (3238)
DE: 3265 Stochastic processes (3235, 4468, 4475, 7857)
DE: 3275 Uncertainty quantification (1873)
DE: 4468 Probability distributions, heavy and fat-tailed (3265)
SC: Hydrology [H]
MN: Fall Meeting 2005