HR: 1340h
AN: H53F-0542 [Abstracts]
TI: Conditional Simulation Using an Artificial Neural Network
AU: * Rizzo, D M
EM: drizzo@cems.uvm.edu
AF: University of Vermont, Department of Civil & Environmental Engineering
213 Votey Building, Burlington, VT 05405
United States
AU: Besaw, L
EM: lbesaw@cem.uvm.edu
AF: University of Vermont, Department of Civil & Environmental Engineering
213 Votey Building, Burlington, VT 05405
United States
AB:
Uncertainty in site characterization, due to sparsely distributed samples and incomplete site knowledge, is of major concern
in resource mining and environmental engineering. Scientists are able to model the spatial continuity and quantify
uncertainty of phenomena of interest (i.e. ore grade, subsurface contamination) through the generation and analysis of many
equiprobable stochastic simulations (realizations) using concepts of probability theory. We have developed a method of
generating equiprobable simulations by combining the traditional frame work of spatial dependencies witnessed in
geostatistics with an artificial neural network (ANN) algorithm know as counterpropagation. This new method allows for the
generation of simulations that respect the observed sample data as well as the data's underlying spatial
structure. Conditional simulation is a natural product of the counterpropagation network using random initial weights while
its architecture has computational advantages over other simulation generators due to its parallel information passing
topology. Computational speedup, due to the implementation of the algorithm on a local cluster of off-the-shelf
computational nodes and software, is another factor that will be discussed. The results of this research illustrate the
potential applicability and utility of using the counterpropagation algorithm to conduct a probabilistic assessment while
increasing interpretational value of site characterization data.
DE: 0520 Data analysis: algorithms and implementation
DE: 0555 Neural networks, fuzzy logic, machine learning
DE: 1829 Groundwater hydrology
DE: 1869 Stochastic hydrology
DE: 3245 Probabilistic forecasting (3238)
SC: Hydrology [H]
MN: Fall Meeting 2005