Uncertainty Quantification with Support Vector Regression Prediction Models

Details

Serval ID
serval:BIB_8B928D0D37D2
Type
Inproceedings: an article in a conference proceedings.
Collection
Publications
Title
Uncertainty Quantification with Support Vector Regression Prediction Models
Title of the conference
Proceedings of the Accuracy conference, Leicester, England
Author(s)
Demyanov V., Pozdnoukhov A., Kanevski M., Christie M.
Publisher
International Spatial Accuracy Research Association
Publication state
Published
Issued date
2010
Pages
133-136
Language
english
Abstract
Uncertainty quantification of petroleum reservoir models is one of
the present challenges, which is usually approached with a wide range
of geostatistical tools linked with statistical optimisation or/and
inference algorithms. The paper considers a data driven approach
in modelling uncertainty in spatial predictions. Proposed semi-supervised
Support Vector Regression (SVR) model has demonstrated its capability
to represent realistic features and describe stochastic variability
and non-uniqueness of spatial properties. It is able to capture and
preserve key spatial dependencies such as connectivity, which is
often difficult to achieve with two-point geostatistical models.
Semi-supervised SVR is designed to integrate various kinds of conditioning
data and learn dependences from them. A stochastic semi-supervised
SVR model is integrated into a Bayesian framework to quantify uncertainty
with multiple models fitted to dynamic observations. The developed
approach is illustrated with a reservoir case study. The resulting
probabilistic production forecasts are described by uncertainty envelopes.
Keywords
uncertainty, prediction, petroleum, machine learning, support vectors, data integration
Create date
25/11/2013 18:18
Last modification date
03/03/2018 19:12
Usage data