BME analysis of neural network residual data from the Chernobyl fallout: bayesian and non-bayesian approaches

Details

Serval ID
serval:BIB_02E77A01E386
Type
Inproceedings: an article in a conference proceedings.
Collection
Publications
Title
BME analysis of neural network residual data from the Chernobyl fallout: bayesian and non-bayesian approaches
Title of the conference
geoENV III: Geostatistics for Environmental Applications Proceedings of the 3rd European Conference on Geostatistics for Environmental Applications, Avignon, France
Author(s)
Christakos G., Serre M., Demyanov V., Timonin V., Kanevski M., Savelieva E., Chernov S.
ISBN
978-94-010-0810-5
ISSN-L
0924-1973
Publication state
Published
Issued date
2000
Peer-reviewed
Oui
Editor
Monestiez P., Allard D., Froidevaux R.
Volume
11
Pages
509-510
Language
english
Notes
Christakos2000
Abstract
Radioactively contaminated territories after the Chernobyl accident
are characterized by non-stationary trends and soft (uncertain) information
about the average concentration of radionuclide in soil. Large-scale
decision-oriented mapping in this situation involves using the Neural
Network method to determine the general non-linear trends of the
data, and the BME method to analyze the hard and soft residual information
generated after the mean trend is removed from the data. In this
work we explore different approaches to map the residual soft data,
which include a Bayesian and a non-Bayesian framework. These approaches
are illustrated by means of the Cs137 mapping case study in Briansk,
Russia
Create date
25/11/2013 19:02
Last modification date
20/08/2019 13:25
Usage data