Mapping of soil contamination by using artificial neural networks and multivariate geostatistics

M. Kanevski, V. Demyanov, M. Maignan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

The work deals with the development and use of mixed models (artificial neural networks-ANN and modern geostatistical models) for the analysis of spatially distributed environmental data. When multivariate data have complex non-linear trends or high variability at different scales in the region of study it is proposed to use ANN to model non-linear large scale structures (trends) and then to apply multivariate geostatistics (co-kriging models) to the residuals. The proposed model is used for the spatial prediction of soil contamination by Chernobyl radionuclides.

Original languageEnglish
Title of host publicationArtificial Neural Networks - ICANN 1997
PublisherSpringer
Pages1125-1130
Number of pages6
ISBN (Electronic)9783540696209
ISBN (Print)9783540636311
DOIs
Publication statusPublished - 1997
Event7th International Conference on Artificial Neural Networks 1997 - Lausanne, Switzerland
Duration: 8 Oct 199710 Oct 1997

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume1327
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference7th International Conference on Artificial Neural Networks 1997
Abbreviated titleICANN 1997
CountrySwitzerland
CityLausanne
Period8/10/9710/10/97

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Mapping of soil contamination by using artificial neural networks and multivariate geostatistics'. Together they form a unique fingerprint.

  • Cite this

    Kanevski, M., Demyanov, V., & Maignan, M. (1997). Mapping of soil contamination by using artificial neural networks and multivariate geostatistics. In Artificial Neural Networks - ICANN 1997 (pp. 1125-1130). (Lecture Notes in Computer Science; Vol. 1327). Springer. https://doi.org/10.1007/BFb0020304