Mining co-variation patterns from ecological data: a process to aid the construction and validation of computer models

Florent Arthaud Serge Fenet 1 Adriana Prado 2
1 DM2L - Data Mining and Machine Learning
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : This paper presents the use of a data mining algorithm to extract co-variation patterns from ecological data. The system of interest is a network of shallow fish-ponds in the region of the Dombes, in France, from which we gathered more than 4 years of measures. These data were analysed and the extracted patterns were structured in a hypergraph that allowed us to infer the most pertinent parameters from which construct a dynamical model of a major vegetation/plakton relationship.
Document type :
Conference papers
Complete list of metadatas
https://hal.archives-ouvertes.fr/hal-01352996
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Wednesday, August 10, 2016 - 4:18:21 PM
Last modification on : Wednesday, November 20, 2019 - 3:09:06 AM

Identifiers

  • HAL Id : hal-01352996, version 1

Collections

CNRS | EC-LYON | UNIV-LYON2 | LIRIS | INSA-LYON | UNIV-LYON1 | INSA-GROUPE | LABEXIMU | UDL

Citation

Florent Arthaud, Serge Fenet, Adriana Prado. Mining co-variation patterns from ecological data: a process to aid the construction and validation of computer models. CompSust2012 : 3rd International Conference on Computational Sustainability, Jun 2012, University of Copenhagen, Denmark. pp.1-3. ⟨hal-01352996⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

121

Contact

Informations

CCSD