Botella Christophe, Servajean Maximilien, Bonnet Pierre, Joly Alexis.
2019. Overview of GeoLifeCLEF 2019: Plant species prediction using environment and animal occurrences.
In : Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. Cappellato Linda (ed.), Ferro Nicola (ed.), Losada David E. (ed.), Müller Henning (ed.)
|
Version publiée
- Anglais
Sous licence  .
paper_257.pdf Télécharger (2MB) | Prévisualisation |
Résumé : The GeoLifeCLEF challenge aim to evaluate location-based species recommendation algorithms through open and perennial datasets in a reproducible way. It offers a ground for large-scale geographic species prediction using cross-kingdom occurrences and spatialized environmental data. The main novelty of the 2019 campaign over the previous one is the availability of new occurrence datasets: (i) automatically identified plant occurrences coming from the popular Pl@ntnet platform and (ii) animal occurrences coming from the GBIF platform. This paper presents an overview of the resources and assessment of the GeoLifeCLEF 2019 task, synthesizes the approaches used by the participating groups and analyzes the main evaluation results. We highlight new successful approaches relevant for community modeling like models learning to predict occurrences from many biological groups and methods weighting occurrences based on species infrequency.
Mots-clés libres : Biodiversity, Environmental data, Species recommendation, Species distribution models, Model performance
Auteurs et affiliations
- Botella Christophe, INRIA (FRA)
- Servajean Maximilien, CNRS (FRA)
-
Bonnet Pierre, CIRAD-BIOS-UMR AMAP (FRA)
ORCID: 0000-0002-2828-4389
- Joly Alexis, INRIA (FRA)
Source : Cirad-Agritrop (https://agritrop.cirad.fr/598378/)
[ Page générée et mise en cache le 2021-08-06 ]
