Overview of LifeCLEF 2024: Challenges on species distribution prediction and identification

Joly Alexis, Picek Lukáš, Kahl Stefan, Goeau Hervé, Espitalier Vincent, Botella Christophe, Marcos Diego, Estopinan Joaquim, Leblanc César, Larcher Théo, Šulc Milan, Hrúz Marek, Servajean Maximilien, Glotin Hervé, Planqué Robert, Vellinga Willem-Pier, Klinck Holger, Denton Tom, Eggel Ivan, Bonnet Pierre, Müller Henning. 2024. Overview of LifeCLEF 2024: Challenges on species distribution prediction and identification. In : Experimental IR Meets Multilinguality, Multimodality, and Interaction. Goeuriot Lorraine (ed.), Mulhem Philippe (ed.), Quénot Georges (ed.), Schwab Didier (ed.), Maria Di Nunzio Georgio (ed.), Soulier Laure (ed.), Galuščáková Petra (ed.), García Seco de Herrera Alba (ed.), Faggioli Guglielmo (ed.), Ferro Nicola (ed.). Cham : Springer, 183-207. (Lecture Notes in Computer Science, 14959, 14959) ISBN 978-3-031-71908-0 International Conference of the Cross-Language Evaluation Forum for European Languages (CLEF 2024). 15, Grenoble, France, 9 Septembre 2024/12 Septembre 2024.

Résumé : Biodiversity monitoring using machine learning and AI- based approaches is becoming increasingly popular. It allows for providing detailed information on species distribution and ecosystem health at a large scale and contributes to informed decision-making on environmental protection. Species identification based on images and sounds, in particular, is invaluable for facilitating biodiversity monitoring efforts and enabling prompt conservation actions to protect threatened and endangered species. The multiplicity of methods developed, however, makes it important to evaluate their performance on realistic datasets and using standardized evaluation protocols. The LifeCLEF lab has been setting up such evaluations since 2011, encouraging machine learning researchers to work on this topic and promoting the adoption of the technologies developed by stakeholders. The 2024 edition proposes five data-oriented challenges related to the identification and prediction of biodiversity: (i) BirdCLEF: bird call identification in soundscapes, (ii) FungiCLEF: revisiting fungi species recognition beyond 0-1 cost, (iii) GeoLifeCLEF: remote sensing based prediction of species, (iv) PlantCLEF: Multi-species identification in vegetation plot images, and (v) SnakeCLEF: revisiting snake species identification in medically important scenarios. This paper overviews the motivation, methodology, and main outcomes of those five challenges.

Mots-clés Agrovoc : identification, distribution des populations, apprentissage machine, intelligence artificielle, biodiversité

Classification Agris : U10 - Informatique, mathématiques et statistiques
P01 - Conservation de la nature et ressources foncières

Agences de financement européennes : European Commission

Projets sur financement : (EU) safeGUARDing biodivErsity aNd critical ecosystem services across sectors and scales, (EU) Modern Approaches to the Monitoring of BiOdiversity

Auteurs et affiliations

• Joly Alexis, INRIA (FRA)
• Picek Lukáš, INRIA (FRA)
• Kahl Stefan, Cornell University (USA)
• Goeau Hervé, CIRAD-BIOS-UMR AMAP (FRA)
• Espitalier Vincent, CIRAD-BIOS-UMR AMAP (FRA)
• Botella Christophe, INRIA (FRA)
• Marcos Diego, INRIA (FRA)
• Estopinan Joaquim, INRIA (FRA)
• Leblanc César, INRIA (FRA)
• Larcher Théo, INRIA (FRA)
• Šulc Milan, Second Foundation (CZE)
• Hrúz Marek, University of West Bohemia (CZE)
• Servajean Maximilien, Université de Montpellier Paul Valéry (FRA)
• Glotin Hervé, Université de Toulon et du Var (FRA)
• Planqué Robert, Xeno-canto foundation (NLD)
• Vellinga Willem-Pier, Xeno-canto foundation (NLD)
• Klinck Holger, Cornell University (USA)
• Denton Tom, Google Deepmind (USA)
• Eggel Ivan, HES (CHE)
• Bonnet Pierre, CIRAD-BIOS-UMR AMAP (FRA) ORCID: 0000-0002-2828-4389
• Müller Henning, HES (CHE)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/613246/)

Métriques

[ Page générée et mise en cache le 2025-09-08 ]