Overview of LifeCLEF 2021: an evaluation of Machine-Learning based Species Identification and Species Distribution Prediction

Alexis Joly (1) , Hervé Goëau (2, 3, 1) , Stefan Kahl (4) , Lukáš Picek (5) , Titouan Lorieul (1) , Elijah Cole (6) , Benjamin Deneu (1) , Maximilien Servajean (7, 8) , Andrew Durso (5) , Isabelle Bolon (9) , Hervé Glotin (10) , Robert Planqué (11) , Rafael Ruiz de Castañeda (9) , Willem-Pier Vellinga (11) , Holger Klinck (4) , Tom Denton (12) , Ivan Eggel (13) , Pierre Bonnet (2, 3) , Henning Müller (13)

1 ZENITH - Scientific Data Management
2 UMR AMAP - Botanique et Modélisation de l'Architecture des Plantes et des Végétations
3 Cirad-BIOS - Département Systèmes Biologiques
4 Cornell University [New York]
5 University of West Bohemia [Plzeň ]
6 CALTECH - California Institute of Technology
7 UPVM - Université Paul-Valéry - Montpellier 3
8 ADVANSE - ADVanced Analytics for data SciencE
9 UNIGE - Université de Genève = University of Geneva
10 DYNI - DYNamiques de l’Information
11 Xeno-canto foundation
12 Google LLC
13 HES-SO - Haute Ecole Spécialisée de Suisse Occidentale

Building accurate knowledge of the identity, the geographic distribution and the evolution of species is essential for the sustainable development of humanity, as well as for biodiversity conservation. However, the difficulty of identifying plants and animals is hindering the aggregation of new data and knowledge. Identifying and naming living plants or animals is almost impossible for the general public and is often difficult even for professionals and naturalists. Bridging this gap is a key step towards enabling effective biodiversity monitoring systems. The LifeCLEF campaign, presented in this paper, has been promoting and evaluating advances in this domain since 2011. The 2021 edition proposes four data-oriented challenges related to the identification and prediction of biodiversity: (i) PlantCLEF: cross-domain plant identification based on herbarium sheets, (ii) BirdCLEF: bird species recognition in audio soundscapes, (iii) GeoLifeCLEF: remote sensing based prediction of species, and (iv) SnakeCLEF: Automatic Snake Species Identification with Country-Level Focus.

Mots clés: Species Identification; Species Distribution Prediction

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]; Multimédia [cs.MM]; Modélisation et simulation; Biodiversité et Ecologie; Environnement et Société

Alexis Joly, Hervé Goëau, Stefan Kahl, Lukáš Picek, Titouan Lorieul, et al.. Overview of LifeCLEF 2021: an evaluation of Machine-Learning based Species Identification and Species Distribution Prediction. CLEF 2021 - 12th International Conference of the Cross-Language Evaluation Forum for European Languages, Sep 2021, Virtual Event, France. pp.371-393, ⟨10.1007/978-3-030-85251-1_24⟩. ⟨hal-03415990⟩