Trade-off between deep learning for species identification and inference about predator-prey co-occurrence: Reproducible R workflow integrating models in computer vision and ecological statistics

Gimenez Olivier, Kervellec Maëlis, Fanjul Jean-Baptiste, Chaine Anna, Marescot Lucile, Bollet Yoann, Duchamp Christophe. 2022. Trade-off between deep learning for species identification and inference about predator-prey co-occurrence: Reproducible R workflow integrating models in computer vision and ecological statistics. Computo, 29 p.

https://doi.org/10.57750/yfm2-5f45

Article de revue ; Article de recherche ; Article de revue à comité de lecture Revue en libre accès total

Prévisualisation

Version publiée - Anglais
Sous licence

.
Gimenez_et_al.2022.Computo.pdf
Télécharger (26MB) | Prévisualisation

Url - autres données associées : https://github.com/computorg/published-202204-deeplearning-occupancy-lynx

Résumé : Deep learning is used in computer vision problems with important applications in several scientific fields. In ecology for example, there is a growing interest in deep learning for automatizing repetitive analyses on large amounts of images, such as animal species identification. However, there are challenging issues toward the wide adoption of deep learning by the community of ecologists. First, there is a programming barrier as most algorithms are written in Python while most ecologists are versed in R. Second, recent applications of deep learning in ecology have focused on computational aspects and simple tasks without addressing the underlying ecological questions or carrying out the statistical data analysis to answer these questions. Here, we showcase a reproducible R workflow integrating both deep learning and statistical models using predator-prey relationships as a case study. We illustrate deep learning for the identification of animal species on images collected with camera traps, and quantify spatial co-occurrence using multispecies occupancy models. Despite average model classification performances, ecological inference was similar whether we analysed the ground truth dataset or the classified dataset. This result calls for further work on the trade-offs between time and resources allocated to train models with deep learning and our ability to properly address key ecological questions with biodiversity monitoring. We hope that our reproducible workflow will be useful to ecologists and applied statisticians.

Mots-clés Agrovoc : application des ordinateurs, écologie, écologie animale, logiciel, imagerie, apprentissage animal

Mots-clés libres : Deep learning, Multi-species data, Predator-prey relationships, Biological conservation

Champ stratégique Cirad : CTS 1 (2019-) - Biodiversité

Agences de financement hors UE : Région Auvergne-Rhône-Alpes, Conseil Général de l'Ain, Conseil Général du Jura, Fédération Nationale des Chasseurs, Ministère français de l'Environnement, Office Français de la Biodiversité, Agence Nationale de la Recherche

Projets sur financement : (FRA) Effets de la gestion et du climat sur la dynamique des communautés - Développement d'une démographie multi-espèce.

Auteurs et affiliations