English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning is used in computer vision problems with important applicationsin several scientific fields. In ecology for example, there is a growinginterest in deep learning for automatizing repetitive analyses on large amountsof images, such as animal species identification.  However, there are challenging issues toward the wide adoption of deeplearning by the community of ecologists. First, there is a programming barrieras most algorithms are written in Python while most ecologists are versed in R.Second, recent applications of deep learning in ecology have focused oncomputational aspects and simple tasks without addressing the underlyingecological questions or carrying out the statistical data analysis to answerthese questions.  Here, we showcase a reproducible R workflow integrating both deep learningand statistical models using predator-prey relationships as a case study. Weillustrate deep learning for the identification of animal species on imagescollected with camera traps, and quantify spatial co-occurrence usingmultispecies occupancy models.  Despite average model classification performances, ecological inference wassimilar whether we analysed the ground truth dataset or the classified dataset.This result calls for further work on the trade-offs between time and resourcesallocated to train models with deep learning and our ability to properlyaddress key ecological questions with biodiversity monitoring. We hope that ourreproducible workflow will be useful to ecologists and applied statisticians.  All material (source of the Rmarkdown notebook and auxiliary files) isavailable fromhttps://github.com/oliviergimenez/computo-deeplearning-occupany-lynx.

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