AI Naturalists Might Hold the Key to Unlocking Biodiversity Data in Social Media Imagery.

artificial intelligence big data biodiversity botany computer vision deep learning informatics machine learning plants social media

Journal

Patterns (New York, N.Y.)
ISSN: 2666-3899
Titre abrégé: Patterns (N Y)
Pays: United States
ID NLM: 101767765

Informations de publication

Date de publication:
09 Oct 2020
Historique:
received: 29 05 2020
revised: 04 08 2020
accepted: 07 09 2020
entrez: 18 11 2020
pubmed: 19 11 2020
medline: 19 11 2020
Statut: epublish

Résumé

The increasing availability of digital images, coupled with sophisticated artificial intelligence (AI) techniques for image classification, presents an exciting opportunity for biodiversity researchers to create new datasets of species observations. We investigated whether an AI plant species classifier could extract previously unexploited biodiversity data from social media photos (Flickr). We found over 60,000 geolocated images tagged with the keyword "flower" across an urban and rural location in the UK and classified these using AI, reviewing these identifications and assessing the representativeness of images. Images were predominantly biodiversity focused, showing single species. Non-native garden plants dominated, particularly in the urban setting. The AI classifier performed best when photos were focused on single native species in wild situations but also performed well at higher taxonomic levels (genus and family), even when images substantially deviated from this. We present a checklist of questions that should be considered when undertaking a similar analysis.

Identifiants

pubmed: 33205140
doi: 10.1016/j.patter.2020.100116
pii: S2666-3899(20)30157-4
pmc: PMC7660428
doi:

Types de publication

Journal Article

Langues

eng

Pagination

100116

Informations de copyright

© 2020 The Authors.

Déclaration de conflit d'intérêts

The authors declare no competing interests.

Références

Proc Natl Acad Sci U S A. 2018 Jun 19;115(25):E5716-E5725
pubmed: 29871948
Nat Ecol Evol. 2018 Mar;2(3):406-407
pubmed: 29335570
Trends Ecol Evol. 2020 Jul;35(7):630-639
pubmed: 32521246
R Soc Open Sci. 2017 Jul 19;4(7):170170
pubmed: 28791142
Appl Plant Sci. 2018 Mar 14;6(2):e1029
pubmed: 29732259
Trends Ecol Evol. 2009 Sep;24(9):467-71
pubmed: 19586682
Zookeys. 2011;(150):71-87
pubmed: 22207807
PLoS Comput Biol. 2018 Apr 5;14(4):e1005993
pubmed: 29621236
Zookeys. 2015 Feb 02;(480):125-46
pubmed: 25685027

Auteurs

Tom A August (TA)

UK Centre for Ecology and Hydrology, Benson Lane, Crowmarsh Gifford, Wallingford, Oxfordshire OX10 8BB, UK.

Oliver L Pescott (OL)

UK Centre for Ecology and Hydrology, Benson Lane, Crowmarsh Gifford, Wallingford, Oxfordshire OX10 8BB, UK.

Alexis Joly (A)

INRIA Sophia-Antipolis - ZENITH Team, LIRMM - UMR 5506 - CC 477, 161 Rue Ada, 34095 Montpellier Cedex 5, France.

Pierre Bonnet (P)

AMAP, Univ Montpellier, CIRAD, CNRS, INRA, IRD, Montpellier, France.
CIRAD, UMR AMAP, Montpellier, France.

Classifications MeSH