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

Autor:	August TA; UK Centre for Ecology and Hydrology, Benson Lane, Crowmarsh Gifford, Wallingford, Oxfordshire OX10 8BB, UK., Pescott OL; UK Centre for Ecology and Hydrology, Benson Lane, Crowmarsh Gifford, Wallingford, Oxfordshire OX10 8BB, UK., Joly A; INRIA Sophia-Antipolis - ZENITH Team, LIRMM - UMR 5506 - CC 477, 161 Rue Ada, 34095 Montpellier Cedex 5, France., Bonnet P; AMAP, Univ Montpellier, CIRAD, CNRS, INRA, IRD, Montpellier, France.; CIRAD, UMR AMAP, Montpellier, France.
Jazyk:	angličtina
Zdroj:	Patterns (New York, N.Y.) [Patterns (N Y)] 2020 Oct 09; Vol. 1 (7), pp. 100116. Date of Electronic Publication: 2020 Oct 09 (Print Publication: 2020).
DOI:	10.1016/j.patter.2020.100116
Abstrakt:	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. Competing Interests: The authors declare no competing interests. (© 2020 The Authors.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu