TY - JOUR
KW - artificial intelligence
KW - computer vision
KW - deep learning
KW - machine learning
KW - social media
KW - Biodiversity
KW - informatics
KW - Botany
KW - plants
KW - big data
AU - August Tom A.
AU - Pescott Oliver L.
AU - Joly Alexis
AU - Bonnet Pierre
AB - Summary 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.
BT - Patterns
DA - 10/2020
DO - https://doi.org/10.1016/j.patter.2020.100116
IS - 7
N2 - Summary 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.
PY - 2020
SN - 2666-3899
T2 - Patterns
TI - AI Naturalists Might Hold the Key to Unlocking Biodiversity Data in Social Media Imagery
UR - https://www.sciencedirect.com/science/article/pii/S2666389920301574
VL - 1
ER -