Pl@ntNet is a web platform started in 2009 and dedicated to identify, explore and share observations of plants using pictures. It is organized by location into different databases for the floras of Europe and tropical regions including the Indian Ocean, French Guyana and North African. The platform uses crowdsourcing approaches and machine learning tools. It supports a computational infrastructure for a mobile plant identification service based on automated image analysis. This service, freely available on iPhone and Android platforms and the web (
http://identify.plantnet-project.org/), was initially set up for a fraction of the European flora (800 species at the beginning). Currently there are 6,000 species of the European flora in the database and more than 20,000 users per day. With more than two million downloads in more than 3 years, this infrastructure is able to produce a large volume of botanical observations (more than two millions occurrence records, with a growing rate of more than 200% per year) contributed by people from many backgrounds and interests.
The volume of daily produced data by this initiative (5,600 occurrence records daily, produced this summer 2016) has a potential huge impact for biodiversity studies. The appropriate use of this huge volume of noisy data (in terms of identification and geolocation precision) will be only possible with the resolution of specific scientific challenges (related to large scale collaborative data revision and enrichment), that will be presented and discussed with the TDWG community.
Development of Pl@ntNet continues. Based on user feedback, we are considering different development directions for educational users in K-12 and at the university levels, and for expansion to new geographical regions including the Caribbean, North America, and the tropical Andeans.
Â
