Pl@ntnet (2012 -)
Pl@ntNet is a citizen science platform that uses deep learning and big data to help people identify plants with their mobile phones. It is used in more than 200 countries by 25M users and allows up to 2M identifications per day of about 50K plant species. Pl@ntNet includes an Android app, an iOs app and a web version. Given a plant image (photo), the application returns a ranked list of the most likely species, together with one or more images of individual plants, allowing interactive validation by the users. The back-office running on the server side of the platform is based on our Snoop visual search engine and NewSQL technology (Cassandra) for big data management. Pl@ntNet relies on collaborative AI, where the users’ observations are revised and enriched by the users in order to serve as training data for an AI multi-head model of plant species. The model is trained on Jean Zay supercomputer on a big dataset of 8M valid observations (5-6 days of training).
The PlantGame (2016 -)
The Plant Game is a participatory game whose purpose is the production of big taxonomic data to improve our knowledge of biodiversity. One major contribution is the active training of the users based on innovative sub-task creation and assignment processes that are adaptive to the increasing skills of the user. Thousands of players are registered and produce on average about tens new validated plant observations per day. The accuracy of the produced taxonnomic tags is very high (about 95%), which is quite impressive considering the fact that a majority of users are beginners when they start playing.
