Description
Pl@ntNet is a participatory botanical observation platform allowing to identify plants from photos (using deep learning) and to share the observations with the community. The platform has three main front-ends: Pl@ntNet androïd (http://bit.ly/1K4D1eU), Pl@ntNet iOS (http://apple.co/2cMtWgu) and Pl@ntNet web (https://identify.plantnet.org/). Pl@ntNet was founded in 2010 by a consortium of four French research organisms (CIRAD, Inria, INRAE and IRD) and is now open to other members. More information about Pl@ntNet can be found at https://plantnet.org/. The occurrences in this collection are Pl@ntNet observations that have been identified only by the deep learning algorithm but which the algorithm confidence was sufficiently high to consider them as valid.
Data Records
The data in this occurrence resource has been published as a Darwin Core Archive (DwC-A), which is a standardized format for sharing biodiversity data as a set of one or more data tables. The core data table contains 12,142,287 records.
This IPT archives the data and thus serves as the data repository. The data and resource metadata are available for download in the downloads section. The versions table lists other versions of the resource that have been made publicly available and allows tracking changes made to the resource over time.
Versions
The table below shows only published versions of the resource that are publicly accessible.
How to cite
Researchers should cite this work as follows:
AFFOUARD A, JOLY A, LOMBARDO J, CHAMP J, GOEAU H, CHOUET M, GRESSE H, BOTELLA C, BONNET P (2023): Pl@ntNet automatically identified occurrences. v1.8. Pl@ntNet. Dataset/Occurrence. https://ipt.plantnet.org/resource?r=queries&v=1.8
Rights
Researchers should respect the following rights statement:
The publisher and rights holder of this work is Pl@ntNet. This work is licensed under a Creative Commons Attribution (CC-BY) 4.0 License.
GBIF Registration
This resource has been registered with GBIF, and assigned the following GBIF UUID: 14d5676a-2c54-4f94-9023-1e8dcd822aa0. Pl@ntNet publishes this resource, and is itself registered in GBIF as a data publisher endorsed by GBIF France.
Keywords
Occurrence; Observation; Occurrence
Contacts
Who created the resource:
-
https://orcid.org/0000-0002-2161-9940
Who can answer questions about the resource:
Who filled in the metadata:
-
Who else was associated with the resource:
Geographic Coverage
Plant observations from Pl@ntNet users come from all around the world.
| Bounding Coordinates | South West [-90, -180], North East [90, 180] |
|---|
Taxonomic Coverage
Pl@ntNet observations focus on plants.
| Kingdom | Plantae (Plant) |
|---|
Project Data
PlantNet is a participatory botanical observation platform allowing to identify plants from photos (using deep learning) and share observations with the community. This resource contains occurrences of plants automatically inferred from the plant observations submitted by the users of PlantNet application.
| Title | Pl@ntNet Queries |
|---|---|
| Identifier | queries |
| Funding | PlantNet is an open consortium founded by four French research organizations (CIRAD, Inria, INRAE, IRD) and supported by Agropolis Fondation. The two main funding resources are: (i) the annual contribution of the members of the consortium, (ii) donations from the end-users of PlantNet application (>10 million users). |
| Study Area Description | Entire world |
The personnel involved in the project:
Sampling Methods
No sampling protocol, opportunistic observations by Pl@ntNet users.
| Study Extent | Entire world, Plantae. |
|---|---|
| Quality Control | The validation is based on two main criteria: - the output of the automated identification algorithm is greater than a threshold (more precisely the top-1 probability output by the convolutional neural network is greater than 0.9) - the species name matches the checklist considered as the most trusted one for the country where the observation was done |
Method step description:
- This collection contains occurrences of plants automatically identified from the observations submitted by Pl@ntNet users to identify them (using one of the three applications: androïd, iOS, web, more information here: https://plantnet.org/). The following filters were applied: - is geolocated - is valid (top-1 softmax output > 0.9) - from a user with an enabled account or from an anonymous user - with a known species name (valid or synonym) in PN - species name != Cannabis - date_query > 0 - remove shared queries (already present in observation dataset) - remove duplicate session (keep the most recent query based on the session number) - must be in one of the WGSRPD polygon level 3 and the binomial species name (without author) must match a species of the corresponding Kew checklist
Bibliographic Citations
- Joly, A., Goëau, H., Bonnet, P., Bakić, V., Barbe, J., Selmi, S., ... & Yahiaoui I., Carré J., Mouysset E., Molino J.-f., Boujemaa B., Barthélémy D., (2014). Interactive plant identification based on social image data. Ecological Informatics, 23, 22-34. https://doi.org/10.1016/j.ecoinf.2013.07.006
- Joly, A., Bonnet, P., Goëau, H., Barbe, J., Selmi, S., Champ, J., Dufour-Kowalski, S., Affouard, A., Carré, J., Molino, J.-f., Boujemaa, N., & Barthélémy D., (2016). A look inside the Pl@ntNet experience. Multimedia Systems, 22(6), 751-766. https://doi.org/10.1007/s00530-015-0462-9
- Goëau, H., Bonnet, P., Joly, A., 2017. Plant identification based on noisy web data: the amazing performance of deep learning (LifeCLEF 2017). CLEF: Conference and Labs of the Evaluation Forum, Sep 2017, Dublin, Ireland. ⟨hal-01629183⟩ https://hal.archives-ouvertes.fr/hal-01629183
- Affouard, A., Goëau, H., Bonnet, P., Lombardo, J. C., & Joly, A., (2017). Pl@ntNet app in the era of deep learning. ICLR: International Conference on Learning Representations, Apr 2017, Toulon, France. ⟨hal-01629195⟩ https://hal.archives-ouvertes.fr/hal-01629195
Additional Metadata
| Alternative Identifiers | 14d5676a-2c54-4f94-9023-1e8dcd822aa0 |
|---|---|
| https://ipt.plantnet.org/resource?r=queries |