Description
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 13,880 records.
1 extension data tables also exist. An extension record supplies extra information about a core record. The number of records in each extension data table is illustrated below.
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:
D'hondt B, Steen F, Neukermans A, Adriaens T, Dalby L, Gillespie M A, Mellerup K A, Høye T T, Bonnet P, Joly A, Govaert S (2026). IAS pilot - Observations of alien plant species using a vehicle-mounted camera system in Flanders (Belgium). Version 1.1. Research Institute for Nature and Forest (INBO). Occurrence dataset. https://ipt.inbo.be/resource?r=ias-pilot-be&v=1.1
Rights
Researchers should respect the following rights statement:
The publisher and rights holder of this work is Research Institute for Nature and Forest (INBO). To the extent possible under law, the publisher has waived all rights to these data and has dedicated them to the Public Domain (CC0 1.0). Users may copy, modify, distribute and use the work, including for commercial purposes, without restriction.
GBIF Registration
This resource has been registered with GBIF, and assigned the following GBIF UUID: 9c85f295-cc92-473c-969a-bb5d3eccfd0b. Research Institute for Nature and Forest (INBO) publishes this resource, and is itself registered in GBIF as a data publisher endorsed by Belgian Biodiversity Platform.
Keywords
Occurrence; CamAlien; invasive species; alien species; non-native species; IAS; plants
Contacts
- Metadata Provider ●
- Originator ●
- Point Of Contact
https://orcid.org/0000-0002-1330-1457
- Originator
- Originator
- Originator
- Metadata Provider ●
- Originator
- Metadata Provider ●
- Originator
- Originator
- Metadata Provider ●
- Originator
- Metadata Provider ●
- Originator
Geographic Coverage
Flanders, Belgium
| Bounding Coordinates | South West [50.705, 4.216], North East [51.072, 4.983] |
|---|
Taxonomic Coverage
6 non-native species of vascular plants
| Genus | Reynoutria sp. |
|---|---|
| Species | Ailanthus altissima, Impatiens glandulifera, Robinia pseudoacacia, Rosa rugosa |
Temporal Coverage
| Start Date / End Date | 2024-07-18 / 2024-09-09 |
|---|
Project Data
Biodiversa+ monitoring pilots aim to facilitate the harmonisation of biodiversity monitoring at a transnational level, by testing common protocols and new technologies. The Biodiversa+ IAS pilot project (2023-2027) implemented the monitoring of invasive alien plants using a vehicle-mounted camera system in various countries across Europe.
| Title | Monitoring Invasive Alien Species with image-based methods |
|---|---|
| Identifier | IAS pilot |
| Funding | Biodiversa+, the European Biodiversity Partnership supporting excellent research on biodiversity with an impact on policy and society. Biodiversa+ was jointly developed by BiodivERsA and the European Commission as part of the EU Biodiversity Strategy 2030. |
| Study Area Description | Europe |
| Design Description | During several field seasons of the project, the CamAlien camera system (AI Lab, Denmark) was mounted on vehicles to capture images of the vegetation along linear transport infrastructure. Typically, this system was mounted on a car for the monitoring of roadside vegetation. The system was also tested on other types of vehicles (e.g., boats, trains). Plant species were then identified from the images using species recognition algorithms (Pl@ntNet). The focus was specifically on invasive alien plants, in the context of large-scale surveys, rapid detection, and support of species management. This pilot study was conducted in 11 countries across Europe. |
The personnel involved in the project:
- Author
Sampling Methods
The CamAlien system essentially is a camera mounted on a moving car. The system continuously takes photos while driving, even at highway speeds. Images are anonymised for GDPR compliance and analysis is powered by the Pl@ntNet API, which returns species confidence scores. The software applies adaptive recording based on speed, and a human observer is able to tag plant sightings on the go, helping to build a better training set for the image recognition models.
| Study Extent | The study aimed to detect a set of predetermined invasive plant species in roadside verges on a regional scale during the field season of several consecutive years. |
|---|---|
| Quality Control | The species recognition algorithm (Pl@ntNet) returned a confidence value for each identification of a plant species in an image. A threshold value above which a confidence score is considered accurate was determined through expert validation and statistical modelling. Expert botanists annotated a subset of images with a range of confidence scores for presence/absence of the classified species. Presence/absence was then modelled as a binary response in a logistic GLM (General Linear Model) against confidence score. The confidence score providing a 50% probability of presence was then selected as threshold value. The images resulting from this filtering process were not all individually reviewed. |
Method step description:
- Partners from the project consortium defined the set of target species (invasive alien plant species of interest), and agreed on a generic sampling plan for the coming field season.
- The CamAlien camera system was mounted on a vehicle.
- The vehicle was driven along the road infrastructure, with the CamAlien system running.
- The resulting images were shared with the lead partner (Aarhus University), for storage and first-level edits.
- The images were transferred to Pl@ntNet, which returned classifications (identifications) of the target species in each of the images.
- The returned data were processed, by filtering on the confidence level threshold, or any other step deemed necessary to increase reliability.
Bibliographic Citations
- Dyrmann M, Skovsen SK, Christiansen PH et al. (2024) High-speed camera system for efficient monitoring of invasive plant species along roadways. F1000Research 2024, 13:360. https://doi.org/10.12688/f1000research.141992.2
- Espitalier V, Lombardo JC, Goëau H, Botella C, Høye T T, Dyrmann M, Bonnet P, Joly A (2025). Adapting a global plant identification model to detect invasive alien plant species in high-resolution road side images. Ecological Informatics 89. https://doi.org/10.1016/j.ecoinf.2025.103129
Additional Metadata
| Alternative Identifiers | 9c85f295-cc92-473c-969a-bb5d3eccfd0b |
|---|---|
| https://ipt.inbo.be/resource?r=ias-pilot-be |