EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating AI-Based Species Recognition and Drone Monitoring for Scalable Invasive Aquatic Plant Management

Leon Sterk

ARPHA Conference Abstracts · 17.08.2026 · 9

DOI: 10.3897/aca.9.e202200 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ARPHA Conference Abstracts, online erschienen am 17.08.2026. Verfasst von Leon Sterk. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Platform Datagestuurd Waterplantenbeheer (PDW) is a Dutch initiative aimed at standardising and modernising the management of invasive aquatic plants. Key components of PDW include an AI-driven identification training tool and the deployment of drones with sensor technology for inventories. By making use of automatomated aquatic plant detection monitoring time reduces and objectivity of observations improve. Moreover, its large-scale monitoring contributes to the EU Regulation (EU Regulation 1143/2014) on Invasive Alien Species) and the Water Framework Directive (2000/60/EC). By embedding standardised data and methodologies, PDW contributes to uniform application of management strategies across regions by connecting different ecological assessments and develop them into concrete operational actions. To detect (invasive) aquatic plants, we deploy high RGB resolution cameras on drones. The drone imagery is transferred in the cloud Platform PDW, where the model automatically processes the data by an Ai-driven identification tool developed in close collaboration with ecologists. The outputs are integrated into a GIS model that delineates plant population boundaries and produces spatially and explicit species maps, giving water managers immediate and reliable tools supporting their decision-making- and operational processes. The strong partnership between ecologists, data scientists, and technology providers ensures ecological validity, sufficient processing capacity, and data storage. Practical applicability is ensured by our collaboration with waterboards and authorities, contractors, and manufacturers. Drone based monitoring directly supports compliance to EU Member States’ obligations for early detection and enhances controlled rapid eradication of invasive aquatic plants. This, combined with the AI-driven species recognition tool, ensures that PDW provides water authorities and contractors with a practical combined tool for planning, risk assessment, and operational management thereby harmonising monitoring protocols. The shared data standards will stimulate cross‑authority collaboration, allowing water managers to collectively upscale (invasive) species monitoring and management. The system uses HPC on various sovereign systems. PDW also provides the possibility to detect other species so that operational management is supported with additional accurate (local) information. The platforms’ technology and methodology are designed to be domain overarching strategy. Looking ahead, PDW provides a solid base for the transition to semi‑autonomous and autonomous systems by contributing to European Digital Information Hub (EDIH NN). The combination of remote‑controlled task allocation within the platform, precise GPS‑based positioning, and autonomous workboats offers a solution to address increasing labour shortages in water management. A persistent challenge we work on is limited water transparency (turbidity). This work forms part of the EngD project “Towards High-Precision Detection of Aquatic Vegetation Using Multi-Sensor Imaging Systems” in collaboration with the University of Groningen (RUG), aiming to increase model robustness under diverse field conditions and water qualities.

Zitieren

APA

Sterk, L. (2026). Integrating AI-Based Species Recognition and Drone Monitoring for Scalable Invasive Aquatic Plant Management. ARPHA Conference Abstracts, 9. https://doi.org/10.3897/aca.9.e202200

Vancouver

Sterk L. Integrating AI-Based Species Recognition and Drone Monitoring for Scalable Invasive Aquatic Plant Management. ARPHA Conference Abstracts. 2026;9. doi:10.3897/aca.9.e202200

BibTeX
@article{Sterk2026,
  author = {Sterk, Leon},
  title = {Integrating AI-Based Species Recognition and Drone Monitoring for Scalable Invasive Aquatic Plant Management},
  journal = {ARPHA Conference Abstracts},
  year = {2026},
  volume = {9},
  doi = {10.3897/aca.9.e202200}
}
Kostenlos starten →