Development model for automatic bat validation

Client: National Database of Flora and Fauna

Year: 2024

The NDFF wanted to be able to automatically validate bat sounds using automatic recognition. This is to ultimately make validation and observation easier and thus increase the quality and quantity of bat data. Aquila Ecology is currently developing such a model for the NDFF.

CrickIt: developing locust recognition model + android application

Client: Province of Limburg

Year: 2023

During this project, Aquila Ecology developed a grasshopper and cricket sound recognition model. In addition, an Android app has also been developed that accurately distinguishes the vocalizing species of locusts and crickets, in order to double the number of observations of these species received by GBIF. The app can be downloaded for free for private individuals from the PlayStore: CrickIt

Pilot to inventory roadside vegetation on highways with AI

Client: Rijkswaterstaat

Year: 2023

Rijkswaterstaat has asked Aquila Ecology to develop a method using AI to inventory the shoulders of national highways. This includes analyzing vegetation to assess nature quality and provide information on biodiversity hotspots, presence of protected species and invasive exotic species. The pilot focused on assessing the reliability, practical feasibility and integration of this method into existing data flows of Rijkswaterstaat. In addition, Aquila Ecology investigated how this technique compares to traditional methods, the costs of scaling up, and possible combinations with other research techniques. The technique appears to be suitable for detecting invasive exotic species and recognizing flowering and medium to large species. We will continue to expand and develop this technology.

KleurKeur effect evaluation with AI

Client: Butterfly Foundation

Year: 2023

Kleurkeur was set up as a quality mark for ecological roadside management, providing site owners with clear guidelines for insect-friendly management. It is important that the verges are evaluated to see whether management has the desired effect. To save costs and time, we use machine learning to determine vegetation composition from photos, resulting in a large data set at a fraction of the cost. Aquila Ecologie has developed this software in-house. This way we obtain an extensive vegetation dataset with minimal additional costs. In addition to the analysis of the model, we made additional vegetation recordings for validation.

AI solutions for data collection

Image Recognition for Biodiversity

Client: Netherlands Enterprise Agency (RVO)

Year: 2022

In this project we investigated the possibility of vegetation monitoring with autonomous drones, where a drone operator can steer the drone over a field at the touch of a button. The photos taken by the drone are analyzed by software that identifies plant species and, in the long term, also determines plant communities. Plant communities serve as the national standard for vegetation monitoring. The aim is to efficiently collect information about vegetation in specific locations, which is important for various applications such as agriculture and nature conservation.

More information about our services?

Feel free to contact us!