Conservation work to detect and protect curlew and other ground-nesting birds in Wales have been given a helping hand by new AI monitoring technology used by researchers from the Game & Wildlife Conservation trust and Liverpool John Moores University.
In order to better recognise curlew and their chicks, they trained a new real-time object detection model called YOLOv10 to spot and recognise not only curlew, but also 25 other species, including foxes, deer and rabbits, by combining a pre-existing conservation AI database with nearly 39,000 images from across the UK.
The results of the study, which saw researchers test the system’s ability to monitor curlew and their chicks on 11 sites across Wales during the 2024 nesting season, were presented in a new scientific paper published this spring.
Using the 3G and 4G networks, 1,072 images were sent from AI-enabled cameras through to the technology system, which then processed the curlew footage in real-time, making it accessible through an app on a mobile phone.
They proved that the model was able to filter out blank images triggered by moving vegetation and could also reliably identify curlew chicks, despite their natural camouflage. It correctly identified curlew over 90% of the time and never falsely detected them when they were not there.
To help the AI model handle real-world challenges, the team taught it to recognise animals under different conditions, such as changes in lighting, angles and sizes. This was done through data augmentation, a technique that adjusts images by changing colours, brightness and flipping them to create variety.
In the past, conservation efforts for vulnerable ground-nesting birds like curlews have often been labour intensive and logistically challenging, as the work to process the vast number of images from camera traps is time-consuming, delaying conservation action.
Making use of this new AI assisted technology will significantly reduce conservationists’ workload, allowing them to respond more effectively to protect the sites where breeding curlew have been detected.
‘Game changer for ecological research’
Katie Appleby, Curlew and People Officer for GWCT Wales and co-author, said: “Curlew is one of the fastest declining bird species in Wales, and as a breeding population it is predicted it will be extinct by 2033 if this trend continues.
“Ground-nesting birds are an essential component of open grassland and wetland ecosystems. Sadly, many of them are under threat as the open habitats they rely on are being encroached by agricultural intensification, urban development and other changes in land use.
“Nesting on the ground also makes them very vulnerable to predation by foxes, badgers and corvids which all eat their eggs and chicks. This means species such as lapwing, skylarks and curlews are struggling to maintain stable populations across Wales.
“The new AI model performed really well in detecting curlews and after working with the system to enhance the detections it became extremely reliable in understanding the curlew behaviour and movements around the nest sites.
“Where historically with traditional trail cameras each image would need to be sifted through manually, we are now able to see in real time what is happening and spot the chicks when they hatch, which is very exciting. This allows me to focus time more effectively across the site and better support the birds.”
James Warrington, Project Officer GWCT Wales, said: “This new AI tool has allowed the team to integrate the technology in other areas of our work in Wales. It has created opportunities for communities, and public engagement through ‘citizen scientists’, to set up cameras in local environments such as gardens, land and workplaces.
“Not only does this increase the data that can be collected, which supports the AI tool, but it also encourages interest and engagement in conservation and raises awareness about the importance of protecting wildlife.”
Lee Oliver, Director for GWCT Cymru, said: “My team are working very hard on the ground during the breeding season to find nests to protect eggs and chicks from predation, alongside working with farmers for delayed cutting and grazing management.
“The use of AI technology is advancing rapidly, and in the field of ecological research is a game changer.
“Time which my team would have spent in the field, manually retrieving and processing images from camera traps, can now instead be spent implementing practical measures to protect curlew.”
Notes to editors
- A conservation AI database comprises a data collection portal for rapid ingestion of remote data from drones and camera traps, which can also be combined with a collection of analytical tools to transform and interpret that data.
- Read a Plain English Summary of the scientific paper
The Game & Wildlife Conservation Trust – providing research-led conservation for a thriving countryside. The GWCT is an independent wildlife conservation charity which has carried out scientific research into Britain’s game and wildlife since the 1930s. We advise farmers and landowners on improving wildlife habitats. We employ more than 60 post-doctoral scientists and other research staff with expertise in areas such as birds, insects, mammals, farming, fish and statistics. We undertake our own research as well as projects funded by contract and grant-aid from Government and private bodies.
For more information, images or to arrange an interview please contact:
Eleanor Williams
ewilliams@gwct.org.uk
07592 025476