Written by
ZSL
Zoological Society of London
8 December 2022
Network Rail’s extensive UK rail network bisects all major British terrestrial habitat types and supports a rich array of rare, protected, and valued species.
During Spring/Summer 2022, ZSL’s Institute of Zoology and Conservation Programmes embarked on a unique collaboration with Network Rail Southern Region to help them begin to assess and improve their biodiversity performance using cutting-edge, remote monitoring technologies.
The purpose of the pilot phase was to trial a range of remote and automated technologies for monitoring wildlife and anthropogenic activity, including networked and standalone cameras, and innovative acoustic sensors, and to evaluate the viability of the proposed methods for tracking Network Rail’s progress towards their biodiversity mission. We worked across a sample of Network Rail sites in the Greater London Area, including in Barnes, Twickenham, and Lewisham.
Camera trapping
32 camera traps were deployed, with almost 40,000 images captured. Foxes were the most common mammal species with the highest activity at all three sites, Woodpigeon the most common bird, and cameras documented five species of conservation concern. These included Moorhen, Song thrush, Redwing, Stock dove and Wood pigeon, all of which are classed as amber on the UK Red List for birds. Foxes and cats were seen using a hole in a fence along the line near Garthorne Nature Reserve, suggesting that some animals may be using the tracks as movement corridors.
Acoustic monitoring
33 acoustic sensors were deployed across lineside estates, with 560 hours of audio files collected. These were processed with machine learning algorithms, enabling identification of records and automated classification of species – followed by analysis of species richness and activity patterns – and for estimation of levels of biotic and anthropogenic urban noise. ~18 bird species were found in the recordings, with European Robin, Eurasian Wren, and Eurasian Magpie the most common, and there were 754 detections of bat presence, likely species including common pipistrelle, soprano pipistrelle, and possibly some Noctule species.
There were high levels of biotic noise in the recordings, in contrast to other London locations where biotic noise is often low. These results require more research and validation, but suggest that the lineside estate may be an important wildlife refuge, despite high levels of anthropogenic disturbance.
Data analysis
This was a short exploratory study, which will be followed by a full analysis of monitoring data collected in the upcoming phase of the project. This will include AI-enabled computer vision analysis and citizen science methods to classify species in images and understand species trapping rates, richness, distribution, spatial and temporal activity mapping, and relative abundance. The project will also feature on ZSL’s Instant Wild, allowing members of the public to tag images from lineside sites, serving to both engage the public with the project, and aid data processing for future analyses.
Acoustic data will also be analysed using machine learning to classify all species, understand species richness and activity patterns, and more robustly estimate levels of biotic and anthropogenic noise.
Next steps
Network Rail have committed to an ambitious vision, via their 2020 Biodiversity Action Plan, for improving lineside biodiversity, including achieving no net loss in biodiversity by 2024 and biodiversity net gain by 2040, and maximising the value and connectivity of their landholdings as wildlife corridors.
Now that we understand more about Network Rail’s objectives, safety requirements and access to sites, recommendations for a broader research and monitoring programme will be made to support Network Rail’s biodiversity ambitions, in the hopes that we can continue to support the company to track these goals in the future.