An innovative project will harness new technology and citizen science to deliver standardised monitoring of wildlife.
There are major gaps in our understanding of biodiversity across the globe, such as where species are present, how their populations are changing and what is causing declines and local extinctions.
This is especially true for insects which are essential for ecosystem function. Researchers from the UK Centre for Ecology & Hydrology (UKCEH) and The Alan Turing Institute, funded by the abrdn Charitable Foundation (aCF), will develop the use of automated sensors, bioacoustics and artificial intelligence (AI) to monitor insects, bats and birds.
They will support volunteers in four areas – in Costa Rica, Singapore, Japan and Uganda – in setting up automated biodiversity monitoring stations comprising high-resolution cameras to photograph insects and acoustic equipment to record the calls of birds and bats. The two-year project will help scientists develop the monitoring equipment as well as the AI software by training computer systems to recognise species from images and recordings.
Dr Tom August, a computational ecologist at UKCEH, explained that with traditional surveys, moth traps, locations or observers may be different from one year to the next, introducing error and bias. Using microphones and cameras to record animals can ensure greater consistency, and lead to accurate estimates of how populations are changing.
“By using a hardware like the automated monitoring stations you can ensure that your sampling is the same every night, every year at every site. Furthermore, the data produced is verifiable and robust across sites and years because you can always return to the images and sounds to check what was recorded, which is not always the case with other methods,” said Dr August.
“Our project will provide a template for automated monitoring and identification globally, providing robust data at scale and low cost.”
As part of the project, UKCEH and the Turing Institute are developing edge processing which will enable images to be analysed on the device, rather than being downloaded and processed later. In the future, non-expert volunteers could use automated monitoring systems to produce lots of data about biodiversity on many sites, in order to guide local habitat management as well as provide important benchmarks for desired species population trends. This would generate new, robust data to inform local, national and international biodiversity assessments.
Professor Mark Girolami, Chief Scientist at The Alan Turing Institute, which carries out research into data science and artificial intelligence, said: “Plummeting populations of insects around the world are causing widespread concern. It has never been more important to understand why and how these declines are happening – more research in this area is urgently needed.’’
Gemma Jones, Global Head of Corporate Sustainability at abrdn, an international investment company, added: “The interlinked biodiversity and climate crises continue to pose unprecedented challenges for society and require understanding, collaboration and collective change at pace.”