Biodiversity ‘time machine’ uses AI to learn from the past

Date

Experts can make crucial decisions about future biodiversity management by using artificial intelligence to learn from past environmental change, according to a new study.

The research team, including academics from Leeds, has proposed a “time machine framework” that will help decision-makers effectively go back in time to observe the links between biodiversity, pollution events and environmental changes such as climate change as they occurred, and examine the impacts they had on ecosystems. 

In a new paper, published in Trends in Ecology and Evolution, the team sets out how these insights can be used to forecast the future of ecosystem services such as climate change mitigation, food provisioning and clean water.

Using this information, stakeholders can prioritise actions which will provide the greatest impact.

Dr Martin Dallimer, from Leeds’ Sustainability Research Institute, is a  co-author on the paper. He said: “We’ve made many poor decisions as to how to manage the natural world in the past, and sometimes we could have done better with more knowledge and a better understanding.

“As we increasingly realise the complexity of the inter-relationships between biodiversity and society, and how biodiversity and ecosystem services underpins our own wellbeing, making use of artificial intelligence to learn from the past as outlined in our time machine approach will be a crucial tool.”

Fellow co-author Professor Jouni Paavola, from Leeds’ School of Earth and Environment, added: “If we are to make better decisions on how we manage biodiversity in the future, we need to understand the whole system, rather than just individual elements, and make sure our decisions are backed up by the appropriate evidence.”

Causes of biodiversity

Biodiversity loss happens over many years and is often caused by the cumulative effect of multiple environmental threats. Only by quantifying biodiversity before, during and after pollution events, can the causes of biodiversity and ecosystem service loss be identified, say the researchers.

Managing biodiversity while ensuring the delivery of ecosystem services is a complex problem because of limited resources, competing objectives and the need for economic profitability. Protecting every species is impossible. The time machine framework offers a way to prioritize conservation approaches and mitigation interventions. 

Principal investigator Dr Luisa Orsini is an Associate Professor at the University of Birmingham and an Alan Turing Fellow. She said: “Biodiversity sustains many ecosystem services. Yet these are declining at an alarming rate. As we discuss vital issues like these at the COP26 Summit in Glasgow, we might be more aware than ever that future generations may not be able to enjoy nature’s services if we fail to protect biodiversity.”

Lead author, Niamh Eastwood, a PhD researcher at Birmingham, said: “We are working with stakeholders such as the UK Environment Agency to make this framework accessible to regulators and policy makers. This will support decision-making in regulation and conservation practices.”

The framework draws on the expertise of biologists, ecologists, environmental scientists, computer scientists and economists. It is the result of a cross-disciplinary collaboration among the University of Birmingham, The Alan Turing Institute, University of Leeds, University of Cardiff, University of California Berkeley, The American University of Paris and the Goethe University Frankfurt.

Further information

The Time Machine framework: monitoring and prediction of biodiversity loss’ is published in Trends in Ecology and Evolution 9 November 2021.

For more information, contact Ian Rosser in Media Relations at the University of Leeds by email on i.rosser@leeds.ac.uk.

Image: A red, polluted lake in Geamana, Romania. Credit: Adobe Stock.