Consider a planner laying a new train line through ecologically sensitive areas. They need to balance economic benefits with ecological damage and think through mitigations such as fencing, animal overpasses or habitat compensation areas, each of which have costs. To maximise benefits and reduce costs, such decisions must be informed by prior research knowledge. However, scientific evidence is difficult to find, synthesise and assess. The Conservation Evidence (www.conservationevidence.com) has manually screened over 1.5M papers in 17 languages, so far distilled to 8,636 relevant studies that test 3,690 conservation actions for 24 species groups, habitats and other conservation issues. However, the laborious process of evidence gathering and synthesis means we can only add a few hundred studies per year, whilst the rate of evidence generation is increasing each year. In this talk, I'll explain how we are planning to accelerate the evidence synthesis pipeline and improve decision support using Large Language Models to ensure future conservation action is informed by scientific research. Bio: Alec is a Henslow Research Fellow at Downing College Cambridge and works with the Conservation Evidence group in the Department of Zoology and Cambridge Conservation Initiative (CCI). He did his PhD in Zoology in the same group in 2017 and before that he studied for a BSc in Marine Biology at the University of St Andrews. His work has focused on understanding the gaps and biases in the evidence for biodiversity conservation and improving decision support to enable more evidence-based conservation.
