Making the most of machine learning to conserve botanical biodiversity

Go back to programme

Making the most of machine learning to conserve botanical biodiversity

  • Watch

    * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

  • Approximately 350,000 species of plants are known to science, and around 2 in 5 are thought to be threatened. However, comprehensive assessment and monitoring of the extinction risk of all plant species is an impossible task; currently, just 1 in 6 have global conservation assessments on the International Union for Conservation of Nature (IUCN) Red List. 

     

    While accurately and reliably automating individual species’ assessments remains an outstanding challenge, we can leverage machine learning techniques to predict which species are likely to be threatened, using their known characteristics (e.g. lifeform, geographic distribution and evolutionary history). By combining a Bayesian statistical approach with the machine learning classifier, we can also obtain robust uncertainty estimates for our species-level extinction risk estimates, making these predictions invaluable for conservation prioritisation and use in future research. 

     

    We can also use unsupervised learning to tease out hidden patterns in global biodiversity: in another recent work, we identified human-induced changes in global floristic bioregions (‘phytoregions’) by using a community network algorithm, Infomap, to analyse supergraphs representing the geographic distributions of all plant species. 

     

    In this AI for Good session, we will describe the challenges and opportunities for using machine learning in plant-focused conservation science and present the results of recent work by the Conservation Assessment and Analysis team at the Royal Botanic Gardens, Kew (United Kingdom).  

     

    This live event includes a 30-minute networking event hosted on the AI for Good Neural Network. This is your opportunity to ask questions, interact with the panelists and participants and build connections with the AI for Good community.

    Share this session
    In partnership with