Scientists use AI to predict plant extinction risk

For the first time, a team of scientists from the Royal Botanic Gardens, Kew have predicted the extinction risk of all 328,565 known species of flowering plants.

AI

The scientists used a Bayesian Additive Regression Trees (BART) model trained on a dataset of more than 53,000 plants already assessed on the International Union for Conservation of Nature (IUCN) Red List, to determine the likely status of the remaining 275,004 unassessed species. An earlier version of this research, from Kew and partners in October 2023, showed that 45% of all flowering plants are threatened with extinction.

By means of new research, anyone can now search for any species on the Plants of the World Online portal to see whether it is probable that the plant is threatened with extinction in the wild, and what level of confidence scientists have in that prediction. Thereby, achieving the ambition of the scientists in making plant conservation more accessible and engaging to a wider audience so that biodiversity can be (urgently) protected.

Plants play a vital role in supporting healthy and resilient ecosystems. Plants can provide natural solutions as our climate changes and underpin our efforts to restore already degraded ecosystems. To achieve the global targets set out through the Convention on Biological Diversity, we need to understand the status of plants.

Dr Steven Bachman, Research Leader in RBG Kew’s Conservation Assessment and Analysis team and author of the study, said: “We hope that these predictions can be used for people to apply to their own local biodiversity to find out if they’ve got a threatened species in their house, garden or local park that needs protecting. At a larger scale, our findings can be used by scientists to prioritise and accelerate extinction assessments for the plants we’ve identified as probably threatened but haven’t been officially assessed by the International Union for Conservation of Nature (IUCN) Red List yet. We hope that a commitment can be made to assess these species or we can encourage other people to carry out these assessments.”

To model extinction risk for all the species, scientists used data from the World Checklist of Vascular Plants, the IUCN Red List and datasets on the impacts of human activities which are all regularly updated. However, the predictions for each species are a moving target as some species’ status can improve while others sadly can massively deteriorate. Therefore, it is crucial that the scientists regularly update this baseline assessment with new versions to ensure they are providing accurate and useful predictions.

Dr Eimear Nic Lughadha, Senior Research Leader in Conservation Assessment and Analysis at RBG Kew and author of the study, says: “Being assessed, particularly as Endangered or Critically Endangered, literally changes the fate of a plant, as once its extinction risk is known, it can be prioritised for conservation. In the absence of IUCN Red List assessments for all plant species, our predictions will provide a really useful indication as to which species we consider most likely to be threatened with extinction and, for the first time, our level of confidence in each species’ prediction.”