For best experience please turn on javascript and use a modern browser!
You are using a browser that is no longer supported by Microsoft. Please upgrade your browser. The site may not present itself correctly if you continue browsing.
A photograph of palm trees from one of W. Daniel Kissling's field studies. Copyright: UvA / W. D. Kissling

The international team of researchers from the Royal Botanic Gardens, Kew, the University of Zurich, and the University of Amsterdam combined existing data from the International Union for Conservation of Nature (IUCN) Red List with machine learning techniques to paint a clearer picture of how palms may be threatened. Although palms are taxonomically well-studied and therefore well represented on the Red List, extinction risk assessments and information on their threats are actually lacking for 70% of the >2,500 palm species.

The IUCN Red List of Threatened Species is widely considered to be a gold standard for evaluating the conservation status of animal, plant, and fungal species. The Red List is not just for threatened species; it documents whether species are threatened, not threatened or when there is not enough information to determine status. But there are gaps in the Red List that need to be addressed, as not all species have been listed and many of the assessments are in need of an update. Conservation efforts are further complicated by inadequate funding, the sheer amount of time needed to manually assess a species, and public perception favouring certain vertebrate species over plants and fungi.

Using AI to fill the gaps

Scientists are, however, confident that AI can greatly speed up research and applications in ecology and conservation. For instance, researchers at RBG Kew and partners are developing novel techniques to estimate the extinction risk for thousands of plant species, aiding efforts to expand and update the IUCN Red List more rapidly than could be done with conventional methods. Similarly, researchers in the Netherlands and elsewhere are developing AI models and research infrastructures to automatically identify species from images and sound which can automate and expand the extent and resolution of biodiversity monitoring.

‘AI provides ample opportunities for biodiversity science, ranging from species identification to conservation assessments’, says UvA scientist W. Daniel Kissling. ‘We need to use all the tools to improve data collection and automation for generating more comprehensive assessments. The biodiversity crisis dictates that we take urgent action to stem biodiversity loss, and we need reliable data and information to take such action’.

Palm species data

In this latest study, the international team employed machine learning to estimate the extinction risk of hundreds of palm species. Using AI and existing Red List data, they were able to study how extinction risks relate to palm distribution, human impacts, forest loss and climate, predicting the extinction risk for 1,381 previously unassessed species. Together with available Red List assessments, they could estimate the extinction risk of 1,889 species or 75% of the palm family. More than half (56%) of these species may be threatened, and if extrapolated for the whole family, more than 1,000 species may be threatened with extinction.

‘This is quite worrying’, says Kissling. ‘Palms are a keystone resource for many animals, including mammals and birds eating their fruits. Palms are also one of the most useful and economically important plant families in the tropics because they are used by rural populations for house construction, food, medicine, cosmetics and rituals. The extinction of these plants will have many cascading consequences, not only for nature but also for people relying on palm products’. According to the study, at least 185 palm species that have a use for local communities may be threatened in 92 regions across the world, further stressing the need to protect these plants.

Next steps

To better understand these risks, their impact on palm diversity and the wider environment, as well as their impact on human populations, the study’s authors believe more work still needs to be done. ‘At our Institute for Biodiversity and Ecosystem Dynamics (IBED), we will continue to study palms in many ways, including their interactions with fruit-eating animals, their evolution, their role in reconstructing past vegetation and climate, their services to humans, and the potential cascading consequences of future palm extinctions on biodiversity’, says Kissling. The findings of this study have laid out a foundation for future research, not only to extend the study of palms, but also for using AI more widely in biodiversity science and ecological research.

Details of the publication

S. Bellot et al, The likely extinction of hundreds of palm species threatens their contributions to people and ecosystems, in: Nature Ecology and Evolution, 26 September 2022, DOI: 10.1038/s41559-022-01858-0

Dr. rer. nat. W.D. (Daniel) Kissling

Faculty of Science

Institute for Biodiversity and Ecosystem Dynamics