More than half of the species whose endangerment status cannot be assessed due to a lack of data are threatened with extinction, according to a machine learning analysis published on Thursday.
The International Union for Conservation of Nature (IUCN) currently has nearly 150,000 entries on its Red List of Threatened Species, including about 41,000 species that are critically endangered.
This includes 41 percent of amphibians, 38 percent of sharks and rays, 33 percent of reef-building corals, 27 percent of mammals, and 13 percent of birds.
But there are thousands of species that the IUCN has been unable to categorize because they have “insufficient data” and are not on the Red List, despite living in the same regions and facing similar threats as the species previously assessed.
Researchers at the Norwegian University of Science and Technology used a machine learning technique to predict the likelihood of 7,699 species facing extinction with insufficient data.
They trained the algorithm on a list of more than 26,000 species that the IUCN was able to categorize, and integrated data about the regions where species live and other factors known to affect biodiversity to determine if they predicted their extinction risk status.
“These could include climatic conditions, land use conditions or land use change, pesticide use, threats from invasive species, or really a number of different stressors,” lead author Jan Borgelt, from the university’s Industrial Ecology Program, told AFP.
After comparing the results of the algorithm with the IUCN lists, the team used them to predict the risk of extinction for the species with insufficient data.
They wrote in the journal Communications Biology that 4,336 species — or 56 percent of those sampled — were likely threatened with extinction, including 85 percent of amphibians and 61 percent of mammals.
This compares to the 28 percent of species assessed by the IUCN Red List.
“We see that in most terrestrial and coastal areas of the world, the average risk of extinction would be higher if we included data-deficient species,” Borgelt said.
A 2019 United Nations global biodiversity assessment warned that up to a million species are at risk of extinction due to a range of factors including habitat loss, invasive species and climate change.
Borgelt said the analysis revealed some risk hotspots for species with insufficient data, including Madagascar and southern India. He said he hopes the study can help IUCN develop its strategy on unreported species, adding that the team has reached out to the union.
“With these machine learning predictions, we can really get pre-assessments or use these as predictions to prioritize which species need to be studied by the IUCN,” he said.
IUCN Red List director Craig Hilton-Taylor said the organization is constantly using new technology to reduce the number of species with insufficient data.
“We also understand that a subset of species with insufficient data are threatened with extinction and factor this into our calculations when estimating the proportion of threatened species in a group,” he told AFP.
#species #included #endangered #species #list #threatened #extinction #study
