Number of fish species threatened with extinction five times higher than previously thought, according to new forecast

Researchers estimate that 12.7% of marine bony fish species are threatened with extinction, five times higher than the previous estimate of 2.5% by the International Union for Conservation of Nature (IUN).

Nicolas Loiseau and Nicolas Mouquet of the MARBEC (Marine Biodiversity, Exploitation and Conservation Unit) in Montpellier, France, and colleagues report these findings in a study published August 29 in the open access journal PLOS BiologyTheir report includes nearly 5,000 species that were not given IUCN conservation status due to insufficient data.

The IUCN Red List of Threatened Species covers more than 150,000 species and guides global conservation efforts for the most endangered species. However, 38% of marine fish species (or 4,992 species at the time of this study) are considered data poor and do not receive official conservation status or the protections that come with it.

To better target conservation efforts to the species that need them, Loiseau and his colleagues combined a machine learning model with an artificial neural network to predict the extinction risk of species for which there is no data. The models were trained using data on occurrence, biological traits, taxonomy and human use of 13,195 species.

They classified 78.5% of the 4,992 species as Least Concern or Threatened (including the IUCN categories Critically Endangered, Endangered and Vulnerable). The number of species classified as Threatened increased fivefold (from 334 to 1,671) and the number of species classified as Least Concern increased by a third (from 7,869 to 10,451).

The species classified as endangered tend to have a small range, large bodies and a low growth rate. Extinction risk also correlated with shallow habitats. The South China Sea, Philippine Sea and Celebes Sea, as well as the west coasts of Australia and North America, were found to be hotspots for species classified as endangered. The researchers recommend increased research and conservation efforts in these areas.

The researchers observed “a significant change in the priority list for species conservation following IUCN predictions” and recommended that priority be given to the Pacific islands and the polar and subpolar regions of the Southern Hemisphere to account for emerging species at risk. Many species for which data are not yet available occur in the Coral Triangle, suggesting that more research is needed there.

The researchers point out that models cannot replace a direct assessment of endangered species, but AI offers a unique opportunity to assess the extinction risk of species quickly, comprehensively and cost-effectively.

Loiseau adds: “Artificial intelligence (AI) enables reliable assessment of the extinction risk of species that have not yet been assessed by the International Union for Conservation of Nature (IUCN).”

“Our analysis of 13,195 marine fish species shows that the extinction risk is significantly higher than the IUCN's original estimates, from 2.5% to 12.7%. We propose to incorporate recent advances in predicting species extinction risk into a new synthetic index called 'predicted IUCN status'. This index can serve as a valuable complement to the current 'measured IUCN status'.”