The risk of extinction could be much worse than current estimates
To effectively protect a species, conservationists need key information: where it lives and what threats it faces. Yet scientists lack this baseline data for thousands of species around the world, making it impossible to know how they are doing, let alone take steps to ensure their survival.
For these “data-deficient” species, a new study published in Communications Biology August 4 suggests no news is likely not good news. The authors used machine learning methods to predict conservation status of 7,699 data-deficient species – from fish to mammals – and found that 56% are likely threatened with extinction. The results are particularly concerning, given that only 28% of species with known conservation status are considered to be at risk of extinction, says lead author Jan Borgelt, a doctoral student in industrial ecology at the Norwegian University of Science and Technology. . “Things could be a lot worse than we actually think,” he adds.
Borgelt and his colleagues based their analysis on the International Union for Conservation of Nature (IUCN) Red List of Threatened Species, a global database that categorizes the risk of extinction posed to more than 147,500 species. However, depending on the species group, around 10-20% of animals, plants and fungi on the Red List are listed as data deficient, meaning there is not enough information to determine their state of preservation one way or the other. This poses challenges for scientists seeking to understand the threats to biodiversity, as well as for policy makers trying to design effective local, regional and international conservation strategies.
Borgelt and his team built a machine learning model based on existing data from 28,363 Red List species whose conservation status had already been assessed. They included information from the IUCN and other reliable sources on the distribution, habitat and threats of these species, then used this data to train their model to come up with a generalized technique for predicting the risk of extinction of a particular species. Next, the researchers applied the model to predict the conservation status of 7,699 Data Deficient Red List species. The only prerequisite was that the geographic range of these species be known.
The model predicted that more than half of the data-deficient species included in the analysis are threatened with extinction. Some groups of animals seem to be in a more difficult situation than others. According to the results, 85% of amphibians, 62% of insects, 61% of mammals and 59% of reptiles with insufficient data are likely at risk of extinction. The results also indicated that data-deficient species in Central Africa, South Asia and Madagascar face particularly high levels of threat.
Although there is uncertainty surrounding the results, Borgelt and his colleagues received an indication that their predictions are quite accurate. After carrying out the analysis, but before publishing its study, the IUCN published an updated red list with conservation lists for 123 species for which data were previously deficient. Three-quarters of these actual statuses matched the predictions made by the researchers’ model.
The new find in Communications Biology that species lacking data may be more threatened than species with known conservation status isn’t necessarily surprising, but it does reinforce the need for comprehensive extinction risk assessments, says Louise Mair, a biologist at the conservation at the University of Newcastle in England, which was not involved in the research. “Up-to-date Red List assessments are essential to inform action and measure progress,” she says.
The biggest obstacle to carrying out such assessments is not the lack of technical expertise to assess species, adds Mair, but the lack of resources. “Conservation faces a huge funding gap globally,” she says.
To spend the limited funds as wisely as possible, Borgelt suggests that predictive models could be used to identify and prioritize species that seem to face the greatest threats. “These new machine learning technologies would not replace experts, but would help guide and allocate resources,” he says. “Some groups of species are really much more urgent than others.”