Plants play a leading role in the scenario of the terrestrial ecosystem. But human beings often ignore the state of conservation of thousands of them. The Red List of the International Union for the Conservation of Nature (IUCN), the main global institution in this field, collects only a minimal part of the plant species that are potentially endangered. To fill this hole of knowledge, the scientific community asks for help to new technologies.
A group of researchers from the United States has published this Monday in the magazine PNAS a method based on the analysis of large databases able to detect the conservation status of up to 150,000 plants. Among them, this artificial intelligence identifies some 15,000 that can be considered threatened according to the IUCN criteria. The experts consulted consider the machine learning as a useful support tool to build effective strategies for biodiversity conservation.
"One of the main problems in finding endangered species is the availability of human and monetary resources," says Anahí Espíndola, a researcher at the University of Maryland and co-author of the study. "The IUCN assessments require that each evaluated species be analyzed individually from different points of view, such as the size of populations, genetic diversity or range of distribution," he adds.
Espíndola explains that, for that reason, the areas of the world with scarce access to funds destined to this type of research or with a scientific tradition in this little rooted field "are relegated". Another bias may depend on which species are considered "attractive or unattractive," says the researcher. "It is easier to communicate the need to evaluate and then protect species with which as humans we can feel related, like other mammals or reptiles, amphibians and birds, either because they seem beautiful or because we feel reflected in their lifestyles" , he says.
Big data to detect the danger of extinction
Artificial intelligence can be a powerful tool to reduce this ignorance, the study says. "Our method tries to predict the probability that a species is or is not endangered by using data related to characteristics of its range of distribution, its preferred climatic conditions and some morphological characteristics," Espíndola explains.
Our method tries to predict the probability that a species is or is not endangered using data related to characteristics of its distribution range, its preferred climatic conditions and some morphological characteristics
The researcher explains that she and her colleagues start from the information on all the species that have already been evaluated by IUCN "to train and create a new classification, using the characteristics of the species as predictor variables". Once a sufficiently precise classification model has been obtained, it is then possible to use that same model "about species for which we know the characteristics analyzed, but not the level of risk of extinction".
One of the main advantages of this method is that it is "relatively accurate", says this scientist. It can also be applied "without the need to have access to important computer resources", he adds. The system can be adapted to national, regional or local scales, explains with his team in the article.
The data used are freely accessible and come "from collections, museums, herbaria, laboratory studies and field work that have been carried out for a long time by researchers around the world," Espíndola also highlights. In his opinion, this "demonstrates the fundamental importance of natural collections and the central role of museums in the generation of knowledge".
The importance of field work
Juan Carlos Moreno, from the Autonomous University of Madrid, believes that the study of Espíndola and his colleagues "is interesting and leads to its maximum potential analysis and trials on a smaller scale." The teacher assures that the described models "allow to understand better the generalities of threat on the plants", but qualifies that they are "simplifications of the reality".
In his opinion, that supposes that "key details can be left to understand the processes that originate them". In short, studies such as this "anticipate and complement the necessary field work and the consultation of experts in local floras to validate the true risk categories," he maintains.
The researcher emphasizes that the main database used for this study (that of the Global Biodiversity Information Facility) "Has a huge geographical bias, with many more records in Europe, North America or Australia than in any other territory." This, in his opinion, "can compromise the validity of planetary generalizations of the threat and its relationship with climatic and morphological factors". Moreno also recalls that the IUCN Red List that can be consulted on the web only takes into account species of plants or animals evaluated in English and excludes those that have an evaluation in another language.
The challenge of preventing the extinction of plants
For Marta Rueda, researcher at the Doñana Biological Station, the lack of awareness of the state of conservation of many plant species "is really worrying". The researcher gives as an example of how this lack of information can negatively affect the fact that many medicines have been obtained from active plant ingredients. "If they are extinguished because we do not know that they are in danger and we do not take measures to protect them, we can lose our reservoir to alleviate present and future diseases", evidence.
The method presented on Monday in PNAS it seems interesting because it allows "processing information in a simple and effective way" and "carry out more targeted conservation actions in terms of economic and human resources". Espíndola, on the other hand, assures that its objective is not to replace the Red List protocols, but "to provide a tool to assist the prioritization of species to be evaluated".
The researcher from the University of Maryland recalls that among the regions most affected by the extinction of plants are those that are experiencing "high rates of deforestation, accelerated expansion of agriculture or urbanization." In many of these cases, he adds, "those changes are not accompanied by environmental impact studies, or if they are, the economic pressure is so great that they are not taken seriously."