plants have a leading role on the stage of the earth’s ecosystem. But humans ignore often the conservation status of thousands of them. The Red List of the International Union for the Conservation of Nature (IUCN), the leading global institution in this field, it collects only a small part of the plant species that are potentially in danger of extinction. To fill this hole of knowledge, the scientific community asks for relief to the new technologies.
A group of researchers from the US has published this Monday in the journal PNAS a method based on the analysis of large databases capable of detecting the conservation status of up to 150,000 plants. Between them, this artificial intelligence identifies some 15,000 that can be considered endangered according to the IUCN criteria. The experts consulted consider the machine learning as a support tool useful to put together effective strategies for the conservation of biodiversity.
“One of the main problems in finding the threatened species is the availability of resources, human and monetary,” says Anahí Espíndola, a researcher at the University of Maryland and co-author of the study. “The assessments of the IUCN require that each species evaluated to be analysed individually from different points of view, as the size of populations, the genetic diversity or the range of distribution,” he adds.
Espíndola explains that, therefore, the areas of the world with access to limited funds for this type of research or a scientific tradition in this field little ingrained “relegated”. Another bias may depend on what species are considered to be “attractive or not attractive”, says the researcher. “It is easier to communicate the need to evaluate and protect species, as humans we can feel related, such as other mammals or reptiles, amphibians, and birds, either because they seem nice or because we feel reflected in its styles of life,” he says.
Big data to detect the danger of extinction
The artificial intelligence can be a powerful tool to reduce this lack of knowledge, says the study. “Our method is to predict the probability that a species is or is not in danger, using data related to features of their distribution range, climatic conditions preferred and of some morphological features”, explains Espíndola.
Our method is to predict the probability that a species is or is not in danger, using data related to features of their distribution range, climatic conditions preferred and of some morphological features
The researcher explains that she and her companions depart from the information about all the species that have already been evaluated by the IUCN “to train and create a new classification, using the characteristics of the species as predictor variables”. Once you have obtained a model of classification is sufficiently accurate, it is possible to then use that same model “species for which we know the features discussed, 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 of having access to computing resources that are important,” he adds. The system can be adapted to national scales, regional, or local, explained together with his team in the article.
The data used are free-access and are “collections, museums, herbaria, laboratory studies and field work that have Oleybet been doing for a very long time by researchers from all over the world”, also highlights Espíndola. In his view, this “demonstrates the fundamental importance of the collections of natural and the central role of museums in the generation of knowledge”.
The importance of the work of field
Juan Carlos Moreno, Autonomous University of Madrid, considers that the study of Espíndola and their peers “is interesting and brings to its full potential and analysis work tested on a smaller scale”. The teacher ensures that the described models allow a better understanding of the general threat about the plants,” but he adds that these are “simplifications of reality”.
In his opinion, this means that “may be key details to understanding the processes that originate”. In short, studies such as this “they anticipate and complement the necessary field work and consultation of experts in the flowers local to validate the true categories of risk”, according to keeps.
The researcher underlines that the main database used for this study (the Global Biodiversity Information Facility) has a geographical bias huge, with many more records in Europe, north America or Australia than in any other territory.” This, in his opinion, “can compromise the validity of generalizations planetary threat and its relationship with climatic factors and morphological”. Moreno also points out that the IUCN Red List searchable in the web only takes into account species of plants or animals assessed in English and excludes those that have an assessment in another language.
The challenge of preventing the extinction of plants
For Martha, Wheel, researcher of the Biological Station of Doñana, the lack of knowledge of the conservation status of many plant species “is really disturbing”. The researcher gets as an example of how it can affect negatively this lack of information is the fact that many drugs have been obtained from the active principles of plants. “If we die out 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 diseases present and future”, evidence.
The method presented this Monday in the journal PNAS that seems interesting because it allows you to “process information easily and effectively” and “to carry out conservation actions more targeted in terms of economic and human resources”. Espíndola, on the other hand, ensures that your goal is not to replace the protocols of the Red List, but “to provide a tool to assist in the prioritization of species to be evaluated”.
the researcher of The University of Maryland remember that, among the regions most affected by the extinction of plants are those that are experiencing high rates of deforestation, rapid expansion of agriculture or urbanisation. In many of these cases, he adds, “these changes are not accompanied by environmental impact studies, or if they are, the pressure echonómica is so large that it is not taken seriously into account.”
