With artificial intelligence you can predict which plants will die out



[ad_1]

The The International Union for Conservation of Nature (IUCN, for its acronym in English) Continuously works in the design of the denominated Red list, which analyzes species and classifies them into categories that range from "minor significance" to "extinct", which takes place through intermediate categories.

These classifications are used to define conservation measures and are therefore "extremely useful", but "to include the species they need to be evaluated individually, which requires a pre-defined protocol, available resources and the presence of experts who make an assessment, which makes it a slow process , "he said. Telam Anahí Espíndola, an Argentine co-author of the study.

"The basic method we used was" random forest ", which is known for its ability to classify and predict data," he said and explained that "in this case we are trying to predict the likelihood that the species is at risk or not, the data , associated with the characteristics of its distribution range, its preferred climatic conditions and some morphological characteristics ".

Espíndola, a professor of entomology at the University of Maryland in the United States, explained that "this method makes it possible to use all types that IUCN already estimates for training and creating a classification of" random forests ", using the characteristics of the species as a predictive variable. "

"Once we have obtained a sufficiently precise classification model, this same model can be used for species for which we know the characteristics used in the model (distribution range, priority climatic conditions and morphology), but for which we do not know the degree of risk of extinction."

In this sense, the co-author of the article is published in an expert journal PNAS He stated that the use and classification of this data would enable "calculate the likelihood that those species that have not yet been evaluated with the IUCN Red List are in danger."

"Extremely useful" of this system is that it is "relatively precise and also can be analyzed without having access to important computer resources", it also has an "advantage" based exclusively on "public data" (open access), they say, that everyone can carry out these analyzes and use their results.

"In addition, this method can be adapted to any geographical or taxonomic scale of interests, as it can also be used at national, regional or local level, and allows identification of the species that the IUCN must prioritize," he said. Espíndola and described this tool as "useful and complements these estimates".

The specialist said that of the 150,000 species analyzed, "approximately 10% (15,000) are likely to belong to conservation categories that are not" lesser concern "."

"From a global perspective, we have identified regions that have the likelihood of endangering species, such as some of the Andean regions in North America or the Brazilian Atlantic forest." These regions are characterized by a high level of endemism and the presence of many rare species, "he concluded.

[ad_2]

Source link