Cactus: prediction of the conservation status of species

CACTUS is an acronym inspired by “A predictive approach to determining the conservation status of species” but it is also a family of succulents very resilient to droughts and extreme temperatures.

Determining the conservation status of species (“vulnerable”, “threatened”, “extirpated”, etc.) is a complex process that requires both reliable data and a careful and well-informed review of criteria defined by the scientific community. (especially those of the IUCN). As this process takes a long time, the list of species analyzed has significant gaps and is not updated quickly enough in view of the speed of current environmental changes. 

Our hypothesis is that it might be possible to predict the conservation status of species much more efficiently by automatically analyzing the masses of data available through artificial intelligence approaches. Recent cyber infrastructures and new data sources indeed offer possibilities to mobilize and integrate massive amounts of biological data that have never been jointly analyzed. We will be particularly interested in the use of participatory science data (such as those from the Pl@ntNet platform) which have the advantage of offering a high observation frequency. 

The automation of the prediction of the status of species has never been considered before at such scales. For the moment, we have no guarantee that the data that we will mobilize contains all the necessary information and even less that the methods that we will implement will allow them to be extracted efficiently. In particular, several issues known to be difficult problems will need to be addressed, in particular the lack of absence data. It is indeed quite easy to find data on the presence of species, but it is very difficult to conclude that a species is absent at a given location simply because there is no known presence data. Deciding definitively on the disappearance of a species is in particular very complicated, especially if the latter was already rare before.

This exploratory action is led by Alexis Joly (Inria research director) with the participation of Joaquim Estopinan (Inria doctoral student), Pierre Bonnet (botanist at CIRAD), François Munoz (ecologist / modeler at LECA), Maximilien Servajean (researcher in machine learning at LIRMM) and Joseph Salmon (professor of statistical learning at the University of Montpellier).

Beyond this first circle of collaborators, we intend to discuss with researchers from IUCN, the main world organization in charge of determining the conservation status of species, well known for its famous red list of threatened species. We would be very happy if our work could ultimately facilitate their work and thus contribute to better management of global biodiversity.