In response to increasing calls for action to halt biodiversity loss, an international team from Switzerland, Sweden and the UK has developed the CAPTAIN (Conservation Area Prioritization Through Artificial INtelligence) software package, which incorporates data relating to biodiversity, a conservation budget, human influence and climate change.
The software's AI-optimized models therefore provide better solutions than alternative software. In fact, for a given budget, CAPTAIN can protect more species than other approaches, which, for example, would limit themselves to to protecting the richest areas.
"To optimize our AI models, we simulate an artificial world, which comprises many species exposed to human impacts, such as direct exploitation or land use changes, and climate change," explains computational biologist Daniele Silvestro, Professor at the University of Fribourg and project leader at the SIB Swiss Institute of Bioinformatics. "We then let the algorithm play the role of policy maker like in a video game, where the reward is the number of species spared from extinction at the end of the game. The program plays the game several times, after which it learns how to best place the protected areas in this simulated world. After this training phase, the algorithm is ready to be applied to real-world data."
In their modeling work, the authors found that biodiversity is best protected when detailed knowledge about the spatial distribution of species is available and their populations are regularly monitored - not only by experts, new technologies, such as the use of soil DNA and drone imagery, but also through collaborative scientific initiatives.
