Science – Würzburg – Artificial intelligence proposes the development of biodiversity – Bavaria

Würzburg (dpa) – According to a study, automated analysis of animal sounds can be used to draw good conclusions about the evolution of biodiversity in the region. The artificial intelligence (AI)-assisted assessment has been tested in tropical reforestation areas, a team led by forest scientist Jörg Müller from the University of Würzburg reported in the specialist journal Nature Communications. The sounds of birds, amphibians and mammals were taken into account.

Studies have previously shown that the presence of animal species can be tracked through soundscapes during forest destruction or restoration. The research team has now installed recording devices in northern Ecuador, South America, on pastures and cocoa plantations that are no longer managed and where forests are gradually being established again. Recordings of various animal sounds were then analyzed using artificial intelligence models.

“The research results show that sound data perfectly reflects the return of biodiversity in abandoned agricultural areas,” Müller said. “The voice of species communities is above all what represents recolonization so well.” These communities have a very distinctive composition in the forest and differ significantly from those in still active agricultural areas.

From the researchers’ point of view, the AI ​​models used could provide a basis for studying biodiversity in other reforestation areas. In the next step, scientists want to improve and expand their models so they can record more species. The system will also be used in the Bavarian Forest National Park in the future.

“Our artificial intelligence models could be the basis for a very universal tool for monitoring biodiversity in reforested areas,” Müller is convinced. In reforestation projects, the system can also help monitor whether a diverse forest is actually appearing in an area as stated – or just a species-poor monoculture.

© dpa-infocom, dpa:231018-99-604867/3