Contact: [email protected]

Data captured by ordinary people has always been helpful to researchers, and now, a new study led by the University of Michigan School for Environment and Sustainability (SEAS) shows that using artificial intelligence can extract and categorize it to build robust datasets. 

“The potential here is really big,” said Hengxing Zou, the lead author of the study who performed the work as a postdoctoral scholar in the U-M SEAS Institute for Global Change Biology. “The approach is really versatile and we have a lot of data out there basically waiting to be mined.”

The research team was specifically interested in comments that captured interactions between different species, which are harder to come by since they require constant observation. What they found is that they can use observations already made by a community of hundreds of millions of participatory scientists.

Kai Zhu, a senior author and associate professor in SEAS, adds, “AI can help turn scattered observations into ecological datasets that reveal how biological communities are responding to global change.”

Brian Weeks, associate professor in SEAS, is also a senior author. Researchers from the University of California Santa Cruz, University of California Davis, Georgia Institute of Technology, American Bird Conservancy, Notre Dame University, Santa Fe Institute and Michigan State University also contributed to the research.

Read the full press release on the Michigan News website.

Study: Large language models unlock the ecology of species interactions (DOI: 10.1073/pnas.2602244123)