University of Michigan Research Utilizes AI to Enhance Birdwatching Data for Environmental Studies
A new study led by Dr. Hengxing Zou, a quantitative ecologist and former postdoctoral researcher at the University of Michigan's Institute for Global Change Biology, explores how artificial intelligence (AI) can analyze millions of birdwatching comments to create vital environmental data. Published in the Proceedings of the National Academy of Sciences, the research combines human observation with large language models to understand species interactions and ecosystem changes. Birdwatchers' detailed notes on platforms like eBird, describing observations such as a blue jay chasing another bird or a hawk feeding on prey, provide rich, natural language data. The AI's role is to distill information from these comments, identifying specific species interactions and their contexts, which would be too numerous to analyze manually. Researchers rigorously manually check the AI's interpretations to ensure accuracy, minimizing issues like 'hallucinations' often associated with generative AI models.
