Utilizing Machine Learning to Explore Biodiversity in the Peruvian Jungle

 Goal of the Project

The goal of our research is to deepen our understanding of biodiversity and species behavior in the Peruvian jungle by combining acoustic monitoring with machine learning techniques. By using unsupervised clustering methods to group vector embeddings, visualizing spectrograms to identify patterns in vocalizations, and analyzing time-of-day activity trends, we seek to uncover ecological insights that would be difficult to obtain through manual analysis alone. This approach supports more scalable, efficient monitoring of wildlife in complex and remote environments.

• How effectively can unsupervised clustering methods group audio recordings?

• What patterns emerge in the acoustic data when visualized through spectrograms?

• Can time-of-day trends in the recordings provide insight into animal behavior?