Search for: All records

Animal-borne acoustic sensors provide valuable insights into wildlife behavior and environments but face significant power and storage constraints that limit deployment duration. We present a novel adaptive acoustic monitoring system designed for long-term, real-time observation of wildlife. Our approach combines low-power hardware, configurable firmware, and an unsupervised machine learning algorithm that intelligently filters acoustic data to prioritize novel or rare sounds while reducing redundant storage. The system employs a variational autoencoder to project audio features into a low-dimensional space, followed by adaptive clustering to identify events of interest. Simulation results demonstrate the system’s ability to normalize the collection of acoustic events across varying abundance levels, with rare events retained at rates of 80–85% while frequent sounds are reduced to 3–10% retention. Initial field deployments on caribou, African elephants, and bighorn sheep show promising application across diverse species and ecological contexts. Power consumption analysis indicates the need for additional optimization to achieve multi-month deployments. This technology enables the creation of novel wilderness datasets while addressing the limitations of traditional static acoustic monitoring approaches, offering new possibilities for wildlife research, ecosystem monitoring, and conservation efforts.