A fully automated framework for acoustic identification and localization of terrestrial wildlife at scale

2026-05-09 · Source: Machine learning : nature.com subject feeds · Field: Science & Research — Life Sciences & Biology, Environmental Science & Earth Systems, Artificial Intelligence & Machine Learning · Depth: Expert, short

Summary

Researchers have developed a fully automated framework for identifying and acoustically localizing terrestrial wildlife at scale, addressing limitations of previous methods that were constrained by technical and cost challenges. The framework utilizes low-cost GPS-Audiomoth recorders and an open-source software pipeline for detection, time-delay estimation, localization, error rejection, and resolution of multiple simultaneous sound sources. This system achieved high spatial accuracy, with 99% of broadcast calls localized within 5 meters during a loudspeaker test. Its utility was demonstrated by surveying birds across a large forested site using an array of over 60 recorders. The framework, which incorporates a Convolutional Neural Network (CNN) for automated detection, produced spatial observation patterns for species that were comparable to those obtained from in-person spot mapping surveys.

Key takeaway

For ecologists and conservationists aiming to monitor wildlife populations across vast areas, this automated acoustic localization framework offers a scalable and cost-effective solution. You can deploy low-cost GPS-Audiomoth recorders and leverage the open-source software pipeline to gather fine-grained spatial data on animal movements and habitat use, significantly expanding your monitoring capabilities beyond traditional in-person surveys.

Key insights

Automated acoustic localization using low-cost hardware and open-source software enables large-scale wildlife monitoring.

Principles

• Low-cost hardware expands monitoring scale.
• Automated analysis reduces effort.
• Spatial data enhances ecological insights.

Method

The framework employs GPS-Audiomoth recorders and an open-source pipeline for detection, time-delay estimation, localization, error rejection, and resolving multiple sound sources, using a CNN for automated detection.

In practice

• Deploy GPS-Audiomoth recorders for cost-effective data.
• Utilize CNNs for automated species detection.
• Apply time-delay estimation for precise localization.

Topics

• Acoustic Localization
• Wildlife Monitoring
• Machine Learning
• GPS-Audiomoth Recorders
• Open-Source Software

Best for: AI Scientist, Research Scientist, Machine Learning Engineer

Related on AIssential

• A finely annotated dataset for the automated acoustic identification of European Orthoptera and Cicadidae — A new dataset combines weak and strong acoustic labels for automated European insect identification.
• How We Used Google's Perch v2 to Build a Bird-Based H5N1 Early Warning System in Patagonia — Bioacoustics foundation models can enable large-scale environmental monitoring for critical conservation challenges.
• NeuralMUSIC: A Hybrid Neural-Subspace Framework for Robot Sound Source Localization — NeuralMUSIC combines neural networks with classical MUSIC for robust, generalizable robot sound source localization.
• Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations — Dolph2Vec, a species-specific SSL model, effectively uncovers fine-grained dolphin communication patterns using a novel, longitudinal dataset.
• AI Trained on Birdsong Can Recognize Whale Calls — Google DeepMind's Perch 2.0, an AI audio model primarily trained on millions of land-based animal recordings including birds, amphibians, insects, and mammals, has shown unexpected strong performance…
• GetNetUPAM: Ecologically Informed Nested Cross-Validation and Noise-Robust Attention for Marine Bioacoustic Monitoring — Ecologically informed nested cross-validation and adaptive attention improve marine bioacoustic model stability and generalization.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Machine learning : nature.com subject feeds.