Home // UBICOMM 2025, The Nineteenth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies // View article


Low-Power Distributed Acoustic Sensor Network for Autonomous Wildlife Monitoring Using LoRa and AI for Digital Twin

Authors:
Gonzalo de Miguel
Miguel Zaragoza-Esquerdo
Alberto Ivars-Palomares
Sandra Sendra
Jaime Lloret

Keywords: LoRa, acoustic sensors, wildlife monitoring, bioacoustic, low-power IoT, BirdNET, FFT, ADPCM compression, environmental sensing, edge computing.

Abstract:
Biodiversity loss driven by climate change, habitat degradation, and anthropogenic pressures demands efficient wildlife monitoring solutions. Conventional methods are often costly, invasive, and limited in spatial or temporal coverage. Acoustic monitoring provides a non-intrusive alternative but faces challenges related to high data volumes, limited power availability, and restricted communication bandwidth in remote deployments. This paper presents a low-power distributed acoustic sensor network for autonomous wildlife monitoring, with emphasis on bird species. Each node combines an ESP32 microcontroller, a high-sensitivity digital microphone, and a Long Range (LoRa) transceiver to capture and transmit event-triggered audio. Real-time Fast Fourier Transform (FFT) analysis detects relevant acoustic activity, triggering Adaptive Differential Pulse Modulation (ADPCM) compression and LoRa-based transmission to a central receiver. The backend decodes the audio, applies the BirdNET Artificial Intelligence (AI) model for species identification, and stores results in a MongoDB database with web-based visualization. Experimental validation demonstrates high detection reliability for species with distinctive calls, confirming the system’s scalability, energy efficiency, and suitability for long-term biodiversity monitoring in remote environments without continuous connectivity.

Pages: 36 to 42

Copyright: Copyright (c) IARIA, 2025

Publication date: September 28, 2025

Published in: conference

ISSN: 2308-4278

ISBN: 978-1-68558-288-3

Location: Lisbon, Portugal

Dates: from September 28, 2025 to October 2, 2025