A lightweight deep-learning detector for the real-time monitoring of the invasive frogs Rhinella marina and Polypedates leucomystax
- 1Okinawa Institute of Science and Technology
Abstract
Early detection of invasive species is critical to efficiently managing biological invasions. Passive acoustic monitoring combined with deep learning has become an effective tool for identifying invasive anurans from their species-specific mating calls. In practice, however, these systems still depend on manually retrieving recordings and running inference on a dedicated workstation, which delays detection at invasion fronts, especially on remote islands where frequent travel is impractical. Here, we present a lightweight convolutional neural network for detecting Rhinella marina and Polypedates leucomystax that can be used with low-power microcontrollers, enabling continuous, real-time monitoring of these invasive species. Our model achieved a mean invasive-species F1 of 0.87 with precision higher than 0.88 for both species, comparable to the performance of substantially larger models at a fraction of the model size. Cross-domain evaluation confirmed reliable detection on two out-of-training locations: Iriomote Island, Japan, and on an independent dataset from Australia, demonstrating generalization across recording conditions and biogeographic contexts, albeit with local threshold calibration for P. leucomystax at Iriomote. Our results demonstrate that effective acoustic detection of invasive species is feasible on self-contained, battery-powered devices, removing the dependence on server infrastructure and enabling autonomous early warning systems in remote protected areas.
Related
- Smartphone-Assisted Aerogel Colorimetric Sensor Array Coupled with Lightweight Deep Learning for Multi-Meat Freshness Monitoring.
- GFLNet: A lightweight real-time detector with knowledge-guided compression in remote sensing images
- CAS-YOLO: A lightweight and efficient object detector for infrared UAV imagery
- IoT-enabled individual poultry monitoring with lightweight step-counting for health assessment
- Democratizing planetary-scale analysis: an ultra-lightweight Earth embedding database for accurate and flexible global land monitoring
BibTeX
@misc{deligkaris2026lightweight,
title = {{A lightweight deep-learning detector for the real-time monitoring of the invasive frogs Rhinella marina and Polypedates leucomystax}},
author = {K. Deligkaris and M. Sadeghi Tabrizi and G. Stephens},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.05.756611},
url = {https://www.biorxiv.org/content/10.64898/2026.10.05.756611v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - A lightweight deep-learning detector for the real-time monitoring of the invasive frogs Rhinella marina and Polypedates leucomystax
AU - K. Deligkaris
AU - M. Sadeghi Tabrizi
AU - G. Stephens
PY - 2026
DA - 2026/10/05
PB - bioRxiv
DO - 10.64898/2026.10.05.756611
UR - https://www.biorxiv.org/content/10.64898/2026.10.05.756611v1
AB - Early detection of invasive species is critical to efficiently managing biological invasions. Passive acoustic monitoring combined with deep learning has become an effective tool for identifying invasive anurans from their species-specific mating calls. In practice, however, these systems still depend on manually retrieving recordings and running inference on a dedicated workstation, which delays detection at invasion fronts, especially on remote islands where frequent travel is impractical. Here, we present a lightweight convolutional neural network for detecting Rhinella marina and Polypedates leucomystax that can be used with low-power microcontrollers, enabling continuous, real-time monitoring of these invasive species. Our model achieved a mean invasive-species F1 of 0.87 with precision higher than 0.88 for both species, comparable to the performance of substantially larger models at a fraction of the model size. Cross-domain evaluation confirmed reliable detection on two out-of-training locations: Iriomote Island, Japan, and on an independent dataset from Australia, demonstrating generalization across recording conditions and biogeographic contexts, albeit with local threshold calibration for P. leucomystax at Iriomote. Our results demonstrate that effective acoustic detection of invasive species is feasible on self-contained, battery-powered devices, removing the dependence on server infrastructure and enabling autonomous early warning systems in remote protected areas.
ER -