Advancing invasive species monitoring: A free tool for detecting invasive cane toads using continental-scale data
Invasive species pose a significant threat to global biodiversity and ecosystem health, necessitating effective monitoring tools for early detection and management. Here, we present the development and assessment of a user-friendly and transferable monitoring tool for the invasive cane toad (Rhinell...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-11-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125001815 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850235360427114496 |
|---|---|
| author | Franco Ka Wah Leung Lin Schwarzkopf Slade Allen-Ankins |
| author_facet | Franco Ka Wah Leung Lin Schwarzkopf Slade Allen-Ankins |
| author_sort | Franco Ka Wah Leung |
| collection | DOAJ |
| description | Invasive species pose a significant threat to global biodiversity and ecosystem health, necessitating effective monitoring tools for early detection and management. Here, we present the development and assessment of a user-friendly and transferable monitoring tool for the invasive cane toad (Rhinella marina) using passive acoustic monitoring (PAM) and machine learning algorithms. Leveraging a continental-scale PAM dataset (Australian Acoustic Observatory), we trained a cane toad classifier using the BirdNET algorithm, a convolutional neural network architecture capable of identifying acoustic events. We validated thousands of BirdNET predictions across Australia, and our classifier achieved over 90 % accuracy even at many sites outside the areas from which the training data were obtained. Additionally, because cane toads typically call for long periods, we significantly enhanced detection accuracy by incorporating contextual information from time-series data, essentially checking if other calls occurred around each detection (an optimized threshold approach using conditional inference trees). This method substantially reduced false positives and improved overall performance in cane toad detection at sites across Australia. Overall, our method will allow others to develop accurate and precise automated acoustic monitoring tools tailored to their situation, with minimal training data, addressing the critical need for accessible solutions in biodiversity monitoring, control of invasive species and conservation. |
| format | Article |
| id | doaj-art-7ebe2ebcab8b4b5f9ddcc01ebd20d559 |
| institution | OA Journals |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-7ebe2ebcab8b4b5f9ddcc01ebd20d5592025-08-20T02:02:17ZengElsevierEcological Informatics1574-95412025-11-018910317210.1016/j.ecoinf.2025.103172Advancing invasive species monitoring: A free tool for detecting invasive cane toads using continental-scale dataFranco Ka Wah Leung0Lin Schwarzkopf1Slade Allen-Ankins2Corresponding author.; College of Science and Engineering, James Cook University, Townsville 4814, Queensland, AustraliaCollege of Science and Engineering, James Cook University, Townsville 4814, Queensland, AustraliaCollege of Science and Engineering, James Cook University, Townsville 4814, Queensland, AustraliaInvasive species pose a significant threat to global biodiversity and ecosystem health, necessitating effective monitoring tools for early detection and management. Here, we present the development and assessment of a user-friendly and transferable monitoring tool for the invasive cane toad (Rhinella marina) using passive acoustic monitoring (PAM) and machine learning algorithms. Leveraging a continental-scale PAM dataset (Australian Acoustic Observatory), we trained a cane toad classifier using the BirdNET algorithm, a convolutional neural network architecture capable of identifying acoustic events. We validated thousands of BirdNET predictions across Australia, and our classifier achieved over 90 % accuracy even at many sites outside the areas from which the training data were obtained. Additionally, because cane toads typically call for long periods, we significantly enhanced detection accuracy by incorporating contextual information from time-series data, essentially checking if other calls occurred around each detection (an optimized threshold approach using conditional inference trees). This method substantially reduced false positives and improved overall performance in cane toad detection at sites across Australia. Overall, our method will allow others to develop accurate and precise automated acoustic monitoring tools tailored to their situation, with minimal training data, addressing the critical need for accessible solutions in biodiversity monitoring, control of invasive species and conservation.http://www.sciencedirect.com/science/article/pii/S1574954125001815Australian acoustic observatoryBirdNETCane toadInvasive speciesMachine learningPassive acoustic monitoring |
| spellingShingle | Franco Ka Wah Leung Lin Schwarzkopf Slade Allen-Ankins Advancing invasive species monitoring: A free tool for detecting invasive cane toads using continental-scale data Ecological Informatics Australian acoustic observatory BirdNET Cane toad Invasive species Machine learning Passive acoustic monitoring |
| title | Advancing invasive species monitoring: A free tool for detecting invasive cane toads using continental-scale data |
| title_full | Advancing invasive species monitoring: A free tool for detecting invasive cane toads using continental-scale data |
| title_fullStr | Advancing invasive species monitoring: A free tool for detecting invasive cane toads using continental-scale data |
| title_full_unstemmed | Advancing invasive species monitoring: A free tool for detecting invasive cane toads using continental-scale data |
| title_short | Advancing invasive species monitoring: A free tool for detecting invasive cane toads using continental-scale data |
| title_sort | advancing invasive species monitoring a free tool for detecting invasive cane toads using continental scale data |
| topic | Australian acoustic observatory BirdNET Cane toad Invasive species Machine learning Passive acoustic monitoring |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125001815 |
| work_keys_str_mv | AT francokawahleung advancinginvasivespeciesmonitoringafreetoolfordetectinginvasivecanetoadsusingcontinentalscaledata AT linschwarzkopf advancinginvasivespeciesmonitoringafreetoolfordetectinginvasivecanetoadsusingcontinentalscaledata AT sladeallenankins advancinginvasivespeciesmonitoringafreetoolfordetectinginvasivecanetoadsusingcontinentalscaledata |