18 July 2024 in New Zealand Journal of Ecology
Passive acoustic monitoring (PAM) is a critical tool in the monitoring and conservation of native species but until now its use in the detection of invasive species has been under-utilised. We present the first publicly available dataset of invasive common brushtail possum (Trichosurus vulpecula) vocalisations including 3500 annotated field recording segments. This study presents an automatic classification model designed and fine-tuned to detect the presence/absence of possums, achieving 98.4% test set accuracy and F1 score of 0.983.
1 January 2023 in Proceedings of Meetings on Acoustics
The collection and annotation of bioacoustic data presents a number of challenges to researchers, often constraining analysis to highly vocal species. Comp The collection and annotation of bioacoustic data presents a number of challenges to researchers, often constraining analysis to highly vocal species. Comp
5 September 2025 in bioRxiv
Active learning optimises machine learning model training through the data-efficient selection of informative samples for annotation and training. In the context of biodiversity monitoring using passive acoustic monitoring, active learning offers a promising strategy to reduce the fundamental annotation bottleneck and improve global training efficiency. However, the generalisability of model performance across ecologically relevant strata (e.g. sites, season etc) is often overlooked. As passive acoustic monitoring is extended to larger scales and finer resolutions, inter-strata spatiotemporal variability also increases. We introduce and investigate the concept of stratified active learning to achieve reliable and generalisable model performance across deployment conditions. We compare between implicit cluster-based diversification methods and explicit stratification, demonstrating that cross-strata generalisation is a function of stratum divergence, not sampling balance. Additionally, mutual information as well as exclusion analysis show that spatiotemporal context can explain a substantial proportion of species label variance and inform sampling decisions.
1 June 2026 in The Journal of the Acoustical Society of America
Passive acoustic monitoring (PAM) has emerged as a promising tool for collecting ecological data, particularly in the context of bird population monitoring. Bird species can be automatically identified using pre-trained models, such as BirdNET. The performance of these models can be significantly improved through fine-tuning with annotated samples recorded in the specific acoustic conditions in which the microphones are deployed. However, passive acoustic monitoring (PAM) collects vast amounts of data, and annotating bird vocalizations requires specialized expertise. As a result, only a very small portion of the recordings can be effectively labeled. Selecting the most relevant samples to annotate in order to maximize performance in model fine-tuning remains a significant challenge. First, a regularization technique addresses the challenge of class imbalance during model fine-tuning. Next, a data-driven methodology is developed, introducing the influence score, which quantifies the impact of individual training samples on model performance to inform sampling strategies. A linear model is proposed to estimate the influence score for generalization to unseen data. Finally, several sampling strategies are compared, based on acoustic indices and predictions of the pre-trained model. Together, these contributions enable the identification of efficient annotation strategies to overcome the challenges of limited annotation resources in large-scale PAM.
23 April 2026 in Methods in Ecology and Evolution
Ecological surveys are often fragmented, costly and limited in scale, leading to large and long‐standing knowledge gaps which threaten our ability to properly safeguard biodiversity. Passive acoustic monitoring (PAM) has promised to deliver automated biodiversity monitoring, but networks are rarely deployed on scales that can offer truly novel insights due to scalability and standardization challenges around collecting, managing, analysing and sharing data. Here we present the Transnational Acoustic Biodiversity Monitoring Network (TABMON), a standardized deployment of 108 autonomous sensors across Norway, the Netherlands, France and Spain along a continental bird migration route. Audio is recorded continuously, uploaded in near real‐time and processed through an automated analysis pipeline designed to support expert validation and the generation of datasets for deriving Essential Biodiversity Variables (EBVs). TABMON provides a methodological blueprint for transnational, networked PAM deployments and highlights both the opportunities and current limitations of near real‐time acoustic biodiversity monitoring at continental scales.
4 October 2025 in bioRxiv
Passive Acoustic Monitoring has emerged as a promising tool for collecting ecological data, particularly in the context of bird population monitoring. Bird species can be automatically identified using pre-trained models, such as BirdNET. The performance of these models can be significantly improved through fine-tuning with annotated samples recorded in the specific acoustic conditions in which the microphones are deployed. However, PAM collects vast amounts of data, and annotating bird vocalizations requires specialized expetise. As a result, only a very small portion of the recordings can be effectively labeled. Selecting the most relevant samples to annotate in order to maximize performance in model fine-tuning remains a significant challenge. First, a regularization technique addresses the challenge of class imbalance during model fine-tuning. Next, a data-driven methodology is developed, introducing the influence score , which quantifies the impact of individual training samples on model performance to inform sampling strategies. A linear model is proposed to estimate the influence score for generalization to unseen data. Finally, several sampling strategies are compared, based on acoustic indices and predictions of the pre-trained model. Together, these contributions enable the identification of efficient annotation strategies to overcome the challenges of limited annotation resources in large-scale passive acoustic monitoring.