Acoustic Monitoring of Tropical Bats: Saccopteryx bilineata's response to habitat and time across a restoration gradient using a 2D-CNN
- 1University of Exeter
Abstract
Global biodiversity loss is a consequence of habitat degradation and fragmentation caused by the expansion of the Anthropocene and the overexploitation of natural resources. Passive acoustic monitoring enables longitudinal assessment of biodiversity but generates massive datasets. Advancements in machine learning have enabled the development of convolutional neural networks capable of automating this process. We developed a lightweight 2D convolutional neural network capable of detecting echolocation calls of the greater sac-winged bat, Saccopteryx bilineata, an insectivorous aerial edge-foraging bat, across a tropical restoration gradient in Para, Brazil. The 2D-CNN model achieved a 97.84% accuracy and 100% precision. Deploying this model across 157,335 field recordings across 29 sampling points resampled over 3 years (2023-2025) yielded 2,098 positive detections of S. bilineata. Generalised linear mixed models revealed that time since reforestation significantly increased the odds of detecting S. bilineata ({beta} = 0.22, p < 0.001), and that detection probability was 2.14 times higher in restoration plots than in forest habitats ({beta} = 0.76, p = 0.0701). Acoustic hardware had a significant covariate influence in both fitted models ({beta} = 0.52, {beta} = 0.72, both p < 0.001). These findings demonstrate the practical applications of deep learning and bioacoustics to quantify habitat recovery and the value of restoration in regenerating functional ecological niches for aerial insectivores during early successional stages.
Related
- Towards Automated Acoustic Monitoring of Threatened Birds in Tropical Forest Ecosystem Restoration
- Soil amendments for cost-effective tropical forest restoration
- Planting set-up and local environmental conditions affect outcomes in tropical agricultural restoration
- Integrating nested species distribution models and multicriteria prioritization into an open-access geoportal for tropical forest restoration
- Audio embeddings identify novel sounds and track soundscape change within a tropical restoration landscape
BibTeX
@misc{secord2026acoustic,
title = {{Acoustic Monitoring of Tropical Bats: Saccopteryx bilineata's response to habitat and time across a restoration gradient using a 2D-CNN}},
author = {I. L. Secord and X. Zhang and R. Preston-Allen and C. Banks-Leite},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.28.755061},
url = {https://www.biorxiv.org/content/10.64898/2026.09.28.755061v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Acoustic Monitoring of Tropical Bats: Saccopteryx bilineata's response to habitat and time across a restoration gradient using a 2D-CNN
AU - I. L. Secord
AU - X. Zhang
AU - R. Preston-Allen
AU - C. Banks-Leite
PY - 2026
DA - 2026/09/28
PB - bioRxiv
DO - 10.64898/2026.09.28.755061
UR - https://www.biorxiv.org/content/10.64898/2026.09.28.755061v1
AB - Global biodiversity loss is a consequence of habitat degradation and fragmentation caused by the expansion of the Anthropocene and the overexploitation of natural resources. Passive acoustic monitoring enables longitudinal assessment of biodiversity but generates massive datasets. Advancements in machine learning have enabled the development of convolutional neural networks capable of automating this process. We developed a lightweight 2D convolutional neural network capable of detecting echolocation calls of the greater sac-winged bat, Saccopteryx bilineata, an insectivorous aerial edge-foraging bat, across a tropical restoration gradient in Para, Brazil. The 2D-CNN model achieved a 97.84% accuracy and 100% precision. Deploying this model across 157,335 field recordings across 29 sampling points resampled over 3 years (2023-2025) yielded 2,098 positive detections of S. bilineata. Generalised linear mixed models revealed that time since reforestation significantly increased the odds of detecting S. bilineata ({beta} = 0.22, p < 0.001), and that detection probability was 2.14 times higher in restoration plots than in forest habitats ({beta} = 0.76, p = 0.0701). Acoustic hardware had a significant covariate influence in both fitted models ({beta} = 0.52, {beta} = 0.72, both p < 0.001). These findings demonstrate the practical applications of deep learning and bioacoustics to quantify habitat recovery and the value of restoration in regenerating functional ecological niches for aerial insectivores during early successional stages.
ER -