Acoustic Monitoring of Tropical Bats: Saccopteryx bilineata's response to habitat and time across a restoration gradient using a 2D-CNN
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…
The article discusses how habitat degradation and fragmentation, driven by human activities, lead to global biodiversity loss. Passive acoustic monitoring, while enabling long-term biodiversity assessment, produces vast amounts of data. The emergence of machine learning techniques, specifically convolutional neural networks (CNNs), has automated this data processing.
Researchers created a lightweight 2D CNN to detect the echolocation calls of the greater sac-winged bat, Saccopteryx bilineata, an insectivorous bat that forages near vegetation. This bat species was studied across a tropical restoration gradient in Para, Brazil. The 2D-CNN model demonstrated remarkable accuracy, achieving a 97.84% accuracy rate and 100% precision.
By analyzing over 157,335 field recordings from 29 sampling points over a three-year period (2023-2025), the model successfully identified 2,098 positive detections of S. bilineata. The generalized linear mixed models showed that the time since reforestation significantly increased the likelihood of detecting S. bilineata, with a beta value of 0.22 and a p-value less than 0.05, indicating a statistically significant relationship.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
