.png){kind=icon}
.png){kind=icon}
Return
BirdNET and Perch perform poorly for species inventories in Amazonia but can provide a proxy for community turnover
.png){kind=icon}
OA
AI
O
N
W
C
J
E
L
A
DOI：10.1016/j.ecoinf.2026.103966.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Global bird classifiers showed very low recall in Amazonian forests. • Species inventories from off-the-shelf classifiers were unreliable. • Classifier outputs still captured broad community structure at low thresholds. • Performance was lower for passerines and high-frequency vocalisations. • Tropical classifier studies need validation against intended ecological uses.
Keywords:
Passive acoustic monitoring
Tropical birds
Machine learning
Bioacoustics
Community ecology
Amazon
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.3
Papers:
3.7K
Citations:
1.3W
Organization
Cited Papers