BirdNET: A deep learning solution for avian diversity monitoring
By Stefan Kahl, Connor M. Wood, Maximilian Eibl, Holger Klinck. Ecological Informatics, 2021
818 citations recorded by the source corpus.
Variation in avian diversity in space and time is commonly used as a metric to assess environmental changes. Conventionally, such data were collected by expert observers, but passively collected acoustic data is rapidly emerging as an alternative survey technique. However, efficiently extracting accurate species richness data from large audio datasets has proven challenging. Recent advances in deep artificial neural networks (DNNs) have transformed the field of machine learning, frequently outperforming traditional signal processing techniques in the domain of acoustic event detection and classification. We developed a DNN, called BirdNET, capable of identifying 984 North American and European bird species by sound. Our task-specific model architecture was derived from the family of residual networks (ResNets), consisted of 157 layers with more than 27 million parameters, and was trained using extensive data pre-processing, augmentation, and mixup. We tested the model against three independent datasets: (a) 22,960 single-species recordings; (b) 286 h of fully annotated soundscape data collected by an array of autonomous recording units in a design analogous to what researchers might use to measure avian diversity in a field setting; and (c) 33,670 h of soundscape data from a single high-quality omnidirectional microphone deployed near four eBird hotspots frequented by expert birders. We found that domain-specific data augmentation is key to build models that are robust against high ambient noise levels and can cope with overlapping vocalizations. Task-specific model designs and training regimes for audio event recognition perform on-par with very complex architectures used in other domains (e.g., object detection in images). We also found that high temporal resolution of input spectrograms (short FFT window length) improves the classification performance for bird sounds. In summary, BirdNET achieved a mean average precision of 0.791 for single-species recordings, a F0.5 score of 0.414 for annotated soundscapes, and an average correlation of 0.251 with hotspot observation across 121 species and 4 years of audio data. By enabling the efficient extraction of the vocalizations of many hundreds of bird species from potentially vast amounts of audio data, BirdNET and similar tools have the potential to add tremendous value to existing and future passively collected audio datasets and may transform the field of avian ecology and conservation.
Subfields: Developmental Biology, Ecological Modeling, Signal Processing
View Paper: https://www.semanticscholar.org/paper/9ca05ee91175d5bc0c61939bbf5d8e71b3c856fd
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Developmental Biology
In Ecological Modeling
In Signal Processing
Citations in the corpus
- Computational bioacoustics with deep learning: a review and roadmap (2021, methodology): “Although ImageNet pretraining is still occasionally used (Disabato et al., 2021; Fonseca et al., 2021), many authors now pretrain using Google’s AudioSet (a diverse dataset of audio from YouTube videos (Hershey et al., 2017)) (C¸oban et al., 2020; Kahl et al., 2021).”
- Perspectives in machine learning for wildlife conservation (2021, methodology): “a: The BirdNET algorithm (26) was used to detect Carolina wren vocalizations in more than 35,000 hours of passive acoustic monitoring data from Ithaca, New York, allowing researchers to document the gradual recovery of the population following a harsh winter season in 2015 (H.”