Publications
Selected peer-reviewed publications by our team and our collaborators that use BirdNET, BirdNET-derived embeddings, or BirdNET-based workflows.
Click one or more tags to filter publications. Click again to deselect. Use Clear to reset.
2025
Assessing spatial variability and efficacy of surrogate species at an ecosystem scale
Evaluates how well surrogate species capture spatial patterns of biodiversity across an ecosystem, finding that surrogate effectiveness varies geographically and emphasizing the need for region-specific validation when using umbrella species.
Bioregional-scale acoustic monitoring can support fire-prone forest restoration planning
Demonstrates that large-scale passive acoustic monitoring networks can provide spatially continuous information on bird communities that is useful for planning fire and forest restoration treatments across bioregional scales.
Continental-scale behavioral response of birds to a total solar eclipse
Combines data from a large network of autonomous recorders and citizen-science devices to show that bird vocal activity declines sharply only in areas experiencing near-total obscuration during a solar eclipse, revealing large-scale behavioural responses to transient darkening.
Continuous Real-Time Acoustic Monitoring of endangered bird species in Hawai ‘i
Describes the deployment of a continuous real-time acoustic monitoring system for endangered Hawaiian forest birds and shows how streaming detections can inform management and research in remote, logistically challenging environments.
Divergent responses of native predators to severe wildfire and biological invasion are mediated by life history
Shows that native predator species differ in their responses to severe wildfire and invasive prey according to life-history traits, highlighting that management actions may differentially affect predator guild members.
Frequent, heterogenous fire supports a forest owl assemblage
Shows that owl assemblages in Sierra Nevada forests are maintained under frequent, heterogeneous fire regimes, suggesting that restoring pyrodiversity can benefit multiple predator species simultaneously.
Investigating misclassification in bird sounds: The adverse effect of label noise on BirdNET
Analyses the impact of label noise in training data on BirdNET’s performance, showing that mislabelled examples can substantially degrade accuracy and providing recommendations for curation and robust training strategies.
Overview of BirdCLEF+ 2025: Multi-Taxonomic Sound Identification in the Middle Magdalena, Colombia
BirdCLEF+ 2025 expands the task beyond birds, introducing multi-taxonomic acoustic identification in Colombia’s Middle Magdalena Valley. The challenge evaluates systems on birds, mammals, amphibians, and insects, reflecting the increasing role of generalized ecoacoustic monitoring. Early results suggest that cross-taxa models benefit from shared feature representations but struggle with uneven data availability.
Setting BirdNET confidence thresholds: species-specific vs. universal approaches
This study compares species-specific versus universal confidence thresholds for BirdNET detections and evaluates their effects on precision–recall trade-offs. The authors show that species-specific thresholds generally yield better classification performance but that universal thresholds may be acceptable where data are limited, and they provide practical recommendations for threshold selection in ecological studies.
2024
A scalable and transferable approach to combining emerging conservation technologies to identify biodiversity change after large disturbances
Integrates passive acoustics, camera traps and remote sensing into a unified analytical framework to quantify biodiversity change following large disturbances, demonstrating a transferable approach for multi-taxa monitoring at landscape scales.
Birdset: A multi-task benchmark for classification in avian bioacoustics
Presents BirdSet, a curated collection of multiple labelled bird sound datasets with standardized splits and multi-task evaluation protocols to benchmark classification models across diverse acoustic and biogeographic conditions.
Detection and identification of a cryptic red crossbill call type in northeastern North America
Uses automated detection and embedding-based analyses to identify a previously unrecognized red crossbill call type in northeastern North America, highlighting the role of machine learning in uncovering cryptic vocal diversity.
Guidelines for appropriate use of BirdNET scores and other detector outputs
Clarifies how to interpret and use detector scores such as those from BirdNET, emphasizing calibration, species- and context-specific performance, and the need to propagate uncertainty when drawing ecological inferences.
Improving learning-based birdsong classification by utilizing combined audio augmentation strategies
Systematically evaluates combinations of spectrogram-based audio augmentation techniques for birdsong classification and shows that carefully designed augmentation pipelines can substantially improve generalization on imbalanced and noisy training data.
Overview of BirdCLEF 2024: Acoustic identification of under-studied bird species in the Western Ghats
BirdCLEF 2024 focuses on the Western Ghats, a global biodiversity hotspot with many understudied and data-poor species. The paper presents newly collected soundscape data and evaluates machine learning systems on sparse training regimes. Results show that transfer learning and multi-species modeling are important for effective identification in low-resource settings.
Real-time acoustic monitoring facilitates the proactive management of biological invasions
Deploys a real-time acoustic monitoring system for an invasive bird species and shows that near-real-time detections can be used operationally to guide management actions and reduce response latency.
Using bioacoustics to enhance the efficiency of spotted owl surveys and facilitate forest restoration
Shows that integrating passive acoustic monitoring into spotted owl survey protocols can increase detection efficiency and reduce field effort, with implications for designing restoration treatments in fire-affected forests.
Using the BirdNET algorithm to identify wolves, coyotes, and potentially their interactions in a large audio dataset
Repurposes BirdNET to detect and classify wolf and coyote vocalizations in extensive passive acoustic datasets, illustrating cross-taxon application and documenting patterns that may indicate interspecific interactions.
2023
A collection of fully-annotated soundscape recordings from neotropical coffee farms in Colombia and Costa Rica (Version 1) [Data set]
Curates annotated soundscapes from shade-coffee farms in Colombia and Costa Rica, supporting work on how agricultural management influences acoustic biodiversity and ecosystem services.
A collection of fully-annotated soundscape recordings from the southern Sierra Nevada mountain range (Version 1) [Data set]
Provides annotated soundscape recordings from the southern Sierra Nevada, facilitating evaluation of acoustic monitoring for forest birds in fire-affected montane landscapes.
Birb: A generalization benchmark for information retrieval in bioacoustics
Introduces BIRB, a benchmark for audio retrieval of bird vocalizations under distribution shift, and shows that current representation-learning approaches struggle with cross-dataset and cross-task generalization in realistic bioacoustic settings.
BirdNET: applications, performance, pitfalls and future opportunities
This review synthesizes published applications of BirdNET in ornithological research, assessing its performance across habitats, species and study designs. It highlights common pitfalls such as species coverage gaps, context-dependent accuracy and threshold selection, and outlines best practices and future directions for integrating BirdNET into monitoring and conservation workflows.
Estimating population size for California spotted owls and barred owls across the Sierra Nevada ecosystem with bioacoustics
Uses large-scale passive acoustic monitoring and calling-rate models to estimate population sizes of California spotted owls and barred owls, demonstrating how bioacoustics can support landscape-scale population assessments of elusive raptors.
Feature embeddings from the BirdNET algorithm provide insights into avian ecology
Demonstrates that BirdNET embeddings capture ecologically meaningful variation in avian communities, showing that embedding-based analyses can reveal gradients in habitat, disturbance and community composition beyond simple species lists.
Global birdsong embeddings enable superior transfer learning for bioacoustic classification
Trains global birdsong embedding models on large, diverse datasets and demonstrates that these embeddings substantially outperform baseline features for transfer-learning tasks across species, regions and recording conditions.
Overview of BirdCLEF 2023: Automated bird species identification in Eastern Africa
This edition introduces a new large-scale dataset from Eastern Africa, emphasizing biodiversity-rich tropical ecosystems. The challenge encourages models that generalize across sites, species, and recording conditions. Findings highlight persistent gaps in performance for rare and acoustically similar species.
Pairing a user-friendly machine-learning animal sound detector with passive acoustic surveys for occupancy modeling of an endangered primate
Applies a BirdNET-based detector to primate vocalizations in passive acoustic data and shows that detector outputs can be integrated into occupancy models to estimate site use of an endangered primate species.
Passive acoustic surveys and the BirdNET algorithm reveal detailed spatiotemporal variation in the vocal activity of two anurans
Combines passive acoustic monitoring with BirdNET-based detection to characterize fine-scale spatial and temporal patterns in calling activity of two frog species, illustrating the transferability of bird-focused models to other taxa.
Quail on fire: changing fire regimes may benefit mountain quail in fire-adapted forests
Uses occupancy modelling and fire-history data to show that mountain quail in fire-adapted forests can benefit from frequent, heterogeneous fire regimes, highlighting how restoration of historical fire patterns may aid some disturbance-adapted species.
2022
A collection of fully-annotated soundscape recordings from the Island of Hawai'i (Version 1) [Data set]
Provides annotated soundscape recordings from the Island of Hawai‘i, focusing on native and non-native species, and supporting research on tropical island bioacoustics and invasive species impacts.
A collection of fully-annotated soundscape recordings from the Northeastern United States (Version 2) [Dataset]
Provides a fully annotated soundscape dataset from Northeastern United States sites, including detailed species-level labels suitable for benchmarking bird sound detection, classification and soundscape analysis methods.
A collection of fully-annotated soundscape recordings from the Southwestern Amazon Basin (Version 1) [Data set]
Offers a labelled soundscape dataset from the southwestern Amazon Basin, capturing high-diversity tropical bird communities and enabling assessments of automated acoustic monitoring methods in complex soundscapes.
A collection of fully-annotated soundscape recordings from the Western United States (Version 1) [Data set]
Releases annotated soundscape recordings from Western United States sites with species-level labels, enabling evaluation of automated detectors and ecological analyses in fire-prone montane forest ecosystems.
Overview of BirdCLEF 2022: Endangered bird species recognition in soundscape recordings
BirdCLEF 2022 shifts attention toward endangered species detection, introducing datasets from conservation-critical regions such as Hawai‘i. The paper details the task setup and evaluation criteria designed to support real-world conservation monitoring. System results underscore the difficulty of rare-species classification in noisy habitats.
The machine learning--powered BirdNET App reduces barriers to global bird research by enabling citizen science participation
Evaluates the BirdNET mobile app as a citizen-science tool and shows that machine-learning-based bird sound identification can substantially expand spatial and taxonomic coverage of avian observations, especially in under-sampled regions.
2021
BirdNET: A deep learning solution for avian diversity monitoring
Introduces BirdNET, a deep convolutional network trained on large-scale annotated bird sound data, and shows that it can reliably detect and identify hundreds of species, enabling scalable passive acoustic monitoring for biodiversity studies.
Overview of BirdCLEF 2021: Bird call identification in soundscape recordings
The 2021 BirdCLEF challenge refines soundscape-based bird call detection with new data sources and improved annotations. It evaluates model performance on varied ecological contexts, emphasizing robustness in passive acoustic monitoring applications. Results show strong gains from ensembles and advanced data augmentation strategies.
Parsing Birdsong with Deep Audio Embeddings
Uses deep audio embeddings derived from BirdNET to segment and cluster song elements within continuous birdsong recordings, showing that generic bioacoustic embeddings can support fine-grained, unsupervised structure discovery in vocal sequences.
Survey coverage, recording duration and community composition affect observed species richness in passive acoustic surveys
Quantifies how spatial coverage, recording duration and community composition influence species richness estimates from passive acoustic surveys, providing guidance on survey design to reduce underestimation and improve comparability across studies.
2020
Overview of BirdCLEF 2020: Bird sound recognition in complex acoustic environments
BirdCLEF 2020 focuses on automated identification of birds in highly complex acoustic soundscapes, featuring overlapping species and environmental noise. The authors outline the challenge design, curated datasets, and training resources. System comparisons highlight continued improvements in deep-learning-based approaches.
2019
Identifying Birds by Sound: Large-scale Acoustic Event Recognition for Avian Activity Monitoring
Develops BirdNET as a comprehensive deep learning framework for large-scale avian acoustic event recognition and demonstrates its applicability for automated biodiversity monitoring and long-term avian activity assessments across diverse recording conditions.
Overview of BirdCLEF 2019: Large-scale bird recognition in soundscapes
The 2019 edition expands BirdCLEF toward larger-scale soundscape recognition with increased species diversity and geographic coverage. The paper describes the dataset, annotation protocols, and evaluation metrics used to benchmark automated systems. Results emphasize the growing challenge of species-rich and acoustically complex habitats.
2018
Overview of BirdCLEF 2018: Monospecies vs. Soundscape Bird Identification
This paper presents the 2018 BirdCLEF challenge, comparing single-species audio classification with full soundscape-based bird identification. It introduces the dataset, evaluation setup, and system performance across participating teams. The work highlights the difficulty of polyphonic and noisy environmental recordings in real-world biodiversity monitoring.
2017
Large-Scale Bird Sound Classification using Convolutional Neural Networks
Presents a convolutional neural network approach for large-scale bird sound classification in the BirdCLEF 2017 challenge, using spectrogram-based inputs and extensive data augmentation to achieve competitive mean average precision on highly imbalanced training data.