Search

Invasive species are a primary threat to biodiversity and are challenging to manage once populations become established in previously unoccupied areas. But removing them is further complicated when invasions occur in continental, mixed‐ownership systems. We demonstrate a rare conservation success: the regional‐scale removal of an invasive predator – the barred owl (Strix varia) – to benefit the spotted owl (Strix occidentalis) in California. Barred owl site occupancy declined sixfold, from 0.19 to 0.03, following 1 year of removals, and site extinction (0.92) far exceeded colonization (0.02). Spotted owls recolonized 56% of formerly occupied territories within 1 year, contrasting starkly with removals conducted after barred owls achieved high densities in the Pacific Northwest. Our study therefore averted the otherwise likely extirpation of California spotted owls (Strix occidentalis occidentalis) by barred owl competition. Collectively, leveraging technological advances in population monitoring, early intervention, targeting defensible biogeographic areas, and fostering public–private partnerships will reduce invasive species‐driven extinction of native fauna in continental systems. [ABSTRACT FROM AUTHOR]

Forty years of increasing fire size and severity in California's Sierra Nevada were embodied by the 2021 Dixie Fire, which burned 389,837 ha between July and October, making it one of the largest, most destructive fires in California's history. Historical fire regimes burned substantial areas annually, but primarily at low and moderate severities. Studies of the implications of fires like the Dixie Fire, which burn largely at higher severities, have focused on habitat change in the burned area; much less is known about potential edge effects. The hermit warbler (Setophaga occidentalis) and western bluebird (Sialia mexicana) have previously been characterized as species with dramatic, opposing post-wildfire responses: hermit warblers display a strongly negative response to fires while western bluebirds display a strong positive response. We conducted passive acoustic monitoring pre- and post-Dixie Fire inside and outside the burned area and analyzed the audio with the machine learning animal identification tool BirdNET. We then used a multi-season occupancy modeling framework to characterize both species' site extinction and site colonization responses as a function of fire and habitat variables. We found no influence of edge effects, though this may have been a function of the low density of our recorders relative to the home range of these species. We did, however, observe contrasting relationships between the species. Hermit warbler site extinction was elevated in burned areas, particularly those burned at higher severities, while site colonization in unburned habitat was positively associated with canopy cover. Western bluebirds displayed the exact opposite pattern (elevated colonization in areas of high-severity fire, elevated extinction in unburned areas with high canopy cover). These results suggest contrasting trajectories for fire-influenced bird species under contemporary fire regimes and could guide hypothesis generation for broader studies of biodiversity responses to fire in this ecosystem. [ABSTRACT FROM AUTHOR]

Applied ecology is based on an assumption that a management action will result in a predicted outcome. Testing the prediction accuracy of ecological models is the most powerful way of evaluating the knowledge implicit in this cause-effect relationship, however, the prevalence of predictive modeling and prediction testing are spreading slowly in ecology. The challenge of prediction testing is particularly acute for small-scale studies, because withholding data for prediction testing (e.g., via k -fold cross validation) can reduce model precision. However, by necessity small-scale studies are common. We use one such study that explored small mammal abundance along an elevational gradient to test prediction accuracy of models with varying degrees of information content. For each of three small mammal species, we conducted 5000 iterations of the following process: (1) randomly selected 75 % of the data to develop generalized linear models of species abundance that used detailed site measurements as covariates, (2) used an information theoretic approach to compare the top model with detailed covariates to habitat type-only and null models constructed with the same data, (3) tested those models' ability to predict the 25 % of the randomly withheld data, and (4) evaluated prediction accuracy with a quadratic loss function. Detailed models fit the model-evaluation data best but had greater expected prediction error when predicting out-of-sample data relative to the habitat type models. Relationships between species and detailed site variables may be evident only within the framework of explicitly hierarchical analyses. We show that even with a small but relatively typical dataset (n = 28 sampling locations across 125 km over two years), researchers can effectively compare models with different information content and measure models' predictive power, thus evaluating their own ecological understanding and defining the limits of their inferences. Identifying the appropriate scope of inference through prediction testing is ecologically valuable and is attainable even with small datasets. [ABSTRACT FROM AUTHOR]

Emerging bioacoustic technology allows researchers to passively record animal vocalizations to study population dynamics at relatively broad spatial scales. Spatiotemporal patterns in vocalization behavior free from direct human influence, which occurs during traditional vocal-lure surveys, may also yield novel behavioral insights. We used passively recorded audio data to examine such patterns in the California Spotted Owl (Strix occidentalis occidentalis) across the northern Sierra Nevada. We assessed temporal patterns in the initiation of bouts of four-note calls and the number of such calls, and we used generalized linear mixed models to test whether environmental factors influenced bout-initiation time, bout duration, and the number of calls per unit time. We found that (1) Spotted Owls were most vocally active within three hours of sunset, (2) bouts of calling were longer with fewer calls per unit time in open and young forest, (3) those bouts were concentrated in the middle of the night, and (4) the frequency of occurrence and duration of bouts of territorial vocal activity was reduced in montane riparian forest. These patterns suggest that Spotted Owls may engage in territorial defense in marginal habitat (open and young forest) and minimize their vocal activity in key foraging habitat (montane riparian forest). This application of acoustic monitoring data to behavioral ecology illustrates the broad applicability of the underlying audio data and its potential to yield novel ecological insights. [ABSTRACT FROM AUTHOR]

Bioacoustics has become widely used in the study of acoustically active animals, and machine learning algorithms have emerged as efficient and effective strategies to identify species vocalizations. Current applications of machine learning in bioacoustics often identify acoustic events to the species-level but fail to capture the complex acoustic repertoires animals use to communicate, which can inform habitat associations, demography, behavior, and the life history of cryptic species. The penultimate layer of most machine learning algorithms results in a vector of numbers describing the input, called feature embeddings. Here, we demonstrate that the feature embeddings generated by the BirdNET algorithm can enable within-species classifications of acoustic events. First, we successfully differentiated adult and juvenile Great Gray Owls; second, we identified three unique sounds associated with Great Spotted Woodpeckers (series call, alarm call, and drumming). These applications of BirdNET feature embeddings suggest that researchers can classify vocalizations into groups when group membership is unknown, and that within-species grouping is possible even when target signals are extremely rare. These applications of a relatively "black-box" aspect of machine learning algorithms can be used to derive ecologically informative acoustic classifications, which can inform the conservation of cryptic and otherwise difficult to study species. • AI tools can identify many species, but fail to represent animals' repertoires • BirdNET algorithm's feature embeddings enable within-species sound classification • Differentiating species' sounds can improve ecological and conservation research [ABSTRACT FROM AUTHOR]

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. • We developed a DNN, called BirdNET, capable of identifying 984 North American and European bird species by sound • We tested the model against three independent datasets of single-species recordings and fully annotated soundscape data • BirdNET achieved a mean average precision of 0.791 for single-species recordings and a F0.5 score of 0.414 for annotated soundscapes • Our system is publicly available and can be used by other researchers • We also provide online demos and prototypes on out project website at https://birdnet.cornell.edu [ABSTRACT FROM AUTHOR]

We report a single-season, non-homing movement of 4287 ± 10 m by an adult male Deer Mouse, Peromyscus maniculatus, in western Maine, United States, in summer 2014. The movement was achieved in two stages: 927 ± 3 m in four days and an additional 3360 ± 10 m in 44 days. This is approximately 40% greater than the previously documented maximum linear movement for an individual of this species. [ABSTRACT FROM AUTHOR]