Acoustic Monitoring Data Research Articles

Comparing field performance of ultrasonic microphones to facilitate analysis of long‐term acoustic bat monitoring data

AbstractPassive acoustic monitoring is a standard technique for studying bat ecology and behavior. However, an issue that has received little attention is how to appropriately analyze data within a long‐term acoustic monitoring dataset when the equipment has been replaced and updated. Equipment changes are often inevitable, especially for microphones, which need to be replaced regularly due to extended weather exposure and associated reductions in recording quality. We compared 2 ultrasonic microphone models (Wildlife Acoustics SMM‐U1 and SMM‐U2) by deploying them side‐by‐side with the same acoustic detector unit. We tested 9 or 10 microphones per model in field deployments lasting an average of 9 nights. We compared triggering frequency, species classification, detection rates, and echolocation call parameters (as indicators of signal quality) from both microphones. The vast majority (97%) of our 25,949 paired recordings were captured simultaneously by both microphones. Yet, the SMM‐U2 outperformed the SMM‐U1 in terms of proportion of files classifiable to the species level (70% versus 61%), rate of bat detections per night (1–6.5 more detections per night depending on species), and recording quality. Based on our results, we propose a correction factor to facilitate direct comparison of datasets collected with these 2 different microphones. Our study will assist bat researchers in selecting appropriate equipment and accounting for potential biases in long‐term acoustic monitoring programs.

Diverse baleen whale acoustic occurrence around two sub-Antarctic islands: A tale of residents and visitors

Knowledge on the occurrence and behaviour of baleen whales around sub-Antarctic regions is limited, and usually based on short, seasonal sighting research from shore or research vessels and whaling records, neither of which provide accurate and comprehensive year-round perspectives of these animals’ ecology. We investigated the seasonal acoustic occurrence and diel vocalizing pattern of baleen whales around the sub-Antarctic Prince Edward Islands (PEIs) using passive acoustic monitoring data from mid-2021 to mid-2023, detecting six distinct baleen whale songs from Antarctic blue whales, Madagascan pygmy blue whales, fin whales, Antarctic minke whales, humpback whales, and sei whales. Antarctic blue and fin whales were detected year-round whereas the other species’ songs were detected seasonally, including a new Antarctic minke whale bio-duck song sub-type described here for the first time. Antarctic minke and sei whales were more vocally active at night-time whereas the other species had no clear diel vocalizing patterns. Random forest models identified month and/or sea surface temperature as the most important predictors of all baleen whale acoustic occurrence. These novel results highlight the PEIs as a useful habitat for baleen whales given the number of species that inhabit or transit through this region.

Temporal patterns in dolphin foraging activity in the Mediterranean Sea: insights from vocalisations recorded during the ACCOBAMS Survey Initiative

Marine organisms continually adapt their physiology and behaviour to temporal variations in their environment, resulting in diurnal rhythmic behaviour, particularly when foraging. In delphinids, these rhythms can be studied by recording echolocation clicks, which can provide indicators of foraging activity. The foraging rhythms of delphinids and their relationship to temporal parameters are poorly documented and most studies so far have used moored passive acoustic systems. The present study provides, for the first time, information on the activity rhythms of delphinids investigated in relation with temporal variables at a basin scale from a moving platform, in the western and central Mediterranean Sea. We used passive acoustic recordings collected by hydrophones towed along transect lines during the ACCOBAMS Survey Initiative in the summer 2018. We extracted variables that may influence daily and monthly rhythms, including time of day, lunar cycle, lunar illumination and sea state and fitted generalised additive models. The nycthemeral and lunar cycles were the two main factors influencing dolphin activity rhythms. Echolocation activity was predominant at night, with a maximum of 0.026 acoustic events per minute at 21:00/22:00 compared to as few as 0.0007 events per minute at 11:00. These events were also more frequent during the third quarter of the moon; 0.033 acoustic events on day 22 of the lunar cycle as opposed to 0.0008 on day 8 of the lunar cycle, corresponding to the first quarter of the moon. Variations in the echolocation activity of delphinids in the Mediterranean Sea could reflect variation in their foraging effort and be related to prey density, composition, accessibility and catchability within dolphin foraging depth range. These results should also improve interpretation of passive acoustic monitoring data.

Characterisation of the ringed seal (Pusa hispida) acoustic repertoire during spring in the Western Canadian Arctic

ABSTRACT Understanding the acoustic repertoire of a species is crucial for comprehending its ecology and can also provide a valuable tool in the analysis of passive acoustic monitoring data. Despite being the most abundant seal species in the Arctic, the call repertoire of ringed seals (Pusa hispida) remains poorly studied. This paper aims to provide a comprehensive and quantitative description of the calls produced by ringed seals. Data collection occurred in May 2022 near Ulukhaktok in the Western Canadian Arctic. Acoustic recorders were deployed in cracks in the sea ice that were regularly used by ringed seals as haul-out areas. All calls were counted and classified into one of three categories: yelps, barks and growls. High-quality calls were further analysed with ten acoustic parameters calculated for each signal. Cluster and classification and regression tree (CART) analyses were used to assess if the visual classification of calls was supported by the acoustic parameters calculated. The cluster and CART analyses affirmed the presence of all three distinct call types in the ringed seal acoustic repertoire. Classification of unseen calls using the CART model demonstrated an accuracy of 98%. The findings presented here serve as foundational information on the acoustic repertoire of ringed seals.

Biogeographic patterns of Pacific white‐sided dolphins based on long‐term passive acoustic records

AbstractAimThis study investigates the biogeographic patterns of Pacific white‐sided dolphins (Lagenorhynchus obliquidens) in the Eastern North Pacific based on long‐term passive acoustic records. We aim to elucidate the ecological and behavioural significance of distinct echolocation click types and their implications for population delineation, geographic distribution, environmental adaptation and management.LocationEastern North Pacific Ocean.Time Period2005–2021.Major Taxa StudiedPacific white‐sided dolphin.MethodsOver 50 cumulative years of passive acoustic monitoring (PAM) data from 14 locations were analyzed using a deep neural network to classify two distinct Pacific white‐sided dolphin echolocation click types. The study assessed spatial, diel, seasonal and interannual patterns of the two click types, correlating them with major environmental drivers such as the El Niño Southern Oscillation and the North Pacific Gyre Oscillation, and modeling long‐term spatial‐seasonal patterns.ResultsDistinct spatial, diel and seasonal patterns were observed for each click type. Significant biogeographical shifts in presence were observed following the 2014–2016 marine heatwave event.Main ConclusionsDistinct spatial distributions of the two click types support the hypothesis that Pacific white‐sided dolphins produce population‐specific echolocation clicks. Seasonal and diel patterns suggest spatiotemporal niche partitioning between the populations in Southern California. Interannual changes, notably initiated during the 2014–2016 marine heatwave, indicate climate‐driven range expansions and contractions related to gradual tropicalization of the Southern California Bight.

Population health implications of exposure to pervasive military aircraft noise pollution.

While the adverse health effects of civil aircraft noise are relatively well studied, impacts associated with more intense and intermittent noise from military aviation have been rarely assessed. In recent years, increased training at Naval Air Station Whidbey Island, USA has raised concerns regarding the public health and well-being implications of noise from military aviation. This study assessed the public health risks of military aircraft noise by developing a systematic workflow that uses acoustic and aircraft operations data to map noise exposure and predict health outcomes at the population scale. Acoustic data encompassing seven years of monitoring efforts were integrated with flight operations data for 2020-2021 and a Department of Defense noise simulation model to characterize the noise regime. The model produced contours for day-night, nighttime, and 24-h average levels, which were validated by field monitoring and mapped to yield the estimated noise burden. Established thresholds and exposure-response relationships were used to predict the population subject to potential noise-related health effects, including annoyance, sleep disturbance, hearing impairment, and delays in childhood learning. Over 74,000 people within the area of aircraft noise exposure were at risk of adverse health effects. Of those exposed, substantial numbers were estimated to be highly annoyed and highly sleep disturbed, and several schools were exposed to levels that place them at risk of delay in childhood learning. Noise in some areas exceeded thresholds established by federal regulations for public health, residential land use and noise mitigation action, as well as the ranges of established exposure-response relationships. This study quantified the extensive spatial scale and population health burden of noise from military aviation.We employed a novel GIS-based workflow for relating mapped distributions of aircraft noise exposure to a suite of public health outcomes by integrating acoustic monitoring and simulation data with a dasymetric population density map. This approach enables the evaluation of population health impacts due to past, current, and future proposed military operations. Moreover, itcanbemodified for application to other environmental noise sources and offers an improved open-sourcetool to assess the population health implications of environmental noise exposure, inform at-risk communities, and guide efforts in noise mitigation and policy governing noise legislation, urban planning, and land use.

Passive acoustic monitoring and convolutional neural networks facilitate high-resolution and broadscale monitoring of a threatened species

Population monitoring is an essential component of biodiversity conservation and management, but low detection probabilities for rare and/or cryptic species makes estimating abundance and occupancy challenging. Passive acoustic monitoring combined with machine learning algorithms represents a potential path forward to effectively and efficiently monitor the occurrence of rare vocalizing species across entire forest landscapes. Our objectives were to develop and implement a convolutional neural network (PNW-Cnet) to identify vocalizations of a rare and threatened forest nesting bird species – the marbled murrelet (Brachyramphus marmoratus) – in the Pacific Northwest, U.S.A., 2018–2021. We used PNW-Cnet predictions from broadscale passive acoustic monitoring data to examine spatiotemporal patterns in the distribution of murrelets. PNW-Cnet showed sufficiently high prediction accuracy (overall precision > 0.9) to enable broadscale population monitoring. Spatiotemporal analysis showed that annual peak murrelet call abundance occurs in ordinal weeks 28–32 (late July–Mid August) but this varied by study area. The greatest number of detections typically occurred in the Olympic Peninsula and Oregon Coast Range where late-successional forest dominates and nearer to ocean habitats. We demonstrate that passive acoustic monitoring can be used to understand intensity of use across broad scales for a rare and cryptic species in addition to the typical detection/non-detection data that are often collected. Passive acoustic monitoring combined with PNW-Cnet offers considerable promise for species distribution modeling and long-term population monitoring for rare species.

Rerouting of a major shipping lane through important harbour porpoise habitat caused no detectable change in annual occurrence or foraging patterns

Shipping is one of the largest industries globally, with well-known negative impacts on the marine environment. Despite the known negative short-term (minutes to hours) impact of shipping on individual animal behavioural responses, very little is understood about the long-term (months to years) impact on marine species presence and area use. This study took advantage of a planned rerouting of a major shipping lane leading into the Baltic Sea, to investigate the impact on the presence and foraging behaviour of a marine species known to be sensitive to underwater noise, the harbour porpoise (Phocoena phocoena). Passive acoustic monitoring data were collected from 15 stations over two years. Against predictions, no clear change occurred in monthly presence or foraging behaviour of the porpoises, despite the observed changes in noise and vessel traffic. However, long-term heightened noise levels may still impact communication, echolocation, or stress levels of individuals, and needs further investigation.

North Atlantic right whale density surface model for the US Atlantic evaluated with passive acoustic monitoring

The Critically Endangered North Atlantic right whale Eubalaena glacialis entered a population decline around 2011. To save this species without closing the ocean to human activities requires detailed information about its intra-annual density patterns that can be used to assess and mitigate human-caused risks. Using 2.9 million km of visual line-transect survey effort from the US Atlantic and Canadian Maritimes conducted in 2003-2020 by 11 institutions, we modeled the absolute density (ind. km-2) of the species using spatial, temporal, and environmental covariates at a monthly time step. We accounted for detectability differences between survey platforms, teams, and conditions, and corrected all data for perception and availability biases, accounting for platform differences, whale dive behavior, group composition, and group size. We produced maps of predicted density and evaluated our results using independently collected passive acoustic monitoring (PAM) data. Densities correlated positively (r = 0.46, ρ = 0.58, τ = 0.46) with acoustic detection rates obtained at 492 stationary PAM recorders deployed across the study area (mean recorder duration = 138 d). This is the first study to quantify the concurrence of visual and acoustic observations of the species in US waters. We summarized predictions into mean monthly density and uncertainty maps for the 2003-2009 and 2010-2020 eras, based on the significant changes in the species’ spatial distribution that began around 2010. The results quantify the striking distribution shifts and provide effort- and bias-corrected density surfaces to inform risk assessments, estimations of take, and marine spatial planning.

Efficient quality assurance and quality control for passive acoustic monitoring data: reducing and documenting false-positive and false-negative errors

ABSTRACT Autonomous Recording Units (ARUs) are widely used to survey for a variety of taxa. This survey method allows for high spatial and temporal coverage but will typically include identification errors that can bias estimates of occupancy. In some instances, verifying all individual detections is prohibitive. To direct verification effort, we developed a model to estimate the probability that transcribers would agree on an identification. Agreement probability was positively influenced by transcriber skill, identification confidence, species commonness and some song types. In contrast, agreement probability was lower when an acoustic signal was classified as a trill. We evaluated our model on independent data where all species detections were verified, and verification effort (time) was quantified. Our model performed well at predicting transcriber agreement on independent data (AUC = 0.71). We applied the model to randomised subsets of the independent data to compare the cost benefit of three approaches to verification under varying effort. We show how modelling probability of transcriber agreement can be used to more efficiently direct verification of species acoustic tags. Our approach could be adapted elsewhere to quantify and reduce species misidentifications in unverified passive acoustic monitoring data for either manual processing or detections from automated classifiers.

Connecting separate monitoring programs through the SoundCoop

Passive acoustic monitoring (PAM) data collection has been growing exponentially, resulting in petabytes of data that document ocean soundscapes, how they change over time, and what animals use these ecosystems at varying timescales. Efficiently extracting this critical information and comparing it to other datasets in the context of ecosystem-based management is a Big Data challenge that traditional desktop processing methods cannot address. The curation, management, and dissemination of PAM datasets is another challenge in need of collaborative progress. To meet these exigencies, a multi-agency funded Sound Cooperative (SoundCoop) project is building community-focused, national cyberinfrastructure capability for PAM data to promote improved, scalable and sustainable accessibility and applications for management and science. Driven by partnerships and framed by four case studies, the SoundCoop has established guidance on the standardized processing of sound level metrics using free software toolkits and begun developing core cyberinfrastructure components that future PAM projects can leverage. U.S. and international scientists contributed PAM data collected across 10 long-term monitoring projects to operationalize the production of hybrid-millidecade spectra across a diversity of labs/instruments. Collectively, the contributed data demonstrate the value of standardized processing that enables the creation of comparable results from disparate monitoring efforts.

Technology Focus: High Pressure/High Temperature (March 2024)

Early February saw the occasion of India Energy Week (IEW), a major event held in Goa, India, with which I was pleased to be engaged. The meeting addressed the many challenges and transformations facing the energy sector around the world, in both the short and long term. Complex alignments and armed conflict affect humankind around the globe and disrupt the infrastructural networks that connect populations. Recent events in the Red Sea serve as only one example of how geopolitics can profoundly influence a hydrocarbon market that expects to see high volatility in pricing. IEW drew further attention to the important role India will play in the global energy economy of the future. A huge market with a booming economy and a growing demand for energy, India, too, seeks to develop its energy mix in accordance with the international goal of achieving a net-zero future and exploring renewable energies. Within that greater framework, the subject of this feature, high-pressure/high-temperature (HP/HT) resources, continues to be a focus of efforts to apply new technologies that maximize productivity while addressing concerns related to capital expenditure, operating expenses, and high drilling costs. These cost-effective technologies will only grow in importance in exploiting HP/HT and ultra-HP/HT fields. Increased emphasis on effective well control, durable completion equipment, and monitoring of downhole conditions will become key entry points for technological advances in the near future. This year saw a somewhat smaller number of HP/HT-centered conference papers for review. Nevertheless, I have identified, with an aim of providing readers an idea of the robust scope of research within the HP/HT industry, important works pertaining to simulation, drilling, and cleanup. These papers, set against the volatility faced by the energy sector, embody the importance of keeping our fellow energy professionals apprised of our successes and lessons learned. Recommended additional reading at OnePetro: www.onepetro.org. OTC 32657 Comparison of Wellhead Fatigue Methods Using Acoustic and Standalone Monitoring Data for HP/HT Developments by Bulent Mercan, 2H Offshore, et al. IPTC 22815 Successful Drilling of the Deepest and Hottest HP/HT Carbonate Well Offshore Malaysia, Lessons Learned, and Way Forward by Swee Hong Gary Ong, PTT Exploration and Production, et al. OTC 32203 Managing the High-Temperature Risk in a Horizontal HP/HT Deepwater Well by Yu Liu, Shell, et al.

Detecting ringed seal vocalizations in multiple environments using deep learning

Deep learning methods have recently been successfully applied to create a variety of automated acoustic detectors in the field of marine bioacoustics. Automated detectors are essential for analyzing large volumes of passive acoustic monitoring (PAM) data since manual analysis is prohibitively time-consuming and costly. PAM is the primary method for obtaining data on species which are endemic to remote regions, such as the Canadian Arctic. Arctic ringed seals are listed as a Species of Special Concern in Canada due to a loss of critical habitat caused by the effects of climate change. Here, ResNet, a convolutional neural network architecture, is trained on thousands of examples of ringed seal vocalizations recorded at various locations within the Canadian Arctic to create the first practical automated ringed seal detector. The network achieves a precision of 0.89, recall of 0.80, and F1 score of 0.85 when tested on 215 five-minute recordings from sites included in the training process. To improve the generalizability of the detector for new locations, fine-tuning is performed using a small subset of annotated data from new sites. The detector will be available as an open-source tool for researchers to use as the basis for further development of new automated detectors.

The past, present and future of underwater passive acoustic monitoring

We review the history of underwater passive acoustic monitoring and predict the future trajectory. Over the past three decades, advances in digital data storage capacity and low power electronics have made it possible to collect autonomous long-term broadband passive acoustic monitoring data. Concomitant advances have taken place in data analysis and curation. Standardized spectra are an excellent first-step in analysis, calculated for all data using multiple frequency bands. These spectra allow in-situ instrument calibration based on an understanding of underwater ambient noise. Software for efficient manual scanning and signal discovery is used for verification and error estimation. Automatic detectors/classifiers are obtained from both supervised and unsupervised machine learning. Detections are aggregated into a database that allows the combination of multiple datasets and association with environmental or other data. Future work will increasing use of arrays of acoustics sensors, the integration of passive acoustics with other sensors, and machine learning that integrates these data streams to provide better understanding of anthropogenic, biological and physical processes in the ocean.

A primer on terrestrial passive acoustic monitoring data management: Best practices and guidelines

Recent advances in recording technology and data storage capabilities have revolutionized how we monitor vocal animals and their habitats. Recently, there has been an explosion of interest in the use of terrestrial passive acoustic monitoring (PAM) which relies on autonomous acoustic recording units (ARU), but terrestrial PAM studies are limited by a lack of standardized protocols for data collection, analysis, and archiving. Here, we draw on collective experiences of recording, analyzing, and archiving, hundreds of years of PAM data to provide guidelines and recommendations for PAM practitioners. First, we highlight some of the major pitfalls in field data collection, including inappropriate recording settings for the research question and incomplete metadata. We then provide recommendations for data management, including suggestions for backing up, compressing, and archiving the data. Our goal is to provide the community with standardized working guidelines that will help facilitate comparative, large-scale terrestrial studies using PAM.

Artificial light at night (ALAN) pollution alters bat lunar chronobiology: insights from broad-scale long-term acoustic monitoring

BackgroundThe timing of behavior and habitat use of nocturnal animals can be influenced by the lunar cycle in nature. The prevalence of artificial light at night (ALAN) has been recognized as a source of environmental pollution. The interaction between ALAN and the lunar cycle on bat behavior is important for understanding anthropogenic effects on bats. We utilized a decade (2012–2022) of acoustic monitoring data collected in North Carolina, United States, to investigate the relationship between bat activity, lunar cycle, and light pollution. We examined whether the amount of lunar illumination affected species-specific nightly activity and whether hourly bat activity patterns varied between nights with different moon phases. We further investigated if the relationship between bat activity and the lunar cycle might be altered by light pollution.ResultsWe found that seven bat species showed activity variation across nights in relation to the amount of moon illumination when ALAN was absent. In general, bats were less active on full moon nights compared to new moon nights. Light pollution interacted with the bat–lunar relationship in five of the seven species, masking the effect of the lunar cycle. We identified delayed bat activity patterns on nights with a full or waxing moon in seven species, and light pollution altered that pattern in four species. Overall, ALAN was associated with decreased bat activity independent of lunar cycle effects.ConclusionsOur study demonstrated that at a broad spatial scale, ALAN negatively affected many North American temperate bat species and altered their lunar chronobiology. As light pollution is spreading to historically dark areas and habitats, ALAN might couple with other threats, such as the white-nose syndrome or climate change, to cause cascading damage in the environment that depends on ecosystem services such as pest control provided by bats. We argue that further research and conservation actions are needed to mitigate the impact of light pollution.

Identifying important habitat for northern bottlenose and Sowerby's beaked whales in the western North Atlantic

Abstract Understanding habitat requirements for species at risk is crucial for effective conservation management, even though the location and extent of vital habitats may be unknown for rare or elusive species. In the case of marine species, determining important habitat often relies on limited occurrence data or extrapolation from species distribution models (SDMs). SDMs predict habitat by associating species records with environmental variables, assuming a functional ecological relationship. This study focuses on northern bottlenose whales (NBW; Hyperoodon ampullatus) and Sowerby's beaked whales (SBW; Mesoplodon bidens) in the western North Atlantic. As both NBW and SBW are at risk in Canada, the objective was to identify the extent and function of important habitats to guide conservation efforts. The analysis mapped all available geographic occurrence data and used passive acoustic monitoring (PAM) data to inform the development of ensemble SDMs to predict potential habitat and assess the persistence of realized habitat use. Important habitats for NBW and SBW were found primarily concentrated along the continental shelf edges, at an average depth of 1200 m ± 460 SD. All habitat areas support foraging and movement and critical life history functions for both species. The Gully and other submarine canyons off eastern Nova Scotia emerged as important areas for both species, validating the existing Critical Habitat for NBW. However, spatial–temporal patterns diverged on either side of this region. North‐eastern Newfoundland was identified as the next closest area of near‐year‐round presence for NBW, whereas the south‐western Scotian Shelf region, Georges Bank and the Fundian Channel supported persistent foraging by SBW. By integrating multiple data sources (sightings, acoustic detections and SDMs) and demonstrating the temporal persistence of habitat use by NBW and SBW, this study provides valuable insights for identifying, protecting and managing important habitat for beaked whales.

Seasonal acoustic presence of marine mammals at the South Orkney Islands, Scotia Sea.

Increased knowledge about marine mammal seasonal distribution and species assemblage from the South Orkney Islands waters is needed for the development of management regulations of the commercial fishery for Antarctic krill (Euphausia superba) in this region. Passive acoustic monitoring (PAM) data were collected during the autumn and winter seasons in two consecutive years (2016, 2017), which represented highly contrasting environmental conditions due to the 2016 El Niño event. We explored differences in seasonal patterns in marine mammal acoustic presence between the two years in context of environmental cues and climate variability. Acoustic signals from five baleen whale species, two pinniped species and odontocete species were detected and separated into guilds. Although species diversity remained stable over time, the ice-avoiding and ice-affiliated species dominated before and after the onset of winter, respectively, and thus demonstrating a shift in guild composition related to season. Herein, we provide novel information about local marine mammal species diversity, community structure and residency times in a krill hotspot. Our study also demonstrates the utility of PAM data and its usefulness in providing new insights into the marine mammal habitat use and responses to environmental conditions, which are essential knowledge for the future development of a sustainable fishery management in a changing ecosystem.

Diel spatio-temporal patterns of humpback whale singing on a high-density breeding ground.

Humpback whale song chorusing dominates the marine soundscape in Hawai'i during winter months, yet little is known about spatio-temporal habitat use patterns of singers. We analysed passive acoustic monitoring data from five sites off Maui and found that ambient noise levels associated with song chorusing decreased during daytime hours nearshore but increased offshore. To resolve whether these changes reflect a diel offshore-onshore movement or a temporal difference in singing activity, data from 71 concurrently conducted land-based theodolite surveys were analysed. Non-calf pods (n = 3082), presumably including the majority of singers, were found further offshore with increasing time of the day. Separately, we acoustically localized 217 nearshore singers using vector-sensors. During the day, distances to shore and minimum distances among singers increased, and singers switched more between being stationary and singing while travelling. Together, these findings suggest that the observed diel trends in humpback whale chorusing off Maui represent a pattern of active onshore-offshore movement of singers. We hypothesize that this may result from singers attempting to reduce intraspecific acoustic masking when densities are high nearshore and avoidance of a loud, non-humpback, biological evening chorus offshore, creating a dynamic of movement of singers aimed at increasing the efficiency of their acoustic display.

Snowmobile noise alters bird vocalization patterns during winter and pre‐breeding season

Abstract Noise pollution poses a significant threat to ecosystems worldwide, disrupting animal communication and causing cascading effects on biodiversity. In this study, we focus on the impact of snowmobile noise on avian vocalizations during the non‐breeding winter season, a less‐studied area in soundscape ecology. We developed a pipeline relying on deep learning methods to detect snowmobile noise and applied it to a large acoustic monitoring dataset collected in Yellowstone National Park. Our results demonstrate the effectiveness of the snowmobile detection model in identifying snowmobile noise and reveal an association between snowmobile passage and changes in avian vocalization patterns. Snowmobile noise led to a decrease in the frequency of bird vocalizations during mornings and evenings, potentially affecting winter and pre‐breeding behaviours such as foraging, predator avoidance and successfully finding a mate. However, we observed a recovery in avian vocalizations after detection of snowmobiles during mornings and afternoons, indicating some resilience to sporadic noise events. Synthesis and applications: Our findings emphasize the need to consider noise impacts in the non‐breeding season and provide valuable insights for natural resource managers to minimize disturbance and protect critical avian habitats. The deep learning approach presented in this study offers an efficient and accurate means of analysing large‐scale acoustic monitoring data and contributes to a comprehensive understanding of the cumulative impacts of multiple stressors on avian communities.