Bird Detection Research Articles

SMB-YOLOv5: A Lightweight Airport Flying Bird Detection Algorithm Based on Deep Neural Networks

SMB-YOLOv5: A Lightweight Airport Flying Bird Detection Algorithm Based on Deep Neural Networks

Bird Collision Prevention Systems in Passenger Aviation

The purpose of this article is to present the results of a preliminary analysis of modern methods for preventing collisions between birds and aircraft. The focus was in particular on methods that enable defining the level of threat in passenger aviation and existing solutions for eliminating these threats. The first section defines the level of the existing threat of collision with birds for civil aviation on the basis of collision statistics based on collision reports submitted by pilots. The second chapter describes normative documents on methods intended to reduce the risk of collisions with birds, such as aviation rules and regulations, passenger aircraft certification, bird detection and deterrence systems, procedures of flight crews and air traffic controllers, and the development of bird detection and deterrence methods. Based on the analysis of existing solutions, the third chapter proposes a block diagram of an on-board system reducing the risk of aircraft collisions with birds by determining the level of collision risk and transmitting information about the risk level to the flight crew in order to reduce the effect of surprise among pilots, improve the accuracy of the statistics and operational safety by carrying out a technical inspection of the aircraft after the collision. The final chapter contains conclusions.

Audio data compression affects acoustic indices and reduces detections of birds by human listening and automated recognisers

ABSTRACT Increasing popularity in passive acoustic monitoring and the ease with which researchers can accumulate large quantities of acoustic data has resulted in challenges for audio recording storage, archiving, and management. Reductions in file size can be achieved by lowering sample rate and compressing to different formats; however, how these processes affect audio data quality, and the resulting interpretation of wildlife data is not well understood. We investigated the effect of sampling rate and lossy compression of audio recordings to MP3 from their native WAV format on the performance of four commonly applied avian bioacoustic applications: community listening, distance estimation, automated recognition, and acoustic indices. Compression to MP3 decreased the number of detections, including a reduction in total abundance of individuals when transcribing audio files for community listening and lower precision and recall for automated recognisers. Sampling rate reduction introduced systematic bias to acoustic indices and had an influence on precision and recall for recognisers as well. We recommend against the use of MP3 compression to reduce file volume and suggest other lossless forms of audio compression where an exact copy of the original recording can be recovered.

Divergent ecological responses to typhoon disturbance revealed via landscape-scale acoustic monitoring.

Climate change is increasing the frequency, intensity, and duration of extreme weather events across the globe. Understanding the capacity for ecological communities to withstand and recover from such events is critical. Typhoons are extreme weather events that are expected to broadly homogenize ecological dynamics through structural damage to vegetation and longer-term effects of salinization. Given their unpredictable nature, monitoring ecological responses to typhoons is challenging, particularly for mobile animals such as birds. Here, we report spatially variable ecological responses to typhoons across terrestrial landscapes. Using a high temporal resolution passive acoustic monitoring network across 24 sites on the subtropical island of Okinawa, Japan, we found that typhoons elicit divergent ecological responses among Okinawa's diverse terrestrial habitats, as indicated by increased spatial variability of biological sound production (biophony) and individual species detections. This suggests that soniferous communities are capable of a diversity of different responses to typhoons. That is, spatial insurance effects among local ecological communities provide resilience to typhoons at the landscape scale. Even though site-level typhoon impacts on soundscapes and bird detections were not particularly strong, monitoring at scale with high temporal resolution across a broad spatial extent nevertheless enabled detection of spatial heterogeneity in typhoon responses. Further, species-level responses mirrored those of acoustic indices, underscoring the utility of such indices for revealing insight into fundamental questions concerning disturbance and stability. Our findings demonstrate the significant potential of landscape-scale acoustic sensor networks to capture the understudied ecological impacts of unpredictable extreme weather events.

Simultaneous passive acoustic monitoring uncovers evidence of potentially overlooked temporal variation in an Amazonian bird community

The vocal activity and detectability of tropical birds are subject to high levels of temporal heterogeneity, but quantifying patterns of diel and day‐to‐day variation in complex systems is challenging with traditional point count methods. As a result, research concerning stochastic temporal effects on tropical bird assemblages is limited, typically offering only broad conclusions, such as that overall activity is highest in the first few hours of the morning and some species are active at different times of the day. Passive acoustic monitoring introduces several advantages for studying temporal variation, particularly by enabling simultaneous and continuous data collection across adjacent sites. Here, we employed autonomous recording units to quantify temporal variation in bird vocal activity and observed species richness at an Amazonian reserve in Madre de Dios, Peru, a region featuring some of Earth's richest, most complex bird assemblages. We manually annotated 18 dawn hour recordings, collected simultaneously from three separate days at the same six sites, which represent various microhabitats and bird community compositions. We documented significant and consistent temporal variation in avian vocal activity levels and observed species richness within the dawn hour and across days. We found that temporal effects were stronger for vocal activity than for observed species richness and that vocal activity patterns over the course of the dawn hour varied between species. Our results indicate that overlooked temporal variation in Amazonian soundscapes may obfuscate the results of surveys that do not sufficiently account for temporal variables with simultaneous monitoring. While manual analysis of large volumes of soundscape data remains challenging, such data should be collected to supplement traditional surveys whenever possible. Rapid advances in the automated processing of acoustic data could lead to more efficient methods for reducing temporal bias and improving the calibration and accuracy of tropical bird surveys.

Bird Detection on Power Transmission Lines Based on Improved YOLOv7

The safety of transmission lines is essential for ensuring the secure and dependable operation of the power grid. However, the harm caused by birds to transmission lines poses a direct threat to their safe operation. The main challenges in detecting birds on lines is that the detected targets are small, densely packed, and susceptible to environmental interference. We introduce a novel dynamic convolutional kernel specifically designed for detecting small and densely packed targets, the ODconv in the backbone of YOLOv7, to capture richer contextual information and improve performance. The substitution of Alpha_GIoU for CIoU in the original YOLOv7 network model serves to refine the loss function, decrease its parameters, and bolster the network’s resilience. The results confirmed that the proposed YOLOv7 with ODConv reached mAP0.5, mAP0.5:0.95, and precision of up to 78.42%, 46.14%, and 73.56% respectively. In contrast to the base model, the enhanced model demonstrated a 2.58% rise in mAP0.5, a 0.72% improvement in mAP0.5:0.95, and an increased precision of 2.34%.

DeepVision: Enhanced Drone Detection and Recognition in Visible Imagery through Deep Learning Networks.

Drones are increasingly capturing the world's attention, transcending mere hobbies to revolutionize areas such as engineering, disaster aid, logistics, and airport protection, among myriad other fascinating applications. However, there is growing concern about the risks that they pose to physical infrastructure, particularly at airports, due to potential misuse. In recent times, numerous incidents involving unauthorized drones at airports disrupting flights have been reported. To solve this issue, this article introduces an innovative deep learning method proposed to effectively distinguish between drones and birds. Evaluating the suggested approach with a carefully assembled image dataset demonstrates exceptional performance, surpassing established detection systems previously proposed in the literature. Since drones can appear extremely small compared to other aerial objects, we developed a robust image-tiling technique with overlaps, which showed improved performance in the presence of very small drones. Moreover, drones are frequently mistaken for birds due to their resemblances in appearance and movement patterns. Among the various models tested, including SqueezeNet, MobileNetV2, ResNet18, and ResNet50, the SqueezeNet model exhibited superior performance for medium area ratios, achieving higher average precision (AP) of 0.770. In addition, SqueezeNet's superior AP scores, faster detection times, and more stable precision-recall dynamics make it more suitable for real-time, accurate drone detection than the other existing CNN methods. The proposed approach has the ability to not only detect the presence or absence of drones in a particular area but also to accurately identify and differentiate between drones and birds. The dataset utilized in this research was obtained from a real-world dataset made available by a group of universities and research institutions as part of the 2020 Drone vs. Bird Detection Challenge. We have also tested the performance of the proposed model on an unseen dataset, further validating its better performance.

Bird Object Detection: Dataset Construction, Model Performance Evaluation, and Model Lightweighting.

The application of object detection technology has a positive auxiliary role in advancing the intelligence of bird recognition and enhancing the convenience of bird field surveys. However, challenges arise due to the absence of dedicated bird datasets and evaluation benchmarks. To address this, we have not only constructed the largest known bird object detection dataset, but also compared the performances of eight mainstream detection models on bird object detection tasks and proposed feasible approaches for model lightweighting in bird object detection. Our constructed bird detection dataset of GBDD1433-2023, includes 1433 globally common bird species and 148,000 manually annotated bird images. Based on this dataset, two-stage detection models like Faster R-CNN and Cascade R-CNN demonstrated superior performances, achieving a Mean Average Precision (mAP) of 73.7% compared to one-stage models. In addition, compared to one-stage object detection models, two-stage object detection models have a stronger robustness to variations in foreground image scaling and background interference in bird images. On bird counting tasks, the accuracy ranged between 60.8% to 77.2% for up to five birds in an image, but this decreased sharply beyond that count, suggesting limitations of object detection models in multi-bird counting tasks. Finally, we proposed an adaptive localization distillation method for one-stage lightweight object detection models that are suitable for offline deployment, which improved the performance of the relevant models. Overall, our work furnishes an enriched dataset and practice guidelines for selecting suitable bird detection models.

Pairwise Guided Multilayer Cross-Fusion Network for Bird Image Recognition

Bird identification is the first step in collecting data on bird diversity and abundance, which also helps research on bird distribution and population measurements. Most research has built end-to-end training models for bird detection task via CNNs or attentive models, but many perform unsatisfactorily in fine-grained bird recognition. Bird recognition tasks are highly influenced by factors, including the similar appearance of different subcategories, diverse bird postures, and other interference factors such as tree branches and leaves from the background. To tackle this challenge, we propose the Progressive Cross-Union Network (PC-Net) to capture more subtle parts with low-level attention maps. Based on cross-layer information exchange and pairwise learning, the proposed method uses two modules to improve feature representation and localization. First, it utilizes low- and high-level information for cross-layer feature fusion, which enables the network to extract more comprehensive and discriminative features. Second, the network incorporates deep semantic localization to identify and enhance the most relevant regions in the images. In addition, the network is designed with a semantic guidance loss to improve its generalization for variable bird poses. The PC-Net was evaluated on an extensively used birds dataset (CUB-200-2011), which contains 200 birds subcategories. The results demonstrate that the PC-Net achieved an impressive recognition accuracy of 89.2%, thereby outperforming maintained methods in bird subcategory identification. We also achieved competitive results on two other datasets with data on cars and airplanes. The results indicated that the PC-Net improves the accuracy of diverse bird recognition, as well as other fine-grained recognition scenarios.

Automated Wildlife Bird Detection from Drone Footage Using Computer Vision Techniques

Wildlife conservationists have traditionally relied on manual identification and tracking of bird species to monitor populations and identify potential threats. However, many of these techniques may prove to be time-consuming. With the advancement of computer vision techniques, automated bird detection and recognition have become possible. In this manuscript, we present an application of an object-detection model for identifying and tracking wild bird species in natural environments. We used a dataset of bird images captured in the wild and trained the YOLOv4 model to detect bird species with high accuracy. We evaluated the model’s performance on a separate set of test images and achieved an average precision of 91.28%. Our method surpassed the time-consuming nature of manual identification and tracking, allowing for efficient and precise monitoring of bird populations. Through extensive evaluation on a separate set of test images, we demonstrated the performance of our model. Furthermore, our results demonstrated the potential of using YOLOv4 for automated bird detection and monitoring in the wild, which could help conservationists better understand bird populations and identify potential threats.

When can local bird detection radars best complement broad‐scale early‐warning forecasts of risk potential for bird–aircraft strikes as part of an integrated approach to strike mitigation?

Worldwide, wildlife–aircraft strikes cost more than US$1.2 billion in aircraft damage and downtime and jeopardize the safety of aircrews, passengers, and animals. Radar has long been used to monitor flying animal movements and can be a useful tool for strike mitigation. In the USA, the Avian Hazard Advisory System (AHAS) is an early‐warning system that integrates data from next‐generation weather radar (NEXRAD) weather surveillance radars (WSRs) with historic bird occurrence data to quantify avian activity and forecast the relative bird risk within a ~9.3‐km radius of military and civilian airfields. Bird detection radars (BDRs) with both horizontal‐surveillance and vertical‐scanning components are also available for monitoring local avian activity at airports, but we have little information regarding the congruence of broad‐scale warnings and local avian activity where WSRs and BDRs overlap. We quantified trends in biological activity recorded at hourly intervals by a BDR at an airfield in Texas, USA, and in the most frequently assigned AHAS risk forecasts for that site during the same intervals. We then examined the strength of association between these datasets by season and time of day to determine when information from BDRs might best complement forecasts from the broad‐scale AHAS system. We found a strong overall association between the datasets but weak or moderate agreement during daylight periods, when most strikes occur. NEXRAD WSRs see only limited bird activity near the Earth's surface, where the majority of damaging strikes take place and, not surprisingly, AHAS warnings during our study were best predicted by the BDR at higher altitudes. Our results suggest BDRs might best complement early‐warning systems, like AHAS, as part of integrated strike mitigation plans at airfields with large numbers of hazardous birds flying at low altitudes during daylight hours, especially in late afternoon.

EF-TTOA: Development of a UAV Path Planner and Obstacle Avoidance Control Framework for Static and Moving Obstacles

With the increasing applications of unmanned aerial vehicles (UAVs) in surveying, mapping, rescue, etc., the security of autonomous flight in complex environments becomes a crucial issue. Deploying autonomous UAVs in complex environments typically requires them to have accurate dynamic obstacle perception, such as the detection of birds and other flying vehicles at high altitudes, as well as humans and ground vehicles at low altitudes or indoors. This work’s primary goal is to cope with both static and moving obstacles in the environment by developing a new framework for UAV planning and control. Firstly, the point clouds acquired from the depth camera are divided into dynamic and static points, and then the velocity of the point cloud clusters is estimated. The static point cloud is used as the input for the local mapping. Path finding is simplified by identifying key points among static points. Secondly, the design of a trajectory tracking and obstacle avoidance controller based on the control barrier function guarantees security for moving and static obstacles. The path-finding module can stably search for the shortest path, and the controller can deal with moving obstacles with high-frequency. Therefore, the UAV can deal with both long-term planning and immediate emergencies. The framework proposed in this work enables a UAV to operate in a wider field, with better security and real-time performance.

How Many Azores Bullfinches (Pyrrhula murina) Are There in the World? Case Study of a Threatened Species

The Azores bullfinch (Pyrrhula murina Godman, 1866) is a rare Passeriformes endemic from the eastern part of São Miguel Island, Azores, Portugal. This bird was almost considered extinct in the first half of the 20th century, but due to recent conservation measures, it has experienced a recovery since the beginning of the 2000s. Despite the attention given to this bird, the size of its population is still controversial, and the most recent studies present significant divergences on this behalf. The purpose of the present study is to present data from the long-term monitoring and results of the third single-morning survey of the Azores bullfinch to update information about the population size and range of this species. In addition, we performed a literature review to highlight the limitations and advantages of the different approaches for monitoring this species. The Azores Bullfinch records during the single-morning survey indicated a reduction in the extent of occurrence and area of occupancy of this species in comparison with the previous studies, despite the increase in bird detection. However, we suggest that the distribution range of this species needs further analysis concerning its area to exclude non suitable habitats from this analysis. In this study, we conclude that the most likely size of the Azores bullfinch population is 500 to 800 couples, with a slow population growth tendency and an area of distribution of 136.5 km2.

Vision-Based Support for the Detection and Recognition of Drones with Small Radar Cross Sections

Drones are increasingly vital in numerous fields, such as commerce, delivery services, and military operations. Therefore, it is essential to develop advanced systems for detecting and recognizing drones to ensure the safety and security of airspace. This paper aimed to develop a robust solution for detecting and recognizing drones and birds in airspace by combining a radar system and a visual imaging system, and contributed to this effort by demonstrating the potential of combining the two systems for drone detection and recognition. The results showed that this approach was highly effective, with a high overall precision and accuracy of 88.82% and 71.43%, respectively, and the high F1 score of 76.27% indicates that the proposed combination approach has great effectiveness in the performance. The outcome of this study has significant practical implications for developing more advanced and effective drone and bird detection systems. The proposed algorithm is benchmarked with other related works, which show acceptable performance compared with other counterparts.

New insights into the influence of turbines on the behaviour of migrant birds: implications for predicting impacts of offshore wind developments on wildlife

Knowledge of the movement and behaviour of birds and bats around turbines in the offshore marine environment is critical for assessing the environmental impacts of offshore wind developments in the eastern USA. To address the problem of gathering high-quality, long-term data on these species in this remote environment, we designed a multi-sensor system that was recently deployed for 6 months in 2021 and 2022. Two Acoustic and Thermographic Offshore Monitoring (ATOM™) systems were deployed on wind turbines 23 nautical miles off the coast of Virginia, USA. The systems were operational during the day and night and recorded 1,581 detections of birds and bats, with 99% of detections occurring in the fall. Most detections were of birds, including 5 shorebird species, 3 gull species, 1 tern species, 3 raptor species, 1 woodpecker species, and 18 passerine species. Skuas, corvids, and swallows were also observed. There were 521 detections of bats. Differences between species detected and identified in each sensor confirms that a multi-sensor approach for monitoring is beneficial. There were no observed collisions; two individuals (1 bird and 1 bat) suffered air displacement, causing them to fall, but they recovered and continued flying. ATOM also collected novel data on insects, tracking over 7,000 insects around the turbine rotor swept zone and revealed foraging behaviour in 596 of the 1,581 bird and bat detections. Offshore wind turbines thus provide potential sites for perching and foraging. Although these turbine sites provide a new opportunity to feed, which may be beneficial for insectivores and omnivores in enabling them to reach migration destinations in better condition, the consequences of a potentially delayed arrival are unknown (positive, negative, or neutral). Overall, our approach produced the first detailed insights into terrestrial land bird and bat activity around offshore turbines, providing novel information on changes in behaviour when turbine blades are moving and during higher wind speeds. Moreover, our data show that foraging activity appears to be conducted with an awareness of the moving blades and in safe zones close but parallel to blade movements. We recorded 113 observations of activity within 10 m of the moving blades and 70 observations where interactions with moving turbine blades were within 1 m; we call these latter avoidance measures nanoavoidance. No collisions were observed.

Urban landscape-level biodiversity assessments of aquatic and terrestrial vertebrates by environmental DNA metabarcoding

Globally, expansive urbanization profoundly alters natural habitats and the associated biota. Monitoring biodiversity in cities can provide essential information for conservation management, but the complexity of urban landscapes poses serious challenges to conventional observational and capture-based surveys. Here we assessed pan-vertebrate biodiversity, including both aquatic and terrestrial taxa, using environmental DNA (eDNA) sampled from 109 water sites across Beijing, China. Using eDNA metabarcoding with a single primer set (Tele02), we detected 126 vertebrate species, including 73 fish, 39 birds, 11 mammals, and 3 reptiles belonging to 91 genera, 46 families, and 22 orders. The probability of detection from eDNA varied substantially among species and was related to their lifestyle, as shown by the greater detectability of fish compared to that of terrestrial and arboreal (birds and mammals) groups, as well as the greater detectability of water birds compared to that of forest birds (Wilcoxon rank-sum test p = 0.007). Furthermore, the eDNA detection probabilities across all vertebrates (Wilcoxon rank-sum test p = 0.009), as well as for birds (p < 0.001), were higher at lentic sites in comparison with lotic sites. Also, the detected biodiversity was positively correlated with lentic waterbody size for fish (Spearman p = 0.012), but not for other groups. Our results demonstrate the capacity of eDNA metabarcoding to efficiently surveil diverse vertebrate communities across an extensive spatial scale in heterogenous urban landscapes. With further methodological development and optimization, the eDNA approach has great potential for non-invasive, efficient, economic, and timely assessments of biodiversity responses to urbanization, thus guiding city ecosystem conservation management.

Bird Species Identification using Audio Processing and AlexNet Neural Network

This research involved identifying the birds with the help of audio recorded from the real world environment. Most of the methods use images for detection of birds. But, some species may be similar to see. Hence, we took audio as the basis for classification. The audio frequency was plotted as spectrogram and it was inspected to extract the patterns and classify the bird. Legacy practices involved manual inspection of spectrogram that are plotted on the frequency of audio signals. But, this is time taking process and often produces inaccurate results. Hence, we created a computerized process to inspect the spectrogram. The computer learns from patterns of spectrogram during the training process and learns to detect a new and unseen audio. This entire procedure involved two crucial phases. The first stage of the process was to create a dataset with audio files collected from websites like Xeno-canto org that includes all sound recordings of birds. In this research work, we considered 4 species of wood pecker in the Germany region. Hence, we have collected approximately 120 recordings for each species, thus a total of 500 recordings were collected. The collected sounds undergone a series of pre-processing phases like reconstruction, framing, and silence removal, pre-emphasis for removing any noises like human actions, wind sounds, tree sounds. For every processed sound clip, the spectrogram is plotted and it was given as input to a neural network that is in the second stage, which in turn detects the recording at the end. Since the image was given as input, we used Convolutional Neural Network (CNN) which is a best neural net in deep learning for text and image based tasks. The CNN categorizes sound clip and determines the species of bird based on input features. A model was created and put into practice.

Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research

AbstractEcological research and monitoring need to be able to rapidly convey information that can form the basis of scientifically sound management. Automated sensor systems, especially if combined with artificial intelligence, can contribute to such rapid high‐resolution data retrieval. Here, we explore the prospects of automated methods to generate insights for seabirds, which are often monitored for their high conservation value and for being sentinels for marine ecosystem changes. We have developed a system of video surveillance combined with automated image processing, which we apply to common murres Uria aalge. The system uses a deep learning algorithm for object detection (YOLOv5) that has been trained on annotated images of adult birds, chicks and eggs, and outputs time, location, size and confidence level of all detections, frame‐by‐frame, in the supplied video material. A total of 144 million bird detections were generated from a breeding cliff over three complete breeding seasons (2019–2021). We demonstrate how object detection can be used to accurately monitor breeding phenology and chick growth. Our automated monitoring approach can also identify and quantify rare events that are easily missed in traditional monitoring, such as disturbances from predators. Further, combining automated video analysis with continuous measurements from a temperature logger allows us to study impacts of heat waves on nest attendance in high detail. Our automated system thus produces comparable, and in several cases significantly more detailed, data than those generated from observational field studies. By running in real time on the camera streams, it has the potential to supply researchers and managers with high‐resolution up‐to‐date information on seabird population status. We describe how the system can be modified to fit various types of ecological research and monitoring goals and thereby provide up‐to‐date support for conservation and ecosystem management.

Multi-scale temporal characters mining for bird activities based on historical avian radar system datasets

AbstractAvian radar systems are effective for wide-area bird detection and tracking, but application significances need further exploration. Existing radar data mining methods provide long-term functionalities, but they are problematic for bird activity modelling especially in temporal domain. This paper complements this insufficiency by introducing a temporal bird activity extraction and interpretation method. The bird behaviour is quantified as the activity degree which integrates intensity and uncertainty characters with an entropy weighing algorithm. The method is applicable in multiple temporal scales. Historical radar dataset from a system deployed in an airport is adopted for verification. Temporal characters demonstrate good consistency with understandings from local observers and ornithologists. Daily commuting and roosting characters of local birds are well reflected, evening bat activities are also extracted. Night migration activities are demonstrated clearly. Results indicate the proposed method is effective in temporal bird activity modelling and interpretation. Its integration with bird strike risk models might be more useful for airport safety management with wildlife interference.

Joint spatiotemporal models to predict seabird densities at sea

IntroductionSeabirds are abundant, conspicuous members of marine ecosystems worldwide. Synthesis of distribution data compiled over time is required to address regional management issues and understand ecosystem change. Major challenges when estimating seabird densities at sea arise from variability in dispersion of the birds, sampling effort over time and space, and differences in bird detection rates associated with survey vessel type.MethodsUsing a novel approach for modeling seabirds at sea, we applied joint dynamic species distribution models (JDSDM) with a vector-autoregressive spatiotemporal framework to survey data collected over nearly five decades and archived in the North Pacific Pelagic Seabird Database. We produced monthly gridded density predictions and abundance estimates for 8 species groups (77% of all birds observed) within Cook Inlet, Alaska. JDSDMs included habitat covariates to inform density predictions in unsampled areas and accounted for changes in observed densities due to differing survey methods and decadal-scale variation in ocean conditions. ResultsThe best fit model provided a high level of explanatory power (86% of deviance explained). Abundance estimates were reasonably precise, and consistent with limited historical studies. Modeled densities identified seasonal variability in abundance with peak numbers of all species groups in July or August. Seabirds were largely absent from the study region in either fall (e.g., murrelets) or spring (e.g., puffins) months, or both periods (shearwaters).DiscussionOur results indicated that pelagic shearwaters (Ardenna spp.) and tufted puffin (Fratercula cirrhata) have declined over the past four decades and these taxa warrant further investigation into underlying mechanisms explaining these trends. JDSDMs provide a useful tool to estimate seabird distribution and seasonal trends that will facilitate risk assessments and planning in areas affected by human activities such as oil and gas development, shipping, and offshore wind and renewable energy.