Bioacoustic sensors, sometimes known as autonomous recording units (ARUs), can record sounds of wildlife over long periods of time in scalable and minimally invasive ways. Deriving per-species ...abundance estimates from these sensors requires detection, classification, and quantification of animal vocalizations as individual acoustic events. Yet, variability in ambient noise, both over time and across sensors, hinders the reliability of current automated systems for sound event detection (SED), such as convolutional neural networks (CNN) in the time-frequency domain. In this article, we develop, benchmark, and combine several machine listening techniques to improve the generalizability of SED models across heterogeneous acoustic environments. As a case study, we consider the problem of detecting avian flight calls from a ten-hour recording of nocturnal bird migration, recorded by a network of six ARUs in the presence of heterogeneous background noise. Starting from a CNN yielding state-of-the-art accuracy on this task, we introduce two noise adaptation techniques, respectively integrating short-term (60 ms) and long-term (30 min) context. First, we apply per-channel energy normalization (PCEN) in the time-frequency domain, which applies short-term automatic gain control to every subband in the mel-frequency spectrogram. Secondly, we replace the last dense layer in the network by a context-adaptive neural network (CA-NN) layer, i.e. an affine layer whose weights are dynamically adapted at prediction time by an auxiliary network taking long-term summary statistics of spectrotemporal features as input. We show that PCEN reduces temporal overfitting across dawn vs. dusk audio clips whereas context adaptation on PCEN-based summary statistics reduces spatial overfitting across sensor locations. Moreover, combining them yields state-of-the-art results that are unmatched by artificial data augmentation alone. We release a pre-trained version of our best performing system under the name of BirdVoxDetect, a ready-to-use detector of avian flight calls in field recordings.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Aim
Ecological data collected by the general public are valuable for addressing a wide range of ecological research and conservation planning, and there has been a rapid increase in the scope and ...volume of data available. However, data from eBird or other large‐scale projects with volunteer observers typically present several challenges that can impede robust ecological inferences. These challenges include spatial bias, variation in effort and species reporting bias.
Innovation
We use the example of estimating species distributions with data from eBird, a community science or citizen science (CS) project. We estimate two widely used metrics of species distributions: encounter rate and occupancy probability. For each metric, we critically assess the impact of data processing steps that either degrade or refine the data used in the analyses. CS data density varies widely across the globe, so we also test whether differences in model performance are robust to sample size.
Main conclusions
Model performance improved when data processing and analytical methods addressed the challenges arising from CS data; however, the degree of improvement varied with species and data density. The largest gains we observed in model performance were achieved with 1) the use of complete checklists (where observers report all the species they detect and identify, allowing non‐detections to be inferred) and 2) the use of covariates describing variation in effort and detectability for each checklist. Occupancy models were more robust to a lack of complete checklists. Improvements in model performance with data refinement were more evident with larger sample sizes. In general, we found that the value of each refinement varied by situation and we encourage researchers to assess the benefits in other scenarios. These approaches will enable researchers to more effectively harness the vast ecological knowledge that exists within CS data for conservation and basic research.
Full text
Available for:
BFBNIB, DOBA, FZAB, GIS, IJS, IZUM, KILJ, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBMB, UILJ, UKNU, UL, UM, UPUK
How do you successfully engage an audience in a citizen-science project? The processes developed by eBird (www.ebird.org), a fast-growing web-based tool that now gathers millions of bird observations ...per month, offers a model.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Citizen science data are increasingly making valuable contributions to ecological studies. However, many citizen science surveys are also designed to encourage wide participation and therefore the ...participants have a range of natural history expertise, leading to variation and potentially bias in the data.
We assessed a recently proposed measure of observer expertise, calculated based on the average numbers of species recorded by observers. We investigated if this observer expertise score is associated with how often an observer reports any individual species. Species reporting rates increased monotonically with the observer's expertise score for 197 of 200 species, suggesting that this expertise score describes inter‐observer variation in the detectability of individual species.
Expertise scores were incorporated into single‐species occupancy models as a covariate, to explain inter‐observer variation in detectability. Including expertise as a detectability covariate led to improved model fit and improved predictive performance on validation data. The expertise score had a large effect on the estimated detectability, comparable in magnitude to the effect of the duration of the observation period.
Expertise scores were also included into single‐species occupancy models that estimated seasonal patterns in species occupancy and seasonal expertise effects. The addition of a seasonal effect of expertise led to improved model fit and increased predictive performance on validation data. The seasonal expertise accounted for bias that may be introduced by seasonal differences in the effect of expertise, caused by changes in the environment or species behaviour.
Measures of observer expertise included in models as a covariate can account for heterogeneity and bias introduced by variable expertise, although in this example the differences in estimated occupancy were small. This method of incorporating observer expertise can be used in any regression model of species occurrence, occupancy, abundance, or density to produce more reliable ecological inference and may be most important where citizen science schemes encourage wide participation. Overall, the results highlight the value of recording observer identity and other detectability covariates, to control for sources of bias associated with the observation process.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK
Citizen science enlists the public in collecting large quantities of data across an array of habitats and locations over long spans of time. Citizen science projects have been remarkably successful ...in advancing scientific knowledge, and contributions from citizen scientists now provide a vast quantity of data about species occurrence and distribution around the world. Most citizen science projects also strive to help participants learn about the organisms they are observing and to experience the process by which scientific investigations are conducted. Developing and implementing public data-collection projects that yield both scientific and educational outcomes requires significant effort. This article describes the model for building and operating citizen science projects that has evolved at the Cornell Lab of Ornithology over the past two decades. We hope that our model will inform the fields of biodiversity monitoring, biological research, and science education while providing a window into the culture of citizen science.
Full text
Available for:
BFBNIB, DOBA, IZUM, KILJ, NMLJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
New technologies are rapidly changing the way we collect, archive, analyze, and share scientific data. For example, over the next several years it is estimated that more than one billion autonomous ...sensors will be deployed over large spatial and temporal scales, and will gather vast quantities of data. Networks of human observers play a major role in gathering scientific data, and whether in astronomy, meteorology, or observations of nature, they continue to contribute significantly. In this paper we present an innovative use of the Internet and information technologies that better enhances the opportunity for citizens to contribute their observations to science and the conservation of bird populations. eBird is building a web-enabled community of bird watchers who collect, manage, and store their observations in a globally accessible unified database. Through its development as a tool that addresses the needs of the birding community, eBird sustains and grows participation. Birders, scientists, and conservationists are using eBird data worldwide to better understand avian biological patterns and the environmental and anthropogenic factors that influence them. Developing and shaping this network over time, eBird has created a near real-time avian data resource producing millions of observations per year.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Migration is a common strategy used by birds that breed in seasonal environments. Selection for greater migration efficiency is likely to be stronger for terrestrial species whose migration ...strategies require non-stop transoceanic crossings. If multiple species use the same transoceanic flyway, then we expect the migration strategies of these species to converge geographically towards the most optimal solution. We test this by examining population-level migration trajectories within the Western Hemisphere for 118 migratory species using occurrence information from eBird. Geographical convergence of migration strategies was evident within specific terrestrial regions where geomorphological features such as mountains or isthmuses constrained overland migration. Convergence was also evident for transoceanic migrants that crossed the Gulf of Mexico or Atlantic Ocean. Here, annual population-level movements were characterized by clockwise looped trajectories, which resulted in faster but more circuitous journeys in the spring and more direct journeys in the autumn. These findings suggest that the unique constraints and requirements associated with transoceanic migration have promoted the spatial convergence of migration strategies. The combination of seasonal atmospheric and environmental conditions that has facilitated the use of similar broad-scale migration strategies may be especially prone to disruption under climate and land-use change.
Full text
Available for:
BFBNIB, NMLJ, NUK, PNG, SAZU, UL, UM, UPUK
Automatic classification of animal vocalizations has great potential to enhance the monitoring of species movements and behaviors. This is particularly true for monitoring nocturnal bird migration, ...where automated classification of migrants' flight calls could yield new biological insights and conservation applications for birds that vocalize during migration. In this paper we investigate the automatic classification of bird species from flight calls, and in particular the relationship between two different problem formulations commonly found in the literature: classifying a short clip containing one of a fixed set of known species (N-class problem) and the continuous monitoring problem, the latter of which is relevant to migration monitoring. We implemented a state-of-the-art audio classification model based on unsupervised feature learning and evaluated it on three novel datasets, one for studying the N-class problem including over 5000 flight calls from 43 different species, and two realistic datasets for studying the monitoring scenario comprising hundreds of thousands of audio clips that were compiled by means of remote acoustic sensors deployed in the field during two migration seasons. We show that the model achieves high accuracy when classifying a clip to one of N known species, even for a large number of species. In contrast, the model does not perform as well in the continuous monitoring case. Through a detailed error analysis (that included full expert review of false positives and negatives) we show the model is confounded by varying background noise conditions and previously unseen vocalizations. We also show that the model needs to be parameterized and benchmarked differently for the continuous monitoring scenario. Finally, we show that despite the reduced performance, given the right conditions the model can still characterize the migration pattern of a specific species. The paper concludes with directions for future research.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
•eBird is a rapidly evolving citizen-science project that meets the needs of a broad user community.•We are developing a novel approach to citizen science based on interdisciplinary collaboration.•We ...have successfully increased data quantity, while maintaining rigorous data quality.•eBird is a major source of avian biodiversity data, now being used across many disciplines.•Feedback and communication from all aspects of the eBird enterprise improve the project’s success.
Citizen-science projects engage volunteers to gather or process data to address scientific questions. But citizen-science projects vary in their ability to contribute usefully for science, conservation, or public policy. eBird has evolved from a basic citizen-science project into a collective enterprise, taking a novel approach to citizen science by developing cooperative partnerships among experts in a wide range of fields: population and distributions, conservation biologists, quantitative ecologists, statisticians, computer scientists, GIS and informatics specialists, application developers, and data administrators. The goal is to increase data quantity through participant recruitment and engagement, but also to quantify and control for data quality issues such as observer variability, imperfect detection of species, and both spatial and temporal bias in data collection. Advances at the interface among ecology, statistics, and computer science allow us to create new species distribution models that provide accurate estimates across broad spatial and temporal scales with extremely detailed resolution. eBird data are openly available and used by a broad spectrum of students, teachers, scientists, NGOs, government agencies, land managers, and policy makers. Feedback from this broad data use community helps identify development priorities. As a result, eBird has become a major source of biodiversity data, increasing our knowledge of the dynamics of species distributions, and having a direct impact on the conservation of birds and their habitats.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK