Research

Publications

The role of atmospheric conditions in the seasonal dynamics of North American migration flyways

Authors:
Frank A La Sorte, Daniel Fink, Wesley M Hochachka, Andrew Farnsworth, Amanda D Rodewald, Kenneth V Rosenberg, Brian L Sullivan, David W Winkler, Chris Wood, Steve Kelling
Date:
2014
Publication:
Journal of Biogeography
Abstract:
Avian migration strategies balance the costs and benefits of annual movements between breeding and wintering grounds. If similar constraints affect a large numbers of species, geographical concentrations of migration routes, or migration flyways, may result. Here we provide the first population-level empirical evaluation of the structure and seasonal dynamics of migration flyways for North American terrestrial birds and their association with atmospheric conditions.

We modelled weekly probability of occurrence for 93 migratory species using spatio-temporal exploratory models and eBird occurrence data for the combined period 2004 to 2011. We used hierarchical cluster analysis to identify species with shared migration routes based on normalized spatio-temporal representations of autumn migration. We summarized atmospheric conditions within flyways using nocturnal wind velocity and bearing estimated at three isobaric levels (725, 825 and 925 mbar) for the combined period 2008 to 2011.
Results

We identified three migration flyways: an eastern and western flyway whose paths shifted westwards in the spring, and a central flyway whose core boundaries overlapped with the eastern flyway and whose width was more constricted in the autumn. The seasonal shift of the eastern flyway created potentially longer migration journeys in the spring, but this longer route coincides with a low-level jet stream that may enhance migration speeds. Atmospheric conditions appeared to have a more limited role in the seasonal dynamics of the western flyway.
Main conclusions

Migration routes for terrestrial species in North America can be organized into three broadly defined migration flyways: a geographically distinct flyway located west of the 103rd meridian and two interrelated flyways located east of the 103rd meridian. Seasonal shifts in flyway locations reflect the influence of looped migration strategies that for the eastern flyway can be explained by the trade-off between minimizing total migration distance while maintaining an association with favourable atmospheric conditions.
Online:
http://onlinelibrary.wiley.com/doi/10.1111/jbi.12328/full

Migration timing and its determinants for nocturnal migratory birds during autumn migration

Authors:
Frank A La Sorte, Wesley M Hochachka, Andrew Farnsworth, Daniel Sheldon, Daniel Fink, Jeffrey Geevarghese, Kevin Winner, Benjamin M Van Doren, Steve Kelling
Date:
2015
Publication:
Journal of Animal Ecology
Abstract:
Summary
1. Migration is a common strategy used by birds that breed in seasonal environments, and multiple environmental and biological factors determine the timing of migration. How these factors operate in combination during autumn migration, which is considered to be under weaker time constraints relative to spring migration, is not clear.
2. Here, we examine the patterns and determinants of migration timing for nocturnal migrants during autumn migration in the north-eastern USA using nocturnal reflectivity data from 12 weather surveillance radar stations and modelled diurnal probability of occurrence for 142 species of nocturnal migrants. We first model the capacity of seasonal atmospheric conditions (wind and precipitation) and ecological productivity (vegetation greenness) to predict autumn migration intensity. We then test predictions, formulated under optimal migration theory, on how migration timing should be related to assemblage-level estimates of body size and total migration distance within the context of dietary guild (insectivore and omnivore) and level of dietary plasticity during autumn migration.
3. Our results indicate seasonal declines in ecological productivity delineate the beginning and end of peak migration, whose intensity is best predicted by the velocity of winds at migration altitudes. Insectivorous migrants departed earlier in the season and, consistent with our predictions, large-bodied and long-distance insectivorous migrants departed the earliest. Contrary to our predictions, large-bodied and some long-distance omnivorous migrants departed later in the season, patterns that were replicated in part by insectivorous migrants that displayed dietary plasticity during autumn migration.
4. Our findings indicate migration timing in the region is dictated by optimality strategies, modified based on the breadth and flexibility of migrant's foraging diets, with declining ecological productivity defining possible resource thresholds during which migration occurs when winds at migration altitudes are mild. These observations provide the basis to assess how avian migration strategies may be affected by adjustments in seasonal patterns of atmospheric circulation and ecological productivity that may occur under global climate change.
Online:
http://onlinelibrary.wiley.com/doi/10.1111/1365-2656.12376/full

A comparison of similarity-based approaches in the classification of flight calls of four species of North American wood-warblers (Parulidae)

Authors:
Sara Keen, Jesse C Ross, Emily T Griffiths, Michael Lanzone, Andrew Farnsworth
Date:
2014
Publication:
Ecological Informatics
Abstract:
Numerous methods are available for analysis of avian vocalizations, but few research efforts have compared recent methods for calculating and evaluating similarity among calls, particularly those collected in the field. This manuscript compares a suite of methodologies for analyzing flight calls of New World warblers, investigating the effectiveness of four techniques for calculating call similarity: (1) spectrographic cross-correlation, (2) dynamic time warping, (3) Euclidean distance between spectrogram-based feature measurements, and (4) random forest distance between spectrogram-based feature measurements. We tested these methods on flight calls, which are short, structurally simple vocalizations typically used during nocturnal migration, as these signals may contain important ecological or demographic information. Using the four techniques listed above, we classified flight calls from three datasets, one collected from captive birds and two collected from wild birds in the field. Each dataset contained an equal number of calls from four warbler species commonly recorded during acoustic monitoring: American Redstart, Chestnut-sided Warbler, Hooded Warbler, and Ovenbird. Using captive recordings to train the classification models, we created four similarity-based classifiers which were then tested on the captive and field datasets. We show that these classification methods are limited in their ability to successfully classify the calls of these warbler species, and that classification accuracy was lower on field recordings than captive recordings for each of the tested methods. Of the four methods we compared, the random forest technique had the highest classification accuracy, enabling correct classification of 67.6% of field recordings. To compare the performance of the automated techniques to manual classification, the most common method used in flight call research, human experts were also asked to classify calls from each dataset. The experts correctly classified approximately 90% of field recordings, indicating that although the automated techniques are faster, they remain less accurate than manual classification. However, because of the challenges inherent to these data, such as the structural similarity among the flight calls of focal species and the presence of environmental noise in the field recordings, some of the tested automated classification techniques may be acceptable for real-world applications. We believe that this comparison of broadly applicable methodologies provides information that will prove to be useful for analysis, detection and classification of short duration signals. Based on our results, we recommend that a combination of feature measurements and random forest classification can be used to assign flight calls to species, while human experts oversee the process.
Online:
http://www.sciencedirect.com/science/article/pii/S1574954114000028

Seasonal changes in the altitudinal distribution of nocturnally migrating birds during autumn migration

Authors:
Frank A La Sorte, Wesley M Hochachka, Andrew Farnsworth, Daniel Sheldon, Benjamin M Van Doren, Daniel Fink, Steve Kelling
Date:
2015
Publication:
Royal Society Open Science
Abstract:
Wind plays a significant role in the flight altitudes selected by nocturnally migrating birds. At mid-latitudes in the Northern Hemisphere, atmospheric conditions are dictated by the polar-front jet stream, whose amplitude increases in the autumn. One consequence for migratory birds is that the region’s prevailing westerly winds become progressively stronger at higher migration altitudes. We expect this seasonality in wind speed to result in migrants occupying progressively lower flight altitudes, which we test using density estimates of nocturnal migrants at 100 m altitudinal intervals from 12 weather surveillance radar stations located in the northeastern USA. Contrary to our expectations, median migration altitudes deviated little across the season, and the variance was lower during the middle of the season and higher during the beginning and especially the end of the season. Early-season migrants included small- to intermediate-sized long-distance migrants in the orders Charadriiformes and Passeriformes, and late-season migrants included large-bodied and intermediate-distance migrants in the order Anseriformes. Therefore, seasonality in the composition of migratory species, and related variation in migration strategies and behaviours, resulted in a convex–concave bounded distribution of migration altitudes. Our results provide a basis for assessing the implications for migratory bird populations of changes in mid-latitude atmospheric conditions probably occurring under global climate change.
Online:
http://rsos.royalsocietypublishing.org/content/2/12/150347.abstract

Warmer Summers and Drier Winters Correlate with More Winter Vagrant Purple Gallinules (Porphyrio martinicus) in the North Atlantic Region

Authors:
Andrew Farnsworth, Frank A La Sorte, Marshall J Iliff
Date:
2015
Publication:
The Wilson Journal of Ornithology
Abstract:
Individuals from a diverse array of bird species sometimes occur well outside of their historic distributions. These vagrants, and their patterns of occurrence, may yield valuable insights regarding how birds respond to environmental change. Among the Rallidae, which are champion dispersers, the Purple Gallinule (Porphyrio martinicus) disperses exceptionally long distances. Whereas most Purple Gallinule vagrants occur from April to October, a much smaller number of records represent a more enigmatic vagrancy pattern that occurs from November to February. Using eBird, a global bird-monitoring project, we compiled 77 occurrences of vagrant Purple Gallinules from 1957–2014 during this seasonal window and examined how those occurrences correlated with environmental conditions and population trends. Average temperature anomalies showed significant correlations with patterns of records, with warmer late summer temperatures in particular in Florida and Puerto Rico correlating with more vagrants. Drier conditions in eastern Mexico, especially during winter, showed similar significant relationships. Our results indicate the potential utility of studying vagrants to understand relationships between bird populations and environmental changes, and more importantly highlight the potential for understanding how vagrancy may relate to changes in this species’ distribution under new climate regimes.
Online:
http://www.wjoonline.org/doi/abs/10.1676/14-086.1

Collaborative Research: Nocturnally migrating songbirds drift when they can and compensate when they must

Authors:
Kyle G Horton, Benjamin M Van Doren, Phillip M Stepanian, Wesley M Hochachka, Andrew Farnsworth, Jeffrey F Kelly
Date:
2016
Publication:
Scientific Reports
Abstract:
The shortest possible migratory route for birds is not always the best route to travel. Substantial research effort has established that birds in captivity are capable of orienting toward the direction of an intended goal, but efforts to examine how free-living birds use navigational information under conditions that potentially make direct flight toward that goal inefficient have been limited in spatiotemporal scales and in the number of individuals observed because of logistical and technological limitations. Using novel and recently developed techniques for analysis of Doppler polarimetric weather surveillance radar data, we examined two impediments for nocturnally migrating songbirds in eastern North America following shortest-distance routes: crosswinds and oceans. We found that migrants in flight often drifted sideways on crosswinds, but most strongly compensated for drift when near the Atlantic coast. Coastal migrants’ tendency to compensate for wind drift also increased through the night, while no strong temporal differences were observed at inland sites. Such behaviors suggest that birds migrate in an adaptive way to conserve energy by assessing while airborne the degree to which they must compensate for wind drift.
Online:
http://www.nature.com/articles/srep21249

Wind drift explains the reoriented morning flights of songbirds

Authors:
Benjamin M Van Doren, Kyle G Horton, Phillip M Stepanian, David S Mizrahi, Andrew Farnsworth
Date:
2016
Publication:
Behavioral Ecology
Abstract:
Remote sensors such as Doppler radars are providing novel insights into the migrations of diverse animal taxa, but limits in scope and sensitivity can hamper the utility of these tools. For example, studies investigating whether songbirds compensate effectively for wind displacement during nocturnal migration have been challenged by the need to assess behavior on a large scale. In addition, these studies typically overlook the potential role low-altitude diurnal flights play in dealing with unfavorable winds. In such cases, a combination of approaches—new and traditional—may be necessary to understand behavior more completely. Here, we unite ground-based visual observations with a new radar analysis method to investigate how songbirds deal with crosswinds over the northeast United States. We find that nocturnally migrating birds experienced significant wind drift, even though they often flew at 90° or more to the wind direction. Significantly, more birds undertook reoriented diurnal flights after nocturnal wind drift, and wind influence, nocturnal migration intensity, and time of season together explained the majority of variation in counts of these “morning flights.” This study shows that bird behavior during migration can be strongly shaped by the danger of wind drift and that some songbird species respond to drift with reoriented diurnal migratory flights. Knowledge of birds’ interactions with wind is essential for successfully modeling migratory behavior and assessing the risks associated with changing habitats and meteorological patterns. Furthermore, an understanding of the degree to which drift defines migratory behaviors may have value across animal taxa.
Online:
http://beheco.oxfordjournals.org/content/early/2016/02/27/beheco.arw021.short

The implications of mid‐latitude climate extremes for North American migratory bird populations

Authors:
Frank A La Sorte, Wesley M Hochachka, Andrew Farnsworth, André A Dhondt, Daniel Sheldon
Date:
2016
Publication:
Ecosphere
Abstract:
Mid-latitude climate extremes are projected to increase in frequency under global climate change. How this may affect migratory bird populations is not well understood. The mid-latitudes of North America experienced an extreme warming event during March 2012 that advanced the spring phenology of ecological productivity, resulting in lower levels of productivity during the summer. Here, we test the predictions that: (1) short-distance migratory birds, due to geographic proximity and more flexible migratory behavior, should advance their spring migration phenology; and (2) breeding populations, due to lower summer productivity, should have reduced occurrences. We used occurrence data for 353 bird species from the eBird database to calculate weekly occurrence anomalies for 2012 relative to the 2010–2014 average. We identified species having unusually large positive occurrence anomalies during March 2012 and species having unusually large negative occurrence anomalies during July–August 2012. For each category, we summarized migration strategies, geographic distributions, and annual associations with temperature and ecological productivity. Short-distance migrants whose winter and breeding ranges intersect the mid-latitudes advanced their spring migration phenology during March (n = 21). Long-distance migrants whose winter and breeding distributions were weakly associated with the mid-latitudes had lower occurrences during the summer (n = 32). Five species were shared between the two categories. Within species’ winter ranges, temperature and ecological productivity were higher than expected during March; within species’ breeding ranges, ecological productivity was lower than expected during the summer. These differences were strongest for the 21 short-distance migrants. Following our expectations, mid-latitude climate extremes and associated ecological consequences broadly affected avian migration and breeding activities within the region. Our findings suggest short-distance migrants are more flexible and resilient, whereas populations of long-distance migrants are at a distinct disadvantage, which may intensify if the frequency of these events increases.
Online:
http://onlinelibrary.wiley.com/doi/10.1002/ecs2.1261/full

A characterization of autumn nocturnal migration detected by weather surveillance radars in the northeastern USA

Authors:
Andrew Farnsworth, Benjamin M. Van Doren, Wesley M. Hochachka, Daniel Sheldon, Kevin Winner, Jed Irvine, Jeffrey Geevarghese, Steve Kelling
Date:
2016
Publication:
Ecological Application
Abstract:
Billions of birds migrate at night over North America each year. However, few studies have described the phenology of these movements, such as magnitudes, directions, and speeds, for more than one migration season and at regional scales. In this study, we characterize density, direction, and speed of nocturnally migrating birds using data from 13 weather surveillance radars in the autumns of 2010 and 2011 in the northeastern USA. After screening radar data to remove precipitation, we applied a recently developed algorithm for characterizing velocity profiles with previously developed methods to document bird migration. Many hourly radar scans contained windborne “contamination,” and these scans also exhibited generally low overall reflectivities. Hourly scans dominated by birds showed nightly and seasonal patterns that differed markedly from those of low reflectivity scans. Bird migration occurred during many nights, but a smaller number of nights with large movements of birds defined regional nocturnal migration. Densities varied by date, time, and location but peaked in the second and third deciles of night during the autumn period when the most birds were migrating. Migration track (the direction to which birds moved) shifted within nights from south-southwesterly to southwesterly during the seasonal migration peaks; this shift was not consistent with a similar shift in wind direction. Migration speeds varied within nights, although not closely with wind speed. Airspeeds increased during the night; groundspeeds were highest between the second and third deciles of night, when the greatest density of birds was migrating. Airspeeds and groundspeeds increased during the fall season, although groundspeeds fluctuated considerably with prevailing winds. Significant positive correlations characterized relationships among bird densities at southern coastal radar stations and northern inland radar stations. The quantitative descriptions of broadscale nocturnal migration patterns presented here will be essential for biological and conservation applications. These descriptions help to define migration phenology in time and space, fill knowledge gaps in avian annual cycles, and are useful for monitoring long-term population trends of migrants. Furthermore, these descriptions will aid in assessing potential risks to migrants, particularly from structures with which birds collide and artificial lighting that disorients migrants.
Online:
http://onlinelibrary.wiley.com/doi/10.1890/15-0023/abstract

Can Nocturnal Flight Calls of the Migrating Songbird, American Redstart, Encode Sexual Dimorphism and Individual Identity?

Authors:
Emily T Griffiths, Sara C Keen, Michael Lanzone, Andrew Farnsworth
Date:
2016
Publication:
PLoS ONE
Abstract:
Bird species often use flight calls to engage in social behavior, for instance maintain group cohesion and to signal individual identity, kin or social associations, or breeding status of the caller. Additional uses also exist, in particular among migrating songbirds for communication during nocturnal migration. However, our understanding of the information that these vocalizations convey is incomplete, especially in nocturnal scenarios. To examine whether information about signaler traits could be encoded in flight calls we quantified several acoustic characteristics from calls of a nocturnally migrating songbird, the American Redstart. We recorded calls from temporarily captured wild specimens during mist-netting at the Powdermill Avian Research Center in Rector, PA. We measured call similarity among and within individuals, genders, and age groups. Calls from the same individual were significantly more similar to one another than to the calls of other individuals, and calls were significantly more similar among individuals of the same sex than between sexes. Flight calls from hatching-year and after hatching-year individuals were not significantly different. Our results suggest that American Redstart flight calls may carry identifiers of gender and individual identity. To our knowledge, this is the first evidence of individuality or sexual dimorphism in the flight calls of a migratory songbird. Furthermore, our results suggest that flight calls may have more explicit functions beyond simple group contact and cohesion. Nocturnal migration may require coordination among numerous individuals, and the use of flight calls to transmit information among intra- and conspecifics could be advantageous. Applying approaches that account for such individual and gender information may enable more advanced research using acoustic monitoring.
Online:
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0156578

Collaborative Research: Innovative Visualizations Shed Light on Avian Nocturnal Migration

Authors:
Judy Shamoun-Baranes*, Andrew Farnsworth*, Bart Aelterman, Jose A Alves, Kevin Azijn, Garrett Bernstein, Sérgio Branco, Peter Desmet, Adriaan M Dokter, Kyle Horton, Steve Kelling, Jeffrey F Kelly, Hidde Leijnse, Jingjing Rong, Daniel Sheldon, Wouter Van den Broeck, Jan Klaas Van Den Meersche, Benjamin Mark Van Doren, Hans van Gasteren
Date:
2016
Publication:
PLoS ONE
Abstract:
Globally, billions of flying animals undergo seasonal migrations, many of which occur at night. The temporal and spatial scales at which migrations occur and our inability to directly observe these nocturnal movements makes monitoring and characterizing this critical period in migratory animals’ life cycles difficult. Remote sensing, therefore, has played an important role in our understanding of large-scale nocturnal bird migrations. Weather surveillance radar networks in Europe and North America have great potential for long-term low-cost monitoring of bird migration at scales that have previously been impossible to achieve. Such long-term monitoring, however, poses a number of challenges for the ornithological and ecological communities: how does one take advantage of this vast data resource, integrate information across multiple sensors and large spatial and temporal scales, and visually represent the data for interpretation and dissemination, considering the dynamic nature of migration? We assembled an interdisciplinary team of ecologists, meteorologists, computer scientists, and graphic designers to develop two different flow visualizations, which are interactive and open source, in order to create novel representations of broad-front nocturnal bird migration to address a primary impediment to long-term, large-scale nocturnal migration monitoring. We have applied these visualization techniques to mass bird migration events recorded by two different weather surveillance radar networks covering regions in Europe and North America. These applications show the flexibility and portability of such an approach. The visualizations provide an intuitive representation of the scale and dynamics of these complex systems, are easily accessible for a broad interest group, and are biologically insightful. Additionally, they facilitate fundamental ecological research, conservation, mitigation of human–wildlife conflicts, improvement of meteorological products, and public outreach, education, and engagement.
Online:
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0160106

Collaborative research: Seasonal differences in landbird migration strategies

Authors:
Kyle G Horton, Benjamin M Van Doren, Phillip M Stepanian, Andrew Farnsworth, Jeffrey F Kelly
Date:
2016
Publication:
Auk
Abstract:
Migrating birds make strategic decisions at multiple temporal and spatial scales. They must select flight altitudes, speeds, and orientations in order to maintain preferred directions of movement and to minimize energy expenditure and risk. Spring flights follow a rapid phenology, but how this rapid transit translates to in-flight decisions is not clear. We described flight strategies of nocturnally migrating landbirds using 6 weather surveillance radars during spring (2013–2015) and fall (2013–2014) migratory periods in the eastern United States to investigate seasonal decision-making patterns and how climate change may influence these trends. During spring, we found groundspeed and airspeed of migrants to be significantly higher than those of fall migrants; compensation for wind drift was also significantly greater during spring. Our results indicate that birds make more rapid and precise flights in spring that are only partially explained by meteorological phenomena. Future applications at greater spatial scales will allow direct comparisons of in-flight behaviors with predictions from migration theory.
Online:
http://www.aoucospubs.org/doi/abs/10.1642/AUK-16-105.1

Detecting Migrating Birds at Night

Authors:
Jia-Bin Huang, Rich Caruana, Andrew Farnsworth, Steve Kelling, and Narendra Ahuja
Date:
2016
Publication:
Conference on Computer Vision and Pattern Recognition
Abstract:
Bird migration is a critical indicator of environmental health, biodiversity, and climate change. Existing techniques for monitoring bird migration are either expensive (e.g., satellite tracking), labor-intensive (e.g., moon watching), indirect and thus less accurate (e.g., weather radar), or intrusive (e.g., attaching geolocators on captured birds). In this paper, we present a vision-based system for detecting migrating birds in flight at night. Our system takes stereo videos of the night sky as inputs, detects multiple flying birds and estimates their orientations, speeds, and altitudes. The main challenge lies in detecting flying birds of unknown trajectories under high noise level due to the low-light environment. We address this problem by incorporating stereo constraints for rejecting physically implausible configurations and gathering evidence from two (or more) views. Specifically, we develop a robust stereo-based 3D line fitting algorithm for geometric verification and a deformable part response accumulation strategy for trajectory verification. We demonstrate the effectiveness of the proposed approach through quantitative evaluation of real videos of birds migrating at night collected with near-infrared cameras.
Download:
Bird_CVPR_2016.pdf
Online:
http://cvpr2016.thecvf.com

Autumn morning flights of migrant songbirds in the northeastern United States are linked to nocturnal migration and winds aloft

Authors:
Benjamin M. Van Doren, Daniel Sheldon, Jeffrey Geevarghese, Wesley M. Hochachka, and Andrew Farnsworth
Date:
2015
Publication:
The Auk
Abstract:
Many passerines that typically migrate at night also engage in migratory flights just after sunrise. These widely observed “morning flights” often involve birds flying in directions other than those aimed toward their ultimate destinations, especially in coastal areas. Morning flights have received little formal investigation, and their study may improve our understanding of how birds orient themselves during and after nocturnal movements and how they use stopover habitat. We studied autumn morning flights in the northeastern United States to identify associations between the number of birds undertaking morning flights and the magnitude of nocturnal migratory movements, nocturnal winds, and local topography. Our analyses included observations of more than 15,000 passerines at 7 locations. We found positive relationships between morning flight size and nocturnal migration density and winds aloft: Significantly more birds flew following larger nocturnal movements, quantified from weather surveillance radar and recordings of nocturnal flight calls, and after stronger nocturnal crosswinds. We also found consistent differences in morning flight size and direction among sites. These patterns are consistent with migrants engaging in morning flight as a corrective measure following displacement by nocturnal winds and to search for suitable stopover habitat.
Download:
Van-Doren-et-al.-2015-Auk1.pdf
Online:
http://www.aoucospubs.org/doi/full/10.1642/AUK-13-260.1

Reconstructing Velocities of Migrating Birds from Weather Radar – A Case Study in Computational Sustainability

Authors:
Andrew Farnsworth, Daniel Sheldon, Jeffrey Geevarghese, Jed Irvine, Benjamin Van Doren, Kevin Webb, Thomas G Dietterich, and Steve Kelling
Date:
2014
Publication:
AI Magazine
Abstract:
Bird migration occurs at the largest of global scales, but monitoring such movements can be challenging. In the US there is an operational network of weather radars providing freely accessible data for monitoring meteorological phenomena in the atmosphere. Individual radars are sensitive enough to detect birds, and can provide insight into migratory behaviors of birds at scales that are not possible using other sensors. Archived data from the WSR-88D network of US weather radars hold valuable and detailed information about the continent-scale migratory movements of birds over the last 20 years. However, significant technical challenges must be overcome to understand this information and harness its potential for science and conservation. We describe recent work on an AI system to quantify bird migration using radar data, which is part of the larger BirdCast project to model and forecast bird migration at large scales using radar, weather, and citizen science data.
Download:
DietterichThomasElectricalEngineeringComputerScienceReconstructingVelocitiesMigrating.pdf
Online:
http://ir.library.oregonstate.edu/xmlui/bitstream/handle/1957/52353/DietterichThomasElectricalEngineeringComputerScienceReconstructingVelocitiesMigrating.pdf?sequence=1

Approximate Bayesian Inference for Reconstructing Velocities of Migrating Birds from Weather Radar

Authors:
SHELDON, D.; FARNSWORTH, A.; IRVINE, J.; VAN DOREN, B.; WEBB, K.; DIETTERICH, T.; and KELLING, S.
Date:
2013
Publication:
AAAI Conference on Artificial Intelligence, North America, jun. 2013.
Abstract:
Archived data from the WSR-88D network of weather radars in the US hold detailed information about the continent-scale migratory movements of birds over the last 20 years. However, significant technical challenges must be overcome to understand this information and harness its potential for science and conservation. We present an approximate Bayesian inference algorithm to reconstruct the velocity fields of birds migrating in the vicinity of a radar station. This is part of a larger project to quantify bird migration at large scales using weather radar data.
Download:
Approximate-Bayesian-Inference-for-Reconstructing-Velocities-of-Migrating-Birds-from-Weather-Radar.pdf
Online:
http://www.aaai.org/ocs/index.php/AAAI/AAAI13/paper/view/6468

Collective Graphical Models

Authors:
Sheldon, D., and T.G. Dietterich
Date:
2012
Publication:
Neural Information Processing Systems (NIPS), Grenada, Spain 12-15 December 2011
Abstract:
There are many settings in which we wish to fit a model of the behavior of individuals but where our data consist only of aggregate information (counts or low-dimensional contingency tables). This paper introduces Collective Graphical Models—a framework for modeling and probabilistic inference that operates directly on the sufficient statistics of the individual model. We derive a highly-efficient Gibbs sampling algorithm for sampling from the posterior distribution of the sufficient statistics conditioned on noisy aggregate observations, prove its correctness, and demonstrate its effectiveness experimentally.
Download:
Collective-Graphical-Models.pdf
Online:
http://people.cs.umass.edu/~sheldon/papers/cgm-single-file.pdf
Toggle Grid