An official website of the United States government
Abstract The exodus of flying animals from their roosting locations is often visible as expanding ring‐shaped patterns in weather radar data. The NEXRAD network, for example, archives more than 25 years of data across 143 contiguous US radar stations, providing opportunities to study roosting locations and times and the ecosystems of birds and bats. However, access to this information is limited by the cost of manually annotating millions of radar scans. We develop and deploy an AI‐assisted system to annotate roosts in radar data. We build datasets with roost annotations to support the training and evaluation of automated detection models. Roosts are detected, tracked, and incorporated into our developed web‐based interface for human screening to produce research‐grade annotations. We deploy the system to collect swallow and martin roost information from 12 radar stations around the Great Lakes spanning 21 years. After verifying the practical value of the system, we propose to improve the detector by incorporating both spatial and temporal channels from volumetric radar scans. The deployment on Great Lakes radar scans allows accelerated annotation of 15 628 roost signatures in 612 786 radar scans with 183.6 human screening hours, or 1.08 s per radar scan. We estimate that the deployed system reduces human annotation time by ~7×. The temporal detector model improves the average precision at intersection‐over‐union threshold 0.5 (APIoU = .50) by 8% over the previous model (48%→56%), further reducing human screening time by 2.3× in its pilot deployment. These data contain critical information about phenology and population trends of swallows and martins, aerial insectivore species experiencing acute declines, and have enabled novel research. We present error analyses, lay the groundwork for continent‐scale historical investigation about these species, and provide a starting point for automating the detection of other family‐specific phenomena in radar data, such as bat roosts and mayfly hatches.
more »
« less
Long‐term analysis of persistence and size of swallow and martin roosts in the US Great Lakes
Abstract In this study, we combined a machine learning pipeline and human supervision to identify and label swallow and martin roost locations on data captured from 2000 to 2020 by 12 Weather Surveillance Radars in the Great Lakes region of the US. We employed radar theory to extract the number of birds in each roost detected by our technique. With these data, we set out to investigate whether roosts formed consistently in the same geographic area over two decades and whether consistency was also predictive of roost size. We used a clustering algorithm to group individual roost locations into 104 high‐density regions and extracted the number of years when each of these regions was used by birds to roost. In addition, we calculated the overall population size and analyzed the daily roost size distributions. Our results support the hypothesis that more persistent roosts are also gathering more birds, but we found that on average, most individuals congregate in roosts of smaller size. Given the concentrations and consistency of roosting of swallows and martins in specific areas throughout the Great Lakes, future changes in these patterns should be monitored because they may have important ecosystem and conservation implications.
more »
« less
- PAR ID:
- 10418976
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Remote Sensing in Ecology and Conservation
- ISSN:
- 2056-3485
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract During their nonbreeding period, many species of swallows and martins (family: Hirundinidae) congregate in large communal roosts. Some of these roosts are well-known within local birdwatching communities; however, monitoring them at large spatial scales and with day-to-day temporal resolution is challenging. Community-science platforms such as the Purple Martin Conservation Association’s project MartinRoost and eBird have addressed some of these challenges by centralizing data collected from regional communities. Additionally, due to the high densities of birds within these aggregations, their early morning dispersals are systematically detected by weather radars, which have also been used to collect data about roost timing and location. An important issue, however, limits spatiotemporal scope of previous radar-based studies: finding the roost signatures on millions of rendered reflectivity images is extremely time-consuming. Recent advances in computer vision, however, have allowed us to reduce this effort. The rise of this technology makes it necessary that we assess whether our biological definition of a roost matches what the machine-learning models are capturing. We do so by comparing eBird detections of roosts in the Great Lakes region with those obtained by a human-supervised machine-learning model from 2000 to 2022. With more than two decades of data, we assess the ability of these two tools to detect roosts on a day-to-day basis, and we compare the phenology of dispersals to investigate whether radar detections correspond to swallow and martin roosts or if they are associated with other well-known birds that form large aggregations. Our comparison of these datasets strongly suggests that swallows and martins are responsible for the dispersals we observe on the radars from July to late September; however, the alternative species we examined could be causing some of the detections in October.more » « less
-
ABSTRACT Many species of swallows and martins congregate in large nonbreeding aggregations throughout the Americas. These roosts typically occur for several days to weeks in the same place during the same time of the year and disappear suddenly as the birds continue their migratory journeys. In the Amazon Rainforest, however, there are reports of large communal roosts of varying species composition throughout the year. Due to the high biomass density of these aggregations, we can systematically observe these tropical roosts using data collected by the operational S‐band Doppler weather radar located in Manaus (3°08′56.0″ S, 59°59′29.1″ W) Using data collected by this radar over 2 years (2014, 2015), we describe the temporal and spatial patterns of roost size in the Amazon Rainforest, and compare it to a similar dataset collected in the Great Lakes region of North America, where swallows and martins form pre‐migratory roosts. Our findings confirm that roosting activity occurs throughout the year in the region around Manaus, and thus likely gather multiple species of swallows and martins. The peak of roosting activity in both years occurred from January to May, when observations on the ground suggest that roosts are predominantly Purple Martin aggregations. We found that the average daily number of birds in roosts in Manaus in 2015 is up to 7 times larger than what was observed in the Great Lakes, even though the area of the latter is 8.7 times larger than the area sampled around Manaus. Our findings highlight the significance of the Amazon Rainforest for swallow and martin populations. Because this region hosts migrating individuals from the Nearctic‐Neotropical and the Austral migratory systems, resident species may share these roosts with populations from both systems during separate times of the year, creating an indirect link between the two poles of the Americas.more » « less
-
Predicting the spatial occurrence of wildlife is a major challenge for ecology and management. In Latin America, limited knowledge of the number and locations of vampire bat roosts precludes informed allocation of measures intended to prevent rabies spillover to humans and livestock. We inferred the spatial distribution of vampire bat roosts while accounting for observation effort and environmental effects by fitting a log Gaussian Cox process model to the locations of 563 roosts in three regions of Peru. Our model explained 45% of the variance in the observed roost distribution and identified environmental drivers of roost establishment. When correcting for uneven observation effort, our model estimated a total of 2340 roosts, indicating that undetected roosts (76%) exceed known roosts (24%) by threefold. Predicted hotspots of undetected roosts in rabies-free areas revealed high-risk areas for future viral incursions. Using the predicted roost distribution to inform a spatial model of rabies spillover to livestock identified areas with disproportionate underreporting and indicated a higher rabies burden than previously recognized. We provide a transferrable approach to infer the distribution of a mostly unobserved bat reservoir that can inform strategies to prevent the re-emergence of an important zoonosis.more » « less
-
Abstract Models of host–pathogen interactions help to explain infection dynamics in wildlife populations and to predict and mitigate the risk of zoonotic spillover. Insights from models inherently depend on the way contacts between hosts are modelled, and crucially, how transmission scales with animal density.Bats are important reservoirs of zoonotic disease and are among the most gregarious of all mammals. Their population structures can be highly heterogeneous, underpinned by ecological processes across different scales, complicating assumptions regarding the nature of contacts and transmission. Although models commonly parameterise transmission using metrics of total abundance, whether this is an ecologically representative approximation of host–pathogen interactions is not routinely evaluated.We collected a 13‐month dataset of tree‐roostingPteropusspp. from 2,522 spatially referenced trees across eight roosts to empirically evaluate the relationship between total roost abundance and tree‐level measures of abundance and density—the scale most likely to be relevant for virus transmission. We also evaluate whether roost features at different scales (roost level, subplot level, tree level) are predictive of these local density dynamics.Roost‐level features were not representative of tree‐level abundance (bats per tree) or tree‐level density (bats per m2or m3), with roost‐level models explaining minimal variation in tree‐level measures. Total roost abundance itself was either not a significant predictor (tree‐level 3D density) or only weakly predictive (tree‐level abundance).This indicates that basic measures, such as total abundance of bats in a roost, may not provide adequate approximations for population dynamics at scales relevant for transmission, and that alternative measures are needed to compare transmission potential between roosts. From the best candidate models, the strongest predictor of local population structure was tree density within roosts, where roosts with low tree density had a higher abundance but lower density of bats (more spacing between bats) per tree.Together, these data highlight unpredictable and counterintuitive relationships between total abundance and local density. More nuanced modelling of transmission, spread and spillover from bats likely requires alternative approaches to integrating contact structure in host–pathogen models, rather than simply modifying the transmission function.more » « less
