Hourly GPS Locations, Associated Habitat Condition, and Annotated Life History State for Training Machine Learned Models of Waterfowl Daily Activity

Publication Date

2022-08-19

Start

2015-01-27

End

2020-08-22

Overton, C.T., Casazza, M.L., and Bretz, J.B., 2022, Hourly GPS locations, associated habitat condition, and annotated life history state for training machine learned models of waterfowl daily activity: U.S. Geological Survey data release, https://doi.org/10.5066/P9XBZKZ8.

Type: Related Primary Publication

Questions pertaining to the intended use of, or assistance with understanding limitations or interpretation of these data are to be directed to the individuals/organization listed in the Point of Contact section. Unless otherwise stated, all data, metadata, and related materials are considered to satisfy the quality standards relative to the purpose for which the data were collected. Although these data and associated metadata have been reviewed for accuracy and completeness and approved for release by the U.S. Geological Survey (USGS), no warranty expressed or implied is made regarding the display or utility of the data on any other system or for general or scientific purposes, nor shall the act of distribution constitute any such warranty. Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government.

Data were collected as part of an on-going project investigating waterfowl ecology, primarily in the Pacific Flyway. Data consists of hourly, half-hourly, or quarter-hourly GPS location intervals. Data records were non-randomly selected from this larger database. Some records were selected based on the availability of auxillary information suitable for annotating life history states (i.e. via nest monitoring) or as indicated by existing algorithms identifying potential states (e.g. molting and migration) , or randomly selected among other potential data. Regardless of the initial reason for selecting locations, all data were visually assessed by waterfowl experts before final annotation of life history state. As a result the data does not unbiasedly reflect waterfowl activity because data selection focused on identification of life history states that are often shorter but more demographically important, such as nesting and migration. However, the set of GPS locations collected within each day are unbiased representations of the activity exhibited by a bird on that day. More details on annotation procedures are provided in the associated manuscript title, Machine learned daily life history classification using low frequency tracking data and automated modelling pipelines: Application to North American waterfowl.

• USGS Data Release Products
• USGS Western Ecological Research Center

Data source

Input directly