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

These data represent an annotated training data for machine learned life history classification of the daily activity of dabbling ducks (f. Anatidae sf. Anatinae) using hourly GPS data. Each row of data represents a single GPS location for one of 5 species of dabbling duck. Note: the machine learned model was developed to be general across sf. Anatinae and does not include specific reference to the species included. That information is obtainable from the point of contact upon request. Each data record contains unique identifiers for individual bird, individual date of locations for an individual bird, and for individual location. Each record contains spatial, temporal and associated habitat information. Each record also contains an annotated label representing one of 8 life history states or movement patterns exhibited by the collective location obtained for the individual on that date. The 8 classes identified were: Brooding, Dead, Local movements, Migration, Molting, Molt-Like, Nesting, Regional Relocation. Detailed description of the machine learned model and annotation methods are provided in the associated manuscript titled, Machine learned daily life history classification using low frequency tracking data and automated modelling pipelines: Application to North American waterfowl. These data support the following publication: Overton, C., Casazza, M., Bretz, J., McDuie, F., Matchett, E., Mackell, D., Lorenz, A., Mott, A., Herzog, M. and Ackerman, J., 2022. Machine learned daily life history classification using low frequency tracking data and automated modelling pipelines: application to North American waterfowl. Movement Ecology, 10(1), pp.1-13. https://doi.org/10.1186/s40462-022-00324-7.