Machine learned daily life history classification using low frequency tracking data and automated modelling pipelines: application to North American waterfowl

Table 1 Distribution of 8 life history states or movement patterns used to train and validate machine learned classification models

	Brooding	Dead	Local	Migration	Molt-like	Molting	Nesting	Regional relocation
Northern Pintail	0	54	1238	64	422	56	0	103
American Wigeon	0	0	0	4	12	0	0	0
Cinnamon Teal	8	522	188	3	166	6	102	9
Mallard	41	1	1914	4	1466	190	107	39
Gadwall	56	0	971	24	896	184	80	34
Undeployed	0	370	0	0	0	0	0	0

Annotation was performed on daily sets of 24 hourly GPS locations obtained between January 2015 and August 2020 from 131 free-living waterfowl representing 5 species in North America, includes GPS locations from two undeployed transmitters representing bird mortality

ISSN: 2051-3933