BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//euroscipy-2023//talk//P38Y7L
BEGIN:VTIMEZONE
TZID:Europe/Zurich
BEGIN:DAYLIGHT
DTSTART:20220817T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221030T030000
RDATE:20231029T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230326T030000
RDATE:20240331T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Where is the flock? The use of graph neural networks for bird iden
 tification with meteorological radar. - Olga Lyashevska\, Abel Soares Siqu
 eira
DTSTART;TZID=Europe/Zurich:20230817T105500
DTEND;TZID=Europe/Zurich:20230817T111500
DTSTAMP:20260819T173244Z
UID:pretalx-euroscipy-2023-P38Y7L@pretalx.com
DESCRIPTION:In this project we generate tools to identify birds within the
  spatial extent of a meteorological radar.  Using the opportunities create
 d by modern dual-polarization radars we build graph neural networks to ide
 ntify bird flocks. For this\, the original point cloud data is converted t
 o multiple undirected graphs following a set of predefined rules\, which a
 re then used as an input in graph convolutional neural network (Kipf and W
 elling\, 2017\, https://doi.org/10.48550/arXiv.1609.02907). Each node has 
 a set of features such as range\, x\, y\, z coordinates and several radar 
 specific parameters e.g. differential reflectivity and phase shift which a
 re used to build model and conduct graph-level classification. This tool w
 ill alleviate problem of manual identification and labelling which is tedi
 ous and time intensive. Going forward we also focus on using the temporal 
 information in the radar data. Repeated radar measurements enable us to tr
 ack these movements across space and time. This makes it possible for regi
 onal movement studies to bridge the methodological gap between fine-scale\
 , individual-based tracking studies and continental-scale monitoring of bi
 rd migration. In particular\, it enables novel studies of the roles of hab
 itat\, topography and environmental stressors on movements that are not fe
 asible with current methodology. Ultimately\, we want to apply the methodo
 logy to data from continental radar networks to study movement across scal
 es.
LOCATION:HS 120
URL:https://pretalx.com/euroscipy-2023/talk/P38Y7L/
END:VEVENT
END:VCALENDAR