BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Cambridge Statistics Discussion Group (CSDG)
SUMMARY:Wildlife from space: detecting\, monitoring and st
 udying wildlife using satellite imagery - Peter Fr
 etwell\, British Antarctic Survey
DTSTART;TZID=Europe/London:20240205T190000
DTEND;TZID=Europe/London:20240205T210000
UID:TALK203668AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/203668
DESCRIPTION:The advent of Very High Resolution optical satelli
 te imagery has enabled us to find and study wildli
 fe in places and in ways that have not previously 
 been possible. In theory\, any large animal (>1m) 
 in open terrain that has a high contrast with its 
 surrounding environment could be monitored by sate
 llite. The technology is particularly useful in re
 mote and hard to access locations\, or where multi
 ple records would be difficult to acquire through 
 other means. The availability of large amounts of 
 coverage from satellites also enables regional and
  continental scale studies regardless of terrain\,
  borders\, or bureaucracy. Additionally\, satellit
 es do not disrupt behavior or disturb animals in w
 ays that ships\, ground\, aircraft\, or UAVs often
  do. In future traditional wildlife line-transect 
 populations studies could be replaced by total are
 a studies from automated VHR satellite imagery.\n 
 \nHowever\, the extensive amounts of data that can
  be collected\, coupled with the relatively low sp
 atial resolution\, offer unique challenges and que
 stions\; is multiple low-resolution data of everyw
 here better than high-quality sparse data? Cost of
  imagery and analytical pipelines will also have t
 o be addressed before optimal use of the technolog
 y can be made\, both by the satellite providers an
 d the users. To utilize the full capacity of the t
 echnology it will need interdisciplinary solutions
  using novel and groundbreaking machine learning t
 echniques and big data pipelines. Although often t
 he techniques and methodologies can be transferred
  between species\, many user cases show that behav
 ioral knowledge of each species is still key to un
 derstanding results. Conservation users\, remote s
 ensing experts and machine learning practitioners 
 will need to work together to build these data str
 eams.\n\nIn this talk we will present several grou
 ndbreaking examples from a decade of developing au
 tomated solutions using VHR and medium resolution 
 satellite imagery focusing initially on the recent
  case of emperor penguin breeding failure and movi
 ng on its use in seals\, whales\, albatrosses and 
 other species. We will discuss challenges\, advant
 ages and future directions of the use of this pote
 ntially revolutionary tool in an era of dynamic ch
 ange for the population of many species.\n
LOCATION:Department of Applied Mathematics and Theoretical 
 Physics\, Centre for Mathematical Sciences\, Unive
 rsity of Cambridge
CONTACT:Peter Watson
END:VEVENT
END:VCALENDAR