BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Global-scale Species Distribution Modelling - Oisin Mac Ao
 dha\, University of Edinburgh
DTSTART:20250411T120000Z
DTEND:20250411T130000Z
UID:TALK225775@talks.cam.ac.uk
CONTACT:114742
DESCRIPTION:*Abstract*\n\nEstimating the geographical range of a species f
 rom sparse observations is a challenging and important geospatial predicti
 on problem. Given a set of locations where a species has been observed\, t
 he goal is to build a model to predict whether the species is present or a
 bsent at any location. This problem has a long history in ecology\, but tr
 aditional methods struggle to take advantage of emerging large-scale crowd
 sourced datasets which can include tens of millions of observations of hun
 dreds of thousands of species in addition to the availability of multi-mod
 al data sources such as paired images and natural language descriptions. I
 n this talk\, I will present recent work from my group where we have devel
 oped deep learning-based solutions for estimating species' ranges from spa
 rse presence-only data. I will also discuss some of the open challenges th
 at exist in this space. \n\n*Bio*\n\nOisin Mac Aodha is a Reader in Machin
 e Learning in the School of Informatics at the University of Edinburgh. He
  is also an ELLIS Scholar and former Turing Fellow. He obtained his PhD fr
 om University College London and was a postdoc at Caltech prior to his cur
 rent role. His current research interests are in the areas of self-supervi
 sed learning\, 3D vision\, fine-grained learning\, and human-in-the-loop l
 earning. In addition\, he works on questions related to AI for conservatio
 n and biodiversity monitoring.\n
LOCATION:Main Seminar Room at the David Attenborough Building. Zoom link: 
 https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4
 QT09&from=addon 
END:VEVENT
END:VCALENDAR