BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.earthmonitor.org//opengeohub-summer-school-2025/
 /9PTJVH
BEGIN:VTIMEZONE
TZID:Europe/Amsterdam
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-opengeohub-summer-school-2025-JE8JLY@pretalx.earthmonitor.org
DTSTART;TZID=Europe/Amsterdam:20250902T090000
DTEND;TZID=Europe/Amsterdam:20250902T093000
DESCRIPTION:The volume of unlabeled Earth observation (EO) data is huge. To
  interpret this vast amount of data\, efficient modelling approaches are n
 eeded that can generalize to large geographic areas and are robust to inhe
 rent noise. Data-driven approaches promise great potential for interpretin
 g and combining data from different space missions. In this talk\, I will 
 present our work on global canopy height mapping (https://langnico.github.
 io/globalcanopyheight/) with optical satellite images and sparse spaceborn
 e lidar data and discuss a recent project called MMEarth (https://vishalne
 d.github.io/mmearth/) that explored multi-modal pretext tasks for learning
  representations that are suitable for a range of downstream tasks with li
 mited training data.
DTSTAMP:20260624T125427Z
LOCATION:HugoTECH
SUMMARY:Learning From Global Earth Observation Data - Nico Lang
URL:https://pretalx.earthmonitor.org/opengeohub-summer-school-2025/talk/JE8
 JLY/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-opengeohub-summer-school-2025-UNKX8N@pretalx.earthmonitor.org
DTSTART;TZID=Europe/Amsterdam:20250905T090000
DTEND;TZID=Europe/Amsterdam:20250905T100000
DESCRIPTION:Machine learning has become an important toolbox for analyzing 
 complex Earth observation data to derive information from the raw data. In
  particular\, supervised deep learning has achieved great success in solvi
 ng EO tasks where the relationship between input and output is not clearly
  understood. However\, applications with limited reference data cannot dir
 ectly benefit from advances in supervised deep learning. This lecture will
  first introduce the concepts of supervised deep learning and then provide
  an overview of research in the field of self-supervised learning (SSL)\, 
 which aims to learn transferable representations (i.e.\, features) from un
 labeled data.
DTSTAMP:20260624T125427Z
LOCATION:HugoTECH
SUMMARY:Learning Representations: From Engineering Features to Engineering 
 Pretext Tasks - Nico Lang
URL:https://pretalx.earthmonitor.org/opengeohub-summer-school-2025/talk/UNK
 X8N/
END:VEVENT
END:VCALENDAR