BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.osgeo.org//foss4g-uk-2026//talk//Q8UHHS
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-uk-2026-Q8UHHS@talks.osgeo.org
DTSTART;TZID=GMT:20261013T104500
DTEND;TZID=GMT:20261013T124500
DESCRIPTION:What happens when a GeoAI workflow needs to run reliably on new
  imagery every week\, across different seasons and geographies\, without s
 omeone manually checking every output? \n\nThis workshop introduces MLOps 
 thinking to the EO community: the engineering practices that take a workin
 g pipeline and make it robust\, reproducible\, and production-aware. Throu
 gh a hands-on session\, using as an example a Maritime Surveillance proble
 m\, participants will explore how to validate inputs\, track experiments\,
  test outputs\, and detect when something silently breaks. No cloud accoun
 ts or infrastructure setup required.\n\nLearning Outcomes\n- Understand th
 e key principles of MLOps and how they apply to EO workflows\n- Be able to
  identify common failure modes when moving from experimentation to product
 ion\n- Apply basic input validation\, experiment tracking\, and output tes
 ting to their own pipelines\n\nPrerequisites\n- A Github account\, with th
 e ability to run a Github Codespace\, OR the ability to run code locally i
 n a laptop\, including Docker containers.\n- Familiarity with EO data conc
 epts (bands\, resolution\, indices) is helpful but not required\n- Some ex
 perience with Python
DTSTAMP:20260821T182713Z
LOCATION:Think
SUMMARY:MLOps for Earth Observation - Juan
URL:https://talks.osgeo.org/foss4g-uk-2026/talk/Q8UHHS/
END:VEVENT
END:VCALENDAR