BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.earthmonitor.org//THLTRJ
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-THLTRJ@pretalx.earthmonitor.org
DTSTART;TZID=Europe/Amsterdam:20250901T110000
DTEND;TZID=Europe/Amsterdam:20250901T113000
DESCRIPTION:Training points (ground observations and measurements of enviro
 nmental variables) that are referenced in space and time\, and are availab
 le for longer periods\, can be used to build spatiotemporal Machine Learni
 ng models (stmlm). Such stmlm's can then be used to generate time-series o
 f predictions\, which can then be used to run time-series analysis. Spatio
 temporal modeling is different from purely spatial mapping is in the follo
 wing three aspects: (1) points and covariate layers are matched in spaceti
 me (usually a day or month-year period of ground observations or at least 
 the year of ground observations)\; (2) covariate layers are based on time-
 series of usually EO-based images (spatiotemporal data cubes) and include 
 also accumulative indices (e.g. cumulative rainfall\, cumulative snow cove
 r\, cumulative cropping fraction\, and similar) and derivatives\; (3) duri
 ng model training and validation\, points are subset in both spacetime to 
 avoid overfitting and bias in predictions. This talk will address 15 pract
 ical lessons from running stml including how to organize monitoring networ
 ks\, how to prevent overfitting\, how to derive prediction errors in space
 time\, how to use time-series of predictions to detect changes and similar
 .
DTSTAMP:20260624T124901Z
LOCATION:HugoTECH
SUMMARY:Spatiotemporal Machine Learning: 15 practical lessons on how to org
 anize monitoring\, modeling and updating of predictions - Tom Hengl (OpenG
 eoHub)
URL:https://pretalx.earthmonitor.org/opengeohub-summer-school-2025/talk/THL
 TRJ/
END:VEVENT
END:VCALENDAR