BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.osgeo.org//foss4g-2026//speaker//D7TPHP
BEGIN:VTIMEZONE
TZID:JST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:JST
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-2026-DAURNY@talks.osgeo.org
DTSTART;TZID=JST:20260901T153000
DTEND;TZID=JST:20260901T160000
DESCRIPTION:Historic agricultural terraces are often poorly documented\, es
 pecially where woodland obscures morphology. This paper presents an open s
 ource GeoAI workflow for semi automatic terrace mapping from LiDAR DEMs. B
 y combining terrain\, solar irradiance\, soil erodibility and accessibilit
 y predictors\, the extended Random Forest model improved detection\, suppo
 rting heritage documentation and assessment.
DTSTAMP:20260718T211454Z
LOCATION:Cosmos2
SUMMARY:An open-source GeoAI workflow for mapping historic agricultural ter
 races - Filippo Brandolini
URL:https://talks.osgeo.org/foss4g-2026/talk/DAURNY/
END:VEVENT
END:VCALENDAR