BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-europe-2025//talk//38KDU
 J
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-europe-2025-38KDUJ@talks.staging.osgeo.org
DTSTART;TZID=CET:20250717T150500
DTEND;TZID=CET:20250717T151000
DESCRIPTION:Increased urbanization rates have had a significant effect on c
 hanging land surface characteristics\, leading to the rise of Urban Heat I
 slands (UHIs)\, localized regions where temperatures are considerably high
 er than in surrounding rural areas. This phenomenon is primarily driven by
  dense urban structures\, reduced vegetation cover\, and anthropogenic hea
 t discharge\, which collectively contribute to enhancing the absorption an
 d retention of heat in urban areas (Anjos et al.\, 2025\; Qin & Jiang\, 20
 24). As climate change intensifies\, UHIs worsen environmental problems\, 
 including increased energy consumption\, lower air quality\, and severe pu
 blic health concerns like heat stress and cardiovascular disease (Chanpich
 aigosol & Chaichana\, 2025). The rapid expansion of urban areas has elevat
 ed UHI mitigation to one of the highest priorities. Yet\, existing detecti
 on and analysis methods often lack scalability\, automation\, limiting the
 ir ability to produce high-resolution\, globally consistent assessments (F
 u et al.\, 2024).
DTSTAMP:20260527T212627Z
LOCATION:PA01 (Quarticle)
SUMMARY:An Open-Source Deep Learning Framework for Scalable Urban Heat Isla
 nd Detection Using Geospatial Data - Mercy Ọ̀nàọpẹ́mipọ̀ Akin
 tola\, Gresa Neziri
URL:https://talks.staging.osgeo.org/foss4g-europe-2025/talk/38KDUJ/
END:VEVENT
END:VCALENDAR