BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085744Z
LOCATION:HG D 1.1
DTSTART;TZID=Europe/Stockholm:20190613T164500
DTEND;TZID=Europe/Stockholm:20190613T171500
UID:submissions.pasc-conference.org_PASC19_sess118_msa110@linklings.com
SUMMARY:Deep Learning Based Understanding of the Land Surface
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Emerg
 ing Application Domains, Climate and Weather, Physics\n\nDeep Learning Bas
 ed Understanding of the Land Surface\n\nFu\n\nOur study aims at understand
 ing the land surface from remote sensing images based on deep learning. Mo
 re specifically, we focus on solving three typical geoscience research iss
 ues, i.e., land cover classification, oil palm tree detection, and buildin
 g extraction. First, we will present a novel deep CNN based approach which
  takes full advantages of different data sources to improve the land cover
  mapping in China. Second, we will introduce our proposed deep learning ba
 sed method for detecting oil palm tree in a large-scale study area of Mala
 ysia. Third, we will present a semantic segmentation based method for buil
 ding footprint extraction in four cities.
END:VEVENT
END:VCALENDAR