BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.earthmonitor.org//KBL7ML
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:STANDARD
DTSTART:20001029T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T010000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-gw2023-KBL7ML@pretalx.earthmonitor.org
DTSTART;TZID=Europe/London:20231006T144500
DTEND;TZID=Europe/London:20231006T150500
DESCRIPTION:Land use monitoring using machine learning and Earth observatio
 n data is usually challenging due to the lack of training samples\, especi
 ally for large areas and long periods where gathering in-situ information 
 is costly or sometimes impossible. This work proposes a machine learning a
 pproach called Time-Weighted Dynamic Time Warping (TWDTW) for data-scarce 
 applications. TWDTW is a satellite image time series classification algori
 thm that uses a Dynamic Time Warping (DTW) distance. DTW is a widely used 
 algorithm in various fields\, including speech recognition\, medicine\, in
 dustry\, and finance\, and has shown promising results in land use mapping
  due to its ability to deal with gaps in time series\, robustness to noise
 \, matching time series of different lengths and intervals\, and to keep i
 ts classification performance on small training sets.\n\nHowever\, DTW has
  limitations in matching events regardless of when they occur\, which can 
 result in out-of-season alignments and misclassifications—for example\, 
 aligning a summer crop to a winter one. TWDTW overcomes this limitation by
  introducing a time weight to matches deviating from an expected date in t
 he training set. This temporal constraint improves classification performa
 nce by controlling for out-of-season alignments while keeping DTW's flexib
 ility to smaller phenological fluctuations of vegetation.\n\nThis presenta
 tion will demonstrate the effectiveness of the TWDTW method for land use c
 lassification using the open-source R package dtwSat. Overall\, this machi
 ne learning method is suitable for data-scarce regions and can contribute 
 to land use monitoring\, supporting the environmental targets proposed by 
 the European Green Deal and the United Nations' Sustainable Development Go
 als.
DTSTAMP:20260511T093650Z
LOCATION:EURAC Auditorium
SUMMARY:Overcoming Data Scarcity in Land Use Monitoring with Time-Weighted 
 Dynamic Time Warping - Victor Maus
URL:https://pretalx.earthmonitor.org/gw2023/talk/KBL7ML/
END:VEVENT
END:VCALENDAR