BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//EURODYN//Schedule//DE
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700329T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701025T030000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:511@eurodyn2026.org
DTSTAMP:20261026T144037Z
DTSTART;TZID=Europe/Berlin:20261001T113000
DTEND;TZID=Europe/Berlin:20261001T115000
SUMMARY:GNSS-Based Displacement Estimation for Bridge Structural Health M
 onitoring: Comparison of Ensemble Kalman Filter and Random Forest Approa
 ches
LOCATION:Room F102
DESCRIPTION:MS 14\n\nPresenter: Watanabe\, Gakuho\n\nAuthors: Watanabe\, 
 Gakuho\; Miyamoto\, Takeshi\; Nisihino\, Takumi\; Tita\, Elfrido\; Miaym
 oto\, Takeshi\n\nChair: Papadimitriou\, Costas\n\nAbstract: GNSS-based d
 isplacement monitoring provides important information for structural hea
 lth monitoring (SHM) of bridges\, but real-time kinematic (RTK) measurem
 ents are contaminated by noise and biases. This study investigates robus
 t displacement estimation for a five-span steel box girder bridge monito
 red by RTK-GNSS. Two approaches are compared: an Ensemble Kalman Filter 
 (EnKF) that assimilates noisy RTK-GNSS measurements into a state-space m
 odel\, and a data-driven Random Forest (RF) model that exploits environm
 ental variables such as member and air temperature\, solar radiation and
  wind speed. Four GNSS antennas installed along the bridge were operated
  at five-minute intervals for 14 months\, in parallel with static GNSS a
 nd displacement sensors used as reference measurements. The models are e
 valuated in terms of RMSE\, MAE\, maximum error and correlation coeffici
 ent\, as well as their ability to reproduce daily thermal cycles and sea
 sonal trends. Both approaches achieve millimetre-level accuracy\; the be
 st configurations provide RMSE below 2 mm and maximum error below 10 mm 
 with correlation coefficients above 0.98. EnKF additionally provides tim
 e-varying confidence intervals\, supporting reliability assessment and t
 hreshold setting for SHM decision-making. The results demonstrate that n
 oisy RTK-GNSS data can be converted into reliable quasi-static displacem
 ent information and provide guidance for selecting estimation strategies
  in bridge SHM and digital twin applications.
URL:https://eurodyn2026.org/submission/511
END:VEVENT
END:VCALENDAR