BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-it-2023//speaker//9SL9JD
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-it-2023-PZZ8M9@talks.staging.osgeo.org
DTSTART;TZID=GMT:20230614T150000
DTEND;TZID=GMT:20230614T151500
DESCRIPTION:Linear Infrastructures\, characterized by high level of systemi
 c vulnerability [1\,2]\, are subject to several environmental and geologic
 al hazards. In the context of risk assessment and management\, monitoring 
 these important assets plays an important role in establishing the mainten
 ance planning and preventive measures against the disruptive phenomenon\, 
 such as ground deformation due to natural and anthropogenic causes. In-sit
 u and traditional infrastructure monitoring approaches\, such as high-prec
 ision leveling measurements [3]\, are known to be costly and time-consumin
 g. On the other hand\, satellite Remote Sensing (RS) techniques\, such as 
 Synthetic Aperture Radar (SAR) Interferometry (InSAR)\, are recognized to 
 be promising tools for monitoring and condition assessment of infrastructu
 res [4]. \nAs an essential branch of Copernicus Land Monitoring Service (C
 LMS)\, the new European Ground Motion Service (EGMS) is providing freely a
 ccessible ground deformation data spatially covering almost all European c
 ountries. The deformation time time-series contained in the datapoints are
  acquired based on InSAR processing of Sentinel-1 images from January 2016
  up to December 2021 [5\,6]. \nIn this study\, InSAR-derived deformation d
 ataset\, geo-environmental parameters\, and Machine Learning (ML) techniqu
 es have been integrated to address the major causes of this complex phenom
 enon\, specifically emphasizing railway and highway in Lombardy region\, I
 taly. The vertical displacement velocities (mm/year) of EGMS datapoints lo
 cated at the neighborhood of these infrastructures are utilized as the inp
 ut ground motion data. The conditioning factors considered in this work in
 clude elevation\, slope angle\, slope aspect\, precipitation\, curvature\,
  solar radiation\, and Normalized Difference Vegetation Index (NDVI). The 
 ML models\, including Decision Tree (DT)\, Linear regression (LR)\, Light 
 GBM (LG)\, XGBoost (XG)\, Random Forest (RF) and Extra Trees (ET)\, are us
 ed in this study. The Train-Test dataset ratio is considered to be 7:3\, w
 ith respect to the higher performance of this ratio [7].\nFirst\, the used
  models have been validated using the Area Under ROC Curve (AUC)\, and ROC
  being Receiver Operating Characteristic curve. The results mostly show ac
 cep results (interval of 0.7 to 0.8) and the applicibility of the model. T
 hen\, the Relative Feature Importance (RFI) analysis is carried out to add
 ress the significant factors causing the ground deformatio. Also\, the res
 ults regarding the Permutation-based and Shapley Additive Explanations (SH
 AP) importance decisions among the factors show that the rainfall (precipi
 tation) and elevation are playing the most important role in the occurrenc
 e of the ground deformation detected on the infrastructures\, based on the
  methodology adopted in this study. Also\, the effect of solar radiation c
 annot be neglected.  More detailed and further discussion of the results w
 ill be provided in the full version of this letter.
DTSTAMP:20260504T191405Z
LOCATION:Sala Biblioteca @ PoliBa
SUMMARY:Assessment of infrastructure deformation using EGMS-InSAR data and 
 geo-environmental factors through machine learning: Railways and highways 
 of Lombardy Region\, Italy - Marco Scaioni\, Rasoul Eskandari\, Ziyang Wan
 g
URL:https://talks.staging.osgeo.org/foss4g-it-2023/talk/PZZ8M9/
END:VEVENT
END:VCALENDAR