BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//flowpath-2025//speaker//MHYPM3
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-flowpath-2025-KAZFMN@talks.staging.osgeo.org
DTSTART;TZID=CET:20250611T183000
DTEND;TZID=CET:20250611T184000
DESCRIPTION:The hydrogeological connection between tunnel excavation and sp
 rings is a key aspect to be assessed during the preliminary design phase\,
  both for environmental and socio-economic reasons. Based on a preliminary
  hydrogeological survey and environmental monitoring of the springs\, the 
 need to anticipate potential impacts at an early stage influences both the
  feasibility of the project and the design of mitigation measures in more 
 critical areas.\nA data-driven Machine Learning (ML) approach\, designed t
 o incorporate the complexity of the relationships between various physical
  and hydrogeological parameters contributing to the risk of spring impact 
 due to tunneling\, was calibrated using a dataset from detailed hydrogeolo
 gical monitoring conducted alongside the excavation of two major tunnels i
 n the Apennines (Italy)\, involving sedimentary and carbonate karst aquife
 rs.\nThe approach shows good scores for model evaluation\, and here we pre
 sent the results of a further validation against datasets from two additio
 nal sites: one in the Alps (Brenner Base Tunnel\, within a crystalline aqu
 ifer) and another in the Apennines (Bologna-Florence highway pass variant\
 , within a turbiditic sedimentary setting). The application of the method 
 to these new sites—one of which features a geological setting different 
 from the original validation dataset— shows good scores again\, demonstr
 ating its potential for broader generalization.\nThe results were compared
  with those of the Drawdown Hazard Index (DHI)\, demonstrating that both m
 ethods can effectively identify risk while also highlighting the sensitivi
 ty of the latter. Specifically\, by adjusting the various thresholds\, hig
 hly accurate results can be achieved. Conversely\, the ML models generate 
 outputs that are not subject to modification or classification into discre
 te categories.
DTSTAMP:20260427T072945Z
LOCATION:Room R3
SUMMARY:Validation of a Machine Learning tool for preliminary quantificatio
 n of the hydrogeological interference risk of tunnels. - Ernesto Pugliese
URL:https://talks.staging.osgeo.org/flowpath-2025/talk/KAZFMN/
END:VEVENT
END:VCALENDAR