BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2026//talk//UHMHQX
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-juliacon-2026-UHMHQX@pretalx.com
DTSTART;TZID=CET:20260812T164500
DTEND;TZID=CET:20260812T170000
DESCRIPTION:This talk discusses two complementary directions in scientific 
 machine learning for geophysics. The first uses DeepONet surrogates to acc
 elerate magnetotelluric forward modelling and transdimensional probabilist
 ic inversion\, making uncertainty analysis more practical. The second uses
  implicit neural representations for three-dimensional gravity inversion\,
  where the subsurface model is learned under physics-based machine learnin
 g.
DTSTAMP:20260502T104503Z
LOCATION:Room 6
SUMMARY:Scientific Machine Learning for Geophysical Modelling\, Inversion a
 nd Uncertainty Quantification - Pankaj K Mishra
URL:https://pretalx.com/juliacon-2026/talk/UHMHQX/
END:VEVENT
END:VCALENDAR