BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-london-2026//talk//J99JNR
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-pydata-london-2026-J99JNR@pretalx.com
DTSTART;TZID=GMT:20260606T144500
DTEND;TZID=GMT:20260606T153000
DESCRIPTION:In science and engineering\, we are frequently challenged by th
 e inability to manipulate environmental variables—a key component of the
  scientific method. For example\, we cannot simply stop a hurricane in its
  tracks or change the temperature of the Sun. Instead\, we heavily rely on
  "Forward Models"—numerical simulations that predict data from physical 
 parameters. However\, these models are often massively computationally exp
 ensive.\n\nEmulators (or surrogate models) present a solution. Whether sol
 ving a single time-sensitive equation or searching a high-dimensional infe
 rence space\, emulators can accelerate simulation results by orders of mag
 nitude. In this talk\, we show how these machine-learning tools are revolu
 tionising research across STEM disciplines\, from inferring input paramete
 rs to developing digital twins and augmenting foundational models.
DTSTAMP:20260602T223428Z
LOCATION:Grand Hall 2
SUMMARY:Fast-Forward(ing) Models: Accelerating High-Dimensional Inference w
 ith AI Emulators - Austen Wallis
URL:https://pretalx.com/pydata-london-2026/talk/J99JNR/
END:VEVENT
END:VCALENDAR