BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260421T090513Z
LOCATION:Bldg. 8 - Room B 102
DTSTART;TZID=Europe/Stockholm:20260630T134500
DTEND;TZID=Europe/Stockholm:20260630T142500
UID:submissions.pasc-conference.org_PASC26_sess148_msa244@linklings.com
SUMMARY:Blended Modelling for Weather and Climate Prediction: A Framework 
 Bridging AI and Physics-Based Systems
DESCRIPTION:Ben Shipway (Met Office)\n\nThe rapid emergence of machine lea
 rning (ML) for weather and climate prediction offers transformative opport
 unities in computational cost, scalability, and agility, but also raises c
 hallenges around trust, robustness, and integration with established model
 ling systems. In the near to medium term, weather and climate prediction i
 s likely to benefit most from blended modelling approaches that combine th
 e complementary strengths of machine learning and physics‑based systems. W
 e present a structured framework and typology that clarifies the spectrum 
 of blending options, ranging from independent physics‑based and independen
 t ML systems to hybrid‑integrated, hybrid‑composite, and augmented approac
 hes. This typology provides a common language for the community, supportin
 g clearer communication, strategic decision‑making, and prioritisation of 
 research and infrastructure investment. We discuss how different blending 
 choices trade off accuracy, computational cost, energy efficiency, agility
 , and trust, and how they enable incremental as well as more radical pathw
 ays for system development. By grounding emerging ML capabilities within e
 stablished physics‑based workflows, blended approaches offer a pragmatic r
 oute to innovation that is compatible with operational constraints, evolvi
 ng computing architectures, and the long‑term demands of weather and clima
 te prediction.\n\nDomain: Computational Methods and Applied Mathematics\n\
 nSession Chairs: Nick Brown (EPCC); Michele Weiland (EPCC, The  University
  of Edinburgh); Adrian Jackson (The University of Edinburgh); and Rui Apos
 tolo (EPCC)\n\n
END:VEVENT
END:VCALENDAR