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:20250822T115806Z
LOCATION:Room 5.0B56
DTSTART;TZID=Europe/Stockholm:20250617T150000
DTEND;TZID=Europe/Stockholm:20250617T170000
UID:submissions.pasc-conference.org_PASC25_sess125@linklings.com
SUMMARY:MS4C - Scaling AI Surrogate Modelling Methods Towards Industrial A
 pplication for Computational Fluid Dynamics
DESCRIPTION:The ScaleAI4CFD minisymposium explores the latest advancements
  in machine learning (ML) models for computational fluid dynamics (CFD), f
 ocusing on scaling these models for industrial applications. This event br
 idges the gap between academic research and industry needs, addressing cha
 llenges in energy, automotive, aerospace, and healthcare sectors. The symp
 osium's emphasis on CFD is strategic, building on the success of the AI4Di
 fferentialEquations workshop at ICLR2024. While ML applications in weather
  forecasting and climate modeling have progressed, other fluid dynamics ar
 eas lag behind. The event features experts from industry, academia, and st
 artups to discuss specific challenges and opportunities in applying AI sur
 rogates to real-world research and design. The focus on CFD also addresses
  crucial environmental concerns. Aerospace and automotive industries signi
 ficantly contribute to climate change, and CFD offers a way to reduce thei
 r environmental impact by minimizing physical prototyping and testing. AI/
 ML surrogate models have the potential to further reduce costs, time, and 
 energy consumption in simulations. Attendees will gain insights into the c
 urrent state of the art and the challenges and opportunities in applying c
 utting-edge AI methods to CFD problems.\n\nDisruption in Science and Engin
 eering Happens at Scale\n\nIn the era of LLM models, one gets notoriously 
 confronted with the question of where we stand with applicability of large
 -scale deep learning models within scientific or engineering domains. The 
 discussion starts by reiterating on recent triumphs in weather and climate
  modeling, making connections t...\n\n\nJohannes Brandstetter (JKU Linz, E
 mmi AI GmbH)\n---------------------\nPanel Discussion – Foundational model
 s for Computational Fluid Dynamics\n\nIn this panel session, we will bring
  together the speakers to discuss the development of ‘Foundational Models’
  a key topic in the field of Machine Learning for Computational Fluid Dyna
 mics. In particular, we will discuss the technical challenges surrounding 
 data generation, generalizabil...\n\n\nNeil Ashton (NVIDIA Inc.), Philipp 
 Bekemeyer (DLR), and Johannes Brandstetter (JKU Linz)\n-------------------
 --\nAssessing the state of the art for AI surrogate methods applied to ext
 ernal automotive aerodynamics – successes and failures\n\nIn this talk, we
  will focus on discussing recent work to assess the capability of AI surro
 gate models in the prediction of automotive aerodynamics. In particular, t
 he talk will focus on both dataset generation (specifically efforts behind
  generating the AhmedML, WindsorML and DrivAerML open-source d...\n\n\nNei
 l Ashton (NVIDIA Inc.)\n---------------------\nScaling Machine Learning Me
 thods Towards Industrial-Grade Aircraft Aerodynamics Applications\n\nIn ar
 eas for which vast amounts of data are available Machine learning and arti
 ficial intelligence techniques had a tremendous success, especially when m
 athematical models are lacking. Instead, engineering tools in general and 
 computational fluid dynamics tools in particular rely on first-order prin.
 ..\n\n\nPhilipp Bekemeyer (DLR)\n\nDomain: Engineering, Computational Meth
 ods and Applied Mathematics\n\nSession Chair: Neil Ashton (NVIDIA Inc.)
END:VEVENT
END:VCALENDAR