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:20241120T082410Z
LOCATION:HG F 1
DTSTART;TZID=Europe/Stockholm:20240604T150000
DTEND;TZID=Europe/Stockholm:20240604T153000
UID:submissions.pasc-conference.org_PASC24_sess178_pap122@linklings.com
SUMMARY:GAIA-Chem: A Framework for Global AI-Accelerated Atmospheric Chemi
 stry Modelling
DESCRIPTION:Paper\n\nJeff Adie (Newcastle University, NVIDIA Inc.); Cheng 
 Siong Chin and Jichun Li (Newcastle University); and Simon See (NVIDIA Inc
 .)\n\nThe inclusion of atmospheric chemistry in global climate projections
  is currently limited by the high computational expense of modelling the m
 any reactions of chemical species. Recent rapid advancements in artificial
  intelligence (AI) provide us with new tools for reducing the cost of nume
 rical simulations. The application of these tools to atmospheric chemistry
  is still somewhat nascent and multiple challenges remain due to the react
 ion complexities and the high number of chemical species. In this work, we
  present GAIA-Chem, a global AI-accelerated atmospheric chemistry framewor
 k for large-scale, multi-fidelity, data-driven chemical simulations; GAIA-
 Chem provides an environment for testing different approaches to data-driv
 en species simulation. GAIA-Chem includes curated training and validation 
 datasets, support for offline and online training schemes, and comprehensi
 ve metrics for model intercomparison. We use GAIA-Chem to evaluate two DNN
  models; a standard autoencoder scheme based on convolutional LSTM nodes, 
 and a transformer-based model. We show computational speedups of up to 1,2
 80 times over numerical methods for the chemical solver and a 2.8 times re
 duction in RMSE when compared to previous works.\n\nDomain: Climate, Weath
 er, and Earth Sciences\n\nSession Chair: Jack Atkinson (University of Camb
 ridge)
END:VEVENT
END:VCALENDAR