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:20250822T115804Z
LOCATION:Room 5.0B15 & 16
DTSTART;TZID=Europe/Stockholm:20250617T130000
DTEND;TZID=Europe/Stockholm:20250617T133000
UID:submissions.pasc-conference.org_PASC25_sess130_msa158@linklings.com
SUMMARY:Integrating Fourier Neural Operators with Diffusion Models to Impr
 ove the Spectral Representation of Synthetic Earthquake Ground Motion Resp
 onse
DESCRIPTION:Filippo Gatti (Université Paris-Saclay), Fanny Lehmann (ETH AI
  Center), Niccolò Perrone and Stefania Fresca (Politecnico di Milano), and
  Hugo Gabrielidis (Université Paris-Saclay)\n\nThis study integrates the M
 ultiple-Input Fourier Neural Operator (MIFNO) with the diffusion model by 
 Gabrielidis et al. (2024) to address challenges in capturing mid-frequency
  details in synthetic earthquake ground motion. MIFNO, a computationally e
 fficient surrogate model for seismic wave propagation, processes 3D hetero
 geneous geological data along with earthquake source characteristics. It i
 s trained to reproduce the three-component (3C) earthquake wavefield at th
 e surface. The HEMEWS-3D database (Lehmann et al., 2024) is used, comprisi
 ng 30,000 earthquake simulations across varying geologies with random sour
 ce positions and orientations. These reference simulations were conducted 
 using the high-performance SEM3D software (CEA et al., 2017), which excels
  in simulating fault-to-structure scenarios at a regional scale. While SEM
 3D provides accurate results at lower frequencies, its performance degrade
 s with increasing frequency due to complex physical phenomena and a known 
 bias in neural networks, which struggle with small-scale features. This li
 mitation restricts MIFNO's applicability in earthquake nuclear engineering
 . The proposed combination with the diffusion model aims to mitigate this 
 issue and improve the accuracy of mid-frequency predictions in synthetic g
 round motion generation.\n\nDomain: Chemistry and Materials, Climate, Weat
 her, and Earth Sciences, Applied Social Sciences and Humanities, Engineeri
 ng, Life Sciences, Physics, Computational Methods and Applied Mathematics\
 n\nSession Chairs: Irene Bonati (SURF), Ewa Deelman (University of Souther
 n California), and Sagar Dolas (SURF)\n\n
END:VEVENT
END:VCALENDAR