Poster (After Call)

FZJ-2026-03290

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png NEOPIC: HPC Strategies for FNO-DSE in Kinetic Plasma Simulation

John, C. M. (Corresponding author)FZJ* ; Muralikrishnan, S.FZJ* ; Kelling, J. ; Gibbon, P.FZJ* ; Herten, A.FZJ*

2026

This record in other databases:  

Please use a persistent id in citations: doi:10.34734/FZJ-2026-03290

Abstract: The NEOPIC project couples Particle-In-Cell (PIC) plasma simulations with Fourier Neural Operators (FNOs) to construct surrogate models for predicting particle fields, replacing conventional mesh- or tree-based field solvers. To mitigate memory pressure at large particle counts, we investigate distributed training and inference strategies that combine data and operator parallelism. This poster presents performance insights and scaling behavior of these parallel approaches.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511) (POF4-511)
2. 5122 - Future Computing & Big Data Systems (POF4-512) (POF4-512)
3. 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) (POF4-511)
4. ATML-X-DEV - ATML Accelerating Devices (ATML-X-DEV) (ATML-X-DEV)
5. ZT-I-PF-5-242 - A Neural Operator Framework for Particle-based Kinetic Plasma Simulations (NEOPIC) (ZT-I-PF-5-242) (ZT-I-PF-5-242)

Appears in the scientific report 2026

---

Database coverage:

---