% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Friedemann:1037349,
author = {Friedemann, Sebastian and Keller, Kai and Lu, Yen-Sen and
Raffin, Bruno and Bautista-Gomez, Leonardo},
title = {{D}ynamic load/propagate/store for data assimilation with
particle filters on supercomputers},
journal = {Journal of computational science},
volume = {76},
issn = {1877-7503},
address = {Amsterdam [u.a.]},
publisher = {Elsevier},
reportid = {FZJ-2025-00662},
pages = {102229},
year = {2024},
abstract = {Several ensemble-based Data Assimilation (DA) methods rely
on a propagate/update cycle, where a potentially compute
intensive simulation code propagates multiple states for
several consecutive time steps, that are then analyzed to
update the states to be propagated for the next cycle. In
this paper we focus on DA methods where the update can be
computed by gathering only lightweight data obtained
independently from each of the propagated states. This
encompasses particle filters where one weight is computed
from each state, but also methods like Approximate Bayesian
Computation (ABC) or Markov Chain Monte Carlo (MCMC). Such
methods can be very compute intensive and running
efficiently at scale on supercomputers is challenging. This
paper proposes a framework based on an elastic and
fault-tolerant runner/server architecture minimizing data
movements while enabling dynamic load balancing. Our
approach relies on runners that load, propagate and store
particles from an asynchronously managed distributed
particle cache permitting particles to move from one runner
to another in the background while particle propagation
proceeds. The framework is validated with a bootstrap
particle filter with the WRF simulation code. We handle up
to 2555 particles on 20,442 compute cores. Compared to a
file-based implementation, our solution spends up to 2.84
less resources (cores×seconds) per particle.},
cin = {JSC},
ddc = {004},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / EoCoE-II - Energy
Oriented Center of Excellence : toward exascale for energy
(824158)},
pid = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)824158},
typ = {PUB:(DE-HGF)16},
UT = {WOS:001185868400001},
doi = {10.1016/j.jocs.2024.102229},
url = {https://juser.fz-juelich.de/record/1037349},
}