001052700 001__ 1052700
001052700 005__ 20260127203443.0
001052700 020__ $$a978-3-031-85702-7 (print)
001052700 020__ $$a978-3-031-85703-4 (electronic)
001052700 0247_ $$2doi$$a10.1007/978-3-031-85703-4_6
001052700 0247_ $$2ISSN$$a0302-9743
001052700 0247_ $$2ISSN$$a1611-3349
001052700 0247_ $$2datacite_doi$$a10.34734/FZJ-2026-01057
001052700 037__ $$aFZJ-2026-01057
001052700 1001_ $$0P:(DE-Juel1)177985$$aRüttgers, Mario$$b0$$eCorresponding author
001052700 1112_ $$aInternational Conference on Parallel Processing and Applied Mathematics$$cOstrava$$d2024-09-08 - 2024-09-11$$gPPAM 2024$$wCzech Republic
001052700 245__ $$aParallel Reinforcement Learning and Gaussian Process Regression for Improved Physics-Based Nasal Surgery Planning
001052700 260__ $$aCham$$bSpringer Nature Switzerland$$c2025
001052700 29510 $$aParallel Processing and Applied Mathematics
001052700 300__ $$a79 - 96
001052700 3367_ $$2ORCID$$aCONFERENCE_PAPER
001052700 3367_ $$033$$2EndNote$$aConference Paper
001052700 3367_ $$2BibTeX$$aINPROCEEDINGS
001052700 3367_ $$2DRIVER$$aconferenceObject
001052700 3367_ $$2DataCite$$aOutput Types/Conference Paper
001052700 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1769497552_21828
001052700 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
001052700 4900_ $$aLecture Notes in Computer Science$$v15581
001052700 520__ $$aSeptoplasty and turbinectomy are among the most frequentbut also most debated interventions in the field of rhinology. A previouslydeveloped tool enhances surgery planning by physical aspects of respi-ration, i.e., for the first time a reinforcement learning (RL) algorithm iscombined with large-scale computational fluid dynamics (CFD) simula-tions to plan anti-obstructive surgery. In the current study, an improve-ment of the tool’s predictive capabilities is investigated for the afore-mentioned types of surgeries by considering two approaches: (i) trainingof parallel environments is executed on multiple ranks and the agentsof each environment share their experience in a pre-defined interval and(ii) for some of the state-reward combinations the CFD solver is replacedby a Gaussian process regression (GPR) model for an improved compu-tational efficiency. It is found that employing a parallel RL algorithmimproves the reliability of the surgery planning tool in finding the globaloptimum. However, parallel training leads to a larger number of state-reward combinations that need to be computed by the CFD solver. Thisoverhead is compensated by replacing some of the computations withthe GPR algorithm, i.e., around 6% of the computations can be savedwithout significantly degrading the predictions’ accuracy. Nevertheless,increasing the number of state-reward combinations predicted by theGPR algorithm only works to a certain extent, since this also leads tolarger errors.
001052700 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001052700 536__ $$0G:(DE-Juel-1)SDLFSE$$aSDLFSE - SDL Fluids & Solids Engineering (SDLFSE)$$cSDLFSE$$x1
001052700 536__ $$0G:(EU-Grant)101136269$$aHANAMI - Hpc AlliaNce for Applications and supercoMputing Innovation: the Europe - Japan collaboration (101136269)$$c101136269$$x2
001052700 588__ $$aDataset connected to CrossRef Book Series, Journals: juser.fz-juelich.de
001052700 7001_ $$00009-0000-7159-8220$$aHübenthal, Fabian$$b1
001052700 7001_ $$00000-0001-6555-9575$$aTsubokura, Makoto$$b2
001052700 7001_ $$0P:(DE-Juel1)165948$$aLintermann, Andreas$$b3
001052700 770__ $$z978-3-031-85702-7=978-3-031-85703-4
001052700 773__ $$a10.1007/978-3-031-85703-4_6
001052700 8564_ $$uhttps://juser.fz-juelich.de/record/1052700/files/978-3-031-85703-4_6.pdf$$yOpenAccess
001052700 909CO $$ooai:juser.fz-juelich.de:1052700$$popenaire$$popen_access$$pdriver$$pVDB$$pec_fundedresources$$pdnbdelivery
001052700 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165948$$aForschungszentrum Jülich$$b3$$kFZJ
001052700 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001052700 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-28
001052700 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001052700 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001052700 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2024-12-28$$wger
001052700 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001052700 980__ $$acontrib
001052700 980__ $$aVDB
001052700 980__ $$aUNRESTRICTED
001052700 980__ $$acontb
001052700 980__ $$aI:(DE-Juel1)JSC-20090406
001052700 9801_ $$aFullTexts