000888680 001__ 888680
000888680 005__ 20240712112908.0
000888680 0247_ $$2doi$$a10.1021/acs.energyfuels.0c01533
000888680 0247_ $$2ISSN$$a0887-0624
000888680 0247_ $$2ISSN$$a1520-5029
000888680 0247_ $$2Handle$$a2128/26507
000888680 0247_ $$2altmetric$$aaltmetric:89222025
000888680 0247_ $$2WOS$$aWOS:000574904900087
000888680 037__ $$aFZJ-2020-05115
000888680 082__ $$a660
000888680 1001_ $$0P:(DE-HGF)0$$aSchweidtmann, Artur M.$$b0
000888680 245__ $$aGraph Neural Networks for Prediction of Fuel Ignition Quality
000888680 260__ $$aColumbus, Ohio$$bAmerican Chemical Society$$c2020
000888680 3367_ $$2DRIVER$$aarticle
000888680 3367_ $$2DataCite$$aOutput Types/Journal article
000888680 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1607698171_537
000888680 3367_ $$2BibTeX$$aARTICLE
000888680 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000888680 3367_ $$00$$2EndNote$$aJournal Article
000888680 520__ $$aPrediction of combustion-related properties of (oxygenated) hydrocarbons is an important and challenging task for which quantitative structure–property relationship (QSPR) models are frequently employed. Recently, a machine learning method, graph neural networks (GNNs), has shown promising results for the prediction of structure–property relationships. GNNs utilize a graph representation of molecules, where atoms correspond to nodes and bonds to edges containing information about the molecular structure. More specifically, GNNs learn physicochemical properties as a function of the molecular graph in a supervised learning setup using a backpropagation algorithm. This end-to-end learning approach eliminates the need for selection of molecular descriptors or structural groups, as it learns optimal fingerprints through graph convolutions and maps the fingerprints to the physicochemical properties by deep learning. We develop GNN models for predicting three fuel ignition quality indicators, i.e., the derived cetane number (DCN), the research octane number (RON), and the motor octane number (MON), of oxygenated and nonoxygenated hydrocarbons. In light of limited experimental data in the order of hundreds, we propose a combination of multitask learning, transfer learning, and ensemble learning. The results show competitive performance of the proposed GNN approach compared to state-of-the-art QSPR models, making it a promising field for future research. The prediction tool is available via a web front-end at www.avt.rwth-aachen.de/gnn.
000888680 536__ $$0G:(DE-HGF)POF3-153$$a153 - Assessment of Energy Systems – Addressing Issues of Energy Efficiency and Energy Security (POF3-153)$$cPOF3-153$$fPOF III$$x0
000888680 588__ $$aDataset connected to CrossRef
000888680 7001_ $$0P:(DE-HGF)0$$aRittig, Jan G.$$b1
000888680 7001_ $$0P:(DE-HGF)0$$aKönig, Andrea$$b2
000888680 7001_ $$0P:(DE-HGF)0$$aGrohe, Martin$$b3
000888680 7001_ $$0P:(DE-Juel1)172025$$aMitsos, Alexander$$b4$$ufzj
000888680 7001_ $$0P:(DE-Juel1)172097$$aDahmen, Manuel$$b5$$eCorresponding author$$ufzj
000888680 773__ $$0PERI:(DE-600)1483539-3$$a10.1021/acs.energyfuels.0c01533$$gVol. 34, no. 9, p. 11395 - 11407$$n9$$p11395 - 11407$$tEnergy & fuels$$v34$$x1520-5029$$y2020
000888680 8564_ $$uhttps://juser.fz-juelich.de/record/888680/files/acs.energyfuels.0c01533.pdf$$yRestricted
000888680 8564_ $$uhttps://juser.fz-juelich.de/record/888680/files/revised_manuscript_clean.pdf$$yPublished on 2020-08-12. Available in OpenAccess from 2021-08-12.
000888680 909CO $$ooai:juser.fz-juelich.de:888680$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000888680 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b0$$kRWTH
000888680 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b1$$kRWTH
000888680 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b2$$kRWTH
000888680 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b3$$kRWTH
000888680 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172025$$aForschungszentrum Jülich$$b4$$kFZJ
000888680 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-Juel1)172025$$aRWTH Aachen$$b4$$kRWTH
000888680 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172097$$aForschungszentrum Jülich$$b5$$kFZJ
000888680 9131_ $$0G:(DE-HGF)POF3-153$$1G:(DE-HGF)POF3-150$$2G:(DE-HGF)POF3-100$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bEnergie$$lTechnologie, Innovation und Gesellschaft$$vAssessment of Energy Systems – Addressing Issues of Energy Efficiency and Energy Security$$x0
000888680 9141_ $$y2020
000888680 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2020-09-12
000888680 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2020-09-12
000888680 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2020-09-12
000888680 915__ $$0StatID:(DE-HGF)0530$$2StatID$$aEmbargoed OpenAccess
000888680 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bENERG FUEL : 2018$$d2020-09-12
000888680 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2020-09-12
000888680 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2020-09-12
000888680 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2020-09-12
000888680 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2020-09-12
000888680 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2020-09-12$$wger
000888680 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2020-09-12
000888680 920__ $$lyes
000888680 9201_ $$0I:(DE-Juel1)IEK-10-20170217$$kIEK-10$$lModellierung von Energiesystemen$$x0
000888680 9801_ $$aFullTexts
000888680 980__ $$ajournal
000888680 980__ $$aVDB
000888680 980__ $$aUNRESTRICTED
000888680 980__ $$aI:(DE-Juel1)IEK-10-20170217
000888680 981__ $$aI:(DE-Juel1)ICE-1-20170217