000877527 001__ 877527
000877527 005__ 20240712112912.0
000877527 0247_ $$2doi$$a10.26434/chemrxiv.12280325.v1
000877527 0247_ $$2Handle$$a2128/25061
000877527 037__ $$aFZJ-2020-02263
000877527 1001_ $$00000-0001-8885-6847$$aSchweidtmann, Artur$$b0
000877527 245__ $$aGraph Neural Networks for Prediction of Fuel Ignition Quality
000877527 260__ $$c2020
000877527 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1592231960_31295
000877527 3367_ $$2ORCID$$aWORKING_PAPER
000877527 3367_ $$028$$2EndNote$$aElectronic Article
000877527 3367_ $$2DRIVER$$apreprint
000877527 3367_ $$2BibTeX$$aARTICLE
000877527 3367_ $$2DataCite$$aOutput Types/Working Paper
000877527 520__ $$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 physico-chemical 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 physico-chemical 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 non-oxygenated hydrocarbons. In light of limited experimental data in the order of hundreds, we propose a combination of multi-task 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.
000877527 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$$x0
000877527 588__ $$aDataset connected to CrossRef
000877527 7001_ $$00000-0003-4645-5716$$aRittig, Jan$$b1
000877527 7001_ $$00000-0001-6372-3546$$aKönig, Andrea$$b2
000877527 7001_ $$00000-0002-0292-9142$$aGrohe, Martin$$b3
000877527 7001_ $$0P:(DE-Juel1)172025$$aMitsos, Alexander$$b4$$ufzj
000877527 7001_ $$0P:(DE-Juel1)172097$$aDahmen, Manuel$$b5$$eCorresponding author$$ufzj
000877527 773__ $$a10.26434/chemrxiv.12280325.v1
000877527 8564_ $$uhttps://juser.fz-juelich.de/record/877527/files/Schweidtmann-et-al_Manuscript_ChemRxiv_20200511.pdf$$yOpenAccess
000877527 909CO $$ooai:juser.fz-juelich.de:877527$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000877527 9101_ $$0I:(DE-588b)36225-6$$60000-0001-8885-6847$$aRWTH Aachen$$b0$$kRWTH
000877527 9101_ $$0I:(DE-588b)36225-6$$60000-0003-4645-5716$$aRWTH Aachen$$b1$$kRWTH
000877527 9101_ $$0I:(DE-588b)36225-6$$60000-0001-6372-3546$$aRWTH Aachen$$b2$$kRWTH
000877527 9101_ $$0I:(DE-588b)36225-6$$60000-0002-0292-9142$$aRWTH Aachen$$b3$$kRWTH
000877527 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172025$$aForschungszentrum Jülich$$b4$$kFZJ
000877527 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-Juel1)172025$$aRWTH Aachen$$b4$$kRWTH
000877527 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172097$$aForschungszentrum Jülich$$b5$$kFZJ
000877527 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-Juel1)172097$$aRWTH Aachen$$b5$$kRWTH
000877527 9131_ $$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$$x0
000877527 9141_ $$y2020
000877527 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000877527 920__ $$lyes
000877527 9201_ $$0I:(DE-Juel1)IEK-10-20170217$$kIEK-10$$lModellierung von Energiesystemen$$x0
000877527 9801_ $$aFullTexts
000877527 980__ $$apreprint
000877527 980__ $$aVDB
000877527 980__ $$aUNRESTRICTED
000877527 980__ $$aI:(DE-Juel1)IEK-10-20170217
000877527 981__ $$aI:(DE-Juel1)ICE-1-20170217