This title appears in the Scientific Report :
2020
Please use the identifier:
http://hdl.handle.net/2128/25061 in citations.
Please use the identifier: http://dx.doi.org/10.26434/chemrxiv.12280325.v1 in citations.
Graph Neural Networks for Prediction of Fuel Ignition Quality
Graph Neural Networks for Prediction of Fuel Ignition Quality
Prediction 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 f...
Saved in:
Personal Name(s): | Schweidtmann, Artur |
---|---|
Rittig, Jan / König, Andrea / Grohe, Martin / Mitsos, Alexander / Dahmen, Manuel (Corresponding author) | |
Contributing Institute: |
Modellierung von Energiesystemen; IEK-10 |
Imprint: |
2020
|
DOI: |
10.26434/chemrxiv.12280325.v1 |
Document Type: |
Preprint |
Research Program: |
Assessment of Energy Systems – Addressing Issues of Energy Efficiency and Energy Security |
Link: |
OpenAccess |
Publikationsportal JuSER |
Please use the identifier: http://dx.doi.org/10.26434/chemrxiv.12280325.v1 in citations.
LEADER | 04672nam a2200625 a 4500 | ||
---|---|---|---|
001 | 877527 | ||
005 | 20240712112912.0 | ||
024 | 7 | |a 10.26434/chemrxiv.12280325.v1 |2 doi | |
024 | 7 | |a 2128/25061 |2 Handle | |
037 | |a FZJ-2020-02263 | ||
100 | 1 | |a Schweidtmann, Artur |0 0000-0001-8885-6847 |b 0 | |
245 | |a Graph Neural Networks for Prediction of Fuel Ignition Quality | ||
260 | |c 2020 | ||
520 | |a Prediction 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. | ||
588 | |a Dataset connected to CrossRef | ||
700 | 1 | |a Rittig, Jan |0 0000-0003-4645-5716 |b 1 | |
700 | 1 | |a König, Andrea |0 0000-0001-6372-3546 |b 2 | |
700 | 1 | |a Grohe, Martin |0 0000-0002-0292-9142 |b 3 | |
700 | 1 | |a Mitsos, Alexander |0 P:(DE-Juel1)172025 |b 4 |u fzj | |
700 | 1 | |a Dahmen, Manuel |0 P:(DE-Juel1)172097 |b 5 |e Corresponding author |u fzj | |
773 | |a 10.26434/chemrxiv.12280325.v1 | ||
856 | 4 | |u http://juser.fz-juelich.de/record/877527/files/Schweidtmann-et-al_Manuscript_ChemRxiv_20200511.pdf |y OpenAccess | |
909 | C | O | |o oai:juser.fz-juelich.de:877527 |p openaire |p open_access |p VDB |p driver |p dnbdelivery |
910 | 1 | |a RWTH Aachen |0 I:(DE-588b)36225-6 |k RWTH |b 0 |6 0000-0001-8885-6847 | |
910 | 1 | |a RWTH Aachen |0 I:(DE-588b)36225-6 |k RWTH |b 1 |6 0000-0003-4645-5716 | |
910 | 1 | |a RWTH Aachen |0 I:(DE-588b)36225-6 |k RWTH |b 2 |6 0000-0001-6372-3546 | |
910 | 1 | |a RWTH Aachen |0 I:(DE-588b)36225-6 |k RWTH |b 3 |6 0000-0002-0292-9142 | |
910 | 1 | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 4 |6 P:(DE-Juel1)172025 | |
910 | 1 | |a RWTH Aachen |0 I:(DE-588b)36225-6 |k RWTH |b 4 |6 P:(DE-Juel1)172025 | |
910 | 1 | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 5 |6 P:(DE-Juel1)172097 | |
910 | 1 | |a RWTH Aachen |0 I:(DE-588b)36225-6 |k RWTH |b 5 |6 P:(DE-Juel1)172097 | |
913 | 1 | |a DE-HGF |l Technologie, Innovation und Gesellschaft |1 G:(DE-HGF)POF3-150 |0 G:(DE-HGF)POF3-153 |2 G:(DE-HGF)POF3-100 |v Assessment of Energy Systems – Addressing Issues of Energy Efficiency and Energy Security |x 0 |4 G:(DE-HGF)POF |3 G:(DE-HGF)POF3 |b Energie | |
914 | 1 | |y 2020 | |
915 | |a OpenAccess |0 StatID:(DE-HGF)0510 |2 StatID | ||
980 | 1 | |a FullTexts | |
980 | |a preprint | ||
980 | |a VDB | ||
980 | |a UNRESTRICTED | ||
980 | |a I:(DE-Juel1)IEK-10-20170217 | ||
536 | |a Assessment of Energy Systems – Addressing Issues of Energy Efficiency and Energy Security |0 G:(DE-HGF)POF3-153 |c POF3-153 |f POF III |x 0 | ||
336 | |a preprint |2 DRIVER | ||
336 | |a Excerpta medica / 28 |0 28 |2 EndNote | ||
336 | |a WORKING_PAPER |2 ORCID | ||
336 | |a Preprint |b preprint |m preprint |0 PUB:(DE-HGF)25 |s 1592231960_31295 |2 PUB:(DE-HGF) | ||
336 | |a Output Types/Working Paper |2 DataCite | ||
336 | |a ARTICLE |2 BibTeX | ||
981 | |a I:(DE-Juel1)ICE-1-20170217 | ||
920 | |l yes | ||
920 | |k Modellierung von Energiesystemen; IEK-10 |0 I:(DE-Juel1)IEK-10-20170217 |l Modellierung von Energiesystemen |x 0 | ||
990 | |a Schweidtmann, Artur |0 0000-0001-8885-6847 |b 0 | ||
991 | |a Dahmen, Manuel |0 P:(DE-Juel1)172097 |b 5 |e Corresponding author |u fzj | ||
991 | |a Mitsos, Alexander |0 P:(DE-Juel1)172025 |b 4 |u fzj | ||
991 | |a Grohe, Martin |0 0000-0002-0292-9142 |b 3 | ||
991 | |a König, Andrea |0 0000-0001-6372-3546 |b 2 | ||
991 | |a Rittig, Jan |0 0000-0003-4645-5716 |b 1 |