% 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{Schweidtmann:877527,
      author       = {Schweidtmann, Artur and Rittig, Jan and König, Andrea and
                      Grohe, Martin and Mitsos, Alexander and Dahmen, Manuel},
      title        = {{G}raph {N}eural {N}etworks for {P}rediction of {F}uel
                      {I}gnition {Q}uality},
      reportid     = {FZJ-2020-02263},
      year         = {2020},
      abstract     = {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.},
      cin          = {IEK-10},
      cid          = {I:(DE-Juel1)IEK-10-20170217},
      pnm          = {153 - Assessment of Energy Systems – Addressing Issues of
                      Energy Efficiency and Energy Security (POF3-153)},
      pid          = {G:(DE-HGF)POF3-153},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.26434/chemrxiv.12280325.v1},
      url          = {https://juser.fz-juelich.de/record/877527},
}