Back to Search
Start Over
Graph Neural Networks for Prediction of Fuel Ignition Quality
- Source :
- Energy & fuels 34(9), 11395-11407 (2020). doi:10.1021/acs.energyfuels.0c01533
- Publication Year :
- 2020
- Publisher :
- American Chemical Society (ACS), 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.
- Subjects :
- Quantitative structure–activity relationship
Computer science
Graph neural networks
General Chemical Engineering
media_common.quotation_subject
Energy Engineering and Power Technology
02 engineering and technology
Machine learning
computer.software_genre
law.invention
Task (project management)
chemistry.chemical_compound
020401 chemical engineering
law
Molecular graph
Quality (business)
0204 chemical engineering
media_common
business.industry
Deep learning
Supervised learning
021001 nanoscience & nanotechnology
Ensemble learning
Backpropagation
Ignition system
Fuel Technology
chemistry
ddc:660
Graph (abstract data type)
Artificial intelligence
Transfer of learning
0210 nano-technology
business
computer
Subjects
Details
- ISSN :
- 15205029 and 08870624
- Volume :
- 34
- Database :
- OpenAIRE
- Journal :
- Energy & Fuels
- Accession number :
- edsair.doi.dedup.....175286d65ef830ffcc9a803da6e91c40