Search Results

In order to reduce the carbon footprint of the Internal Combustion Engine (ICE), biofuels have been in use for a number of years. One of the problems with first-generation (1G) biofuels however is their competition with food production. In search of second-generation (2G) biofuels, that are not in competition with food agriculture, a novel biorefinery process has been developed to produce biofuel from woody biomass sources. This novel technique, part of the Belgian federal government funded Ad-Libio project, uses a catalytic process that operates at low temperature and is able to convert 2G feedstock into a stable light naphtha. The bulk of the yield consists out of hydrocarbons containing five to six carbon atoms, along with a fraction of oxygenates and aromatics. The oxygen content and the aromaticity of the hydrocarbons can be varied, both of which have a significant influence on the fuel’s combustion and emission characteristics when used in Internal Combustion Engines.

Despite the increasing number of electrified vehicles the transportation system still largely depends on the use of fossil fuels. One way to more rapidly reduce the dependency on fossil fuels in transport is to replace them with biofuels. Evaluating the potential of different biofuels in different applications requires knowledge of their physicochemical properties. In chemistry, message passing neural networks (MPNNs) correlating the atoms and bonds of a molecule to properties have shown promising results in predicting the properties of individual chemical components. In this article a machine learning approach, developed from the message passing neural network called Chemprop, is evaluated for the prediction of multiple properties of organic molecules (containing carbon, nitrogen, oxygen and hydrogen). A novel approach using transfer learning based on estimated property values from theoretical estimation methods is applied.