The downstream oil and gas industry constantly faces the challenge of producing low emission fuels for existing engines and advanced fuels for future engine technologies. Fast and reliable models are needed to monitor and blend various refinery streams for producing specification fuels whilst maximizing the economic gain from the barrel. A barrier to the development of such models is the lack of sufficient and reliable data on the properties of different chemical classes that are present in crude oil. Artificial intelligence (AI) based computing systems like artificial neural networks (ANN) have recently found increasing applications in predicting complex physical and chemical phenomena. This proposal aims to develop robust AI tools for predicting physical, thermo-chemical and combustion properties of oxygenated fuels by generating a large and reliable data-set required to train the AI models and to understand the impact of different functional groups on fuel performance characteristics. Transportation fuels like gasoline, diesel, jet fuel etc. are made up of several hundred to thousands of individual molecules which are in turn made up of a small number of molecular fragments or functional groups that determine the physical, thermo-chemical and combustion properties of the fuel. Fossil fuels can be dis-assembled into various underlying functional groups, namely paraffinic CH3 groups, paraffinic CH2 groups, paraffinic CH groups, olefinic -CH=CH2 groups, naphthenic CH-CH2 groups and aromatic C-CH groups. Biomass derived fuels are sometimes blended with fossil fuels for improving ignition properties like cetane number or antiknock quality like octane number, and these bio-fuels possess additional functional groups like alcoholic OH and ether O groups. Blends containing various chemical classes like n-paraffins, iso-paraffins, naphthenes, olefins, aromatics, alcohols and ethers will be employed. Physical properties like viscosity and density;