Comprehensive accurate prediction of critical jet fuel properties with multiple machine learning models

Abstract

Quantitative structure–property relationship (QSPR) model development driven by emerging machine learning (ML) shows promise for accelerating design and preparation of jet fuels with complex hydrocarbon compositions. In this work, we collected 104 jet fuels from different refineries, determined the detailed components of the fuel composition, and tested the fuel properties (density, viscosity, net heat of combustion, freezing point and flash point) using standard methods to form a database of molecule structure/composition and properties. Subsequently, six mainstream ML algorithms were adopted to establish the QSPR models, in which the prediction accuracy of the best ML models for each property is improved to above 0.93. Finally, the best ML property models are applied to predict unseen RP-3 fuels, and all prediction errors are within acceptable limits. This effort not only provides valuable data for the construction of the jet fuel database, but also provides tools for predicting its critical properties.