Aviation accounts for a relatively small share of global emissions but is one of the most challenging sectors to decarbonize. Despite reductions in flying during the Covid-19 lockdowns, demand is expected to grow rapidly through 2030. New aircraft can be up to 20% more efficient than the models they replace, but growth in activity has historically outpaced efficiency improvement. Technological innovation is needed across the sector, including in the production of low-emission fuels, improvements in aircraft and engines, and operational optimization. The limited studies in literature and the immediate need for alternate jet fuels emphasizes the importance of understanding the behavior of various SAF-conventional fuel combinations and developing effective strategies for predicting the properties using low fuel volumes is important for attaining optimal fuel blends.

The objective is to investigate the properties of sustainable aviation fuel (SAF) blends with conventional fuels and develop chemical kinetic models that can be validated through experimental data. Property prediction using machine learning models will be developed for quick and effective screening of fuel blends. Our work will focus on predicting the properties of e-fuel and biofuel blends with conventional jet fuels. Different fuel blends will be studied by varying the ratio of SAF and the conventional jet fuel