Construction of a three-component thermophysical property surrogate model for RP-3 aviation kerosene via machine learning-augmented molecular dynamics

Key Points

• The surrogate model predicts thermophysical properties accurately, improving efficiency in simulations.
• Key metrics indicate a significant reduction in computational time by approximately 30% for RP-3 kerosene.
• Modeling employed a machine learning approach integrated with molecular dynamics for property estimation.
• Findings highlight the potential for more efficient computational methods in thermophysical property analysis.