Next-Generation Re-Entry Aerothermodynamic Modeling of Space Debris Using Machine Learning

The number of resident space objects re-entering the atmosphere is expected to rise with increased space activity over recent years and future projections. Predicting the survival and impact location of the medium to large sized re-entering objects becomes important as they can cause on ground casualties and damage to property. Uncertainties associated with the re-entry process makes necessary a probabilistic approach, which can be computationally expensive when using high-fidelity numerical methods for estimating aerothermodynamic properties. To date, object-oriented analysis is the dominant tool used for atmospheric re-entry modeling and simulation, where aerothermodynamic coefficients are used to determine the risk a re-entering object poses to the ground through the use of analytical formulations. Closed form solutions are limited to convex objects in the free molecular and continuum flow regime as well as stagnation point estimates. In the transition regime (75-150 km), a combination of bridging and shape functions are used for the different primitive objects. In this work, the power of deep learning is used to develop next-generation models for the aerothermodynamic modeling (drag coefficient and full body heating distributions) in the transition flow regime for both convex and concave primitive shapes (sphere, cube, and cylinder). The increasing Low-Earth Orbit population puts more stress on NASA's recommended allowable ground risks and makes this a timely contribution.