A machine learning framework for scattering kernel derivation using molecular dynamics data in very low Earth orbit

The free molecular flow regime in very low Earth orbit makes gas–surface interactions (GSIs) crucial for satellite aerodynamic modeling. The Direct Simulation Monte Carlo (DSMC) method is required to estimate aerodynamic forces due to the breakdown of the continuum assumption. DSMC typically uses the Maxwell model for GSI, treating it as a superposition of diffuse and specular reflections with a constant accommodation coefficient. In reality, this coefficient varies with several factors, including the angle and magnitude of incident velocity. A high-precision GSI model could significantly improve aerodynamic optimization and the design of intakes for atmospheric breathing propulsion systems, refining mission planning, reducing fuel needs, and extending operational lifetimes. To gain a deep understanding of the GSI at the microscopic level, molecular dynamics (MD) simulations provide valuable insight into the physical processes involved. However, due to computational limitations, simulating an entire satellite is impractical. Instead, we use MD to analyze the impact of selected velocity vectors on a amorphous Al2O3 surface. The obtained scattering kernels for the respective velocity vectors are then used to train a conditional variational autoencoder (cVAE). This model is able to generate scattering kernels for any incident velocity vector and can be integrated into DSMC simulations, significantly enhancing their accuracy. Applications of this model on a flat plate have shown that the cVAE is able to predict the shift from diffuse to quasi-specular reflection with increasing polar angle. Additionally, the aerodynamic coefficients and molecular fluxes are considerably different from those obtained with the Maxwell model.