Quantify the performance uncertainty physics-based learning and fuse with classical orbit prediction

We have received a new award from AFOSR (Air Force Office of Scientific Research).

The project focuses on two fundamental questions:

1. how can we quantify the performance uncertainty of the learning-integrated orbit predictions?
2. how can we fuse the newly developed machine learning (ML) approach with the classical orbit prediction? Success of this project will create performance-guaranteed learning strategies, and enhance our SSA capabilities with safer, more robust, and higher accuracy orbit predictions.

We appreciate the AFOSR for the continuous support!