A machine learning and feature engineering approach for the prediction of the uncontrolled re-entry of space objects

The continuously growing number of objects orbiting around the Earth is expected to be accompanied by an increasing frequency of objects re-entering the Earth's atmosphere. Many of these re-entries will be uncontrolled, making their prediction challenging and subject to several uncertainties. Traditionally, re-entry predictions are based on the propagation of the object's dynamics using state-of-the-art modelling techniques for the forces acting on the object. However, modelling errors, particularly related to the prediction of atmospheric drag may result in poor prediction accuracies. In this context, we explore the possibility to perform a paradigm shift, from a physics-based approach to a data-driven approach. To this aim, we present the development of a deep learning model for the re-entry prediction of uncontrolled objects in Low Earth Orbit (LEO). The model is based on a modified version of the Sequence-to-Sequence architecture and is trained on the average altitude profile as derived from a set of Two-Line Element (TLE) data of over 400 bodies. The novelty of the work consists in introducing in the deep learning model, alongside the average altitude, three new input features: a drag-like coefficient (B*), the average solar index, and the area-to-mass ratio of the object. The developed model is tested on a set of objects studied in the Inter-Agency Space Debris Coordination Committee (IADC) campaigns. The results show that the best performances are obtained on bodies characterised by the same drag-like coefficient and eccentricity distribution as the training set.

Constrained optimisation of preliminary spacecraft configurations under the design-for-demise paradigm

In the past few years, the interest towards the implementation of design-for-demise measures has increased steadily. Most mid-sized satellites currently launched and already in orbit fail to comply with the casualty risk threshold of 0.0001. Therefore, satellites manufacturers and mission operators need to perform a disposal through a controlled re-entry, which has a higher cost and increased complexity. Through the design-for-demise paradigm, this additional cost and complexity can be removed as the spacecraft is directly compliant with the casualty risk regulations. However, building a spacecraft such that most of its parts will demise may lead to designs that are more vulnerable to space debris impacts, thus compromising the reliability of the mission. In fact, the requirements connected to the demisability and the survivability are in general competing. Given this competing nature, trade-off solutions can be found, which favour the implementation of design-for-demise measures while still maintaining the spacecraft resilient to space debris impacts. A multi-objective optimisation framework has been developed by the authors in previous works. The framework's objective is to find preliminary design solutions considering the competing nature of the demisability and the survivability of a spacecraft since the early stages of the mission design. In this way, a more integrated design can be achieved. The present work focuses on the improvement of the multi-objective optimisation framework by including constraints. The paper shows the application of the constrained optimisation to two relevant examples: the optimisation of a tank assembly and the optimisation of a typical satellite configuration.

Spacecraft design optimisation for demise and survivability

Among the mitigation measures introduced to cope with the space debris issue there is the de-orbiting of decommissioned satellites. Guidelines for re-entering objects call for a ground casualty risk no higher than 0.0001. To comply with this requirement, satellites can be designed through a design-for-demise philosophy. Still, a spacecraft designed to demise has to survive the debris-populated space environment for many years. The demisability and the survivability of a satellite can both be influenced by a set of common design choices such as the material selection, the geometry definition, and the position of the components. Within this context, two models have been developed to analyse the demise and the survivability of satellites. Given the competing nature of the demisability and the survivability, a multi-objective optimisation framework was developed, with the aim to identify trade-off solutions for the preliminary design of satellites. As the problem is nonlinear and involves the combination of continuous and discrete variables, classical derivative based approaches are unsuited and a genetic algorithm was selected instead. The genetic algorithm uses the developed demisability and survivability criteria as the fitness functions of the multi-objective algorithm. The paper presents a test case, which considers the preliminary optimisation of tanks in terms of material, geometry, location, and number of tanks for a representative Earth observation mission. The configuration of the external structure of the spacecraft is fixed. Tanks were selected because they are sensitive to both design requirements: they represent critical components in the demise process and impact damage can cause the loss of the mission because of leaking and ruptures. The results present the possible trade off solutions, constituting the Pareto front obtained from the multi-objective optimisation.