Classification of Low Earth Orbit (LEO) Resident Space Objects' (RSO) Light Curves Using a Support Vector Machine (SVM) and Long Short-Term Memory (LSTM).

Light curves are plots of brightness measured over time. In the field of Space Situational Awareness (SSA), light curves of Resident Space Objects (RSOs) can be utilized to infer information about an RSO such as the type of object, its attitude, and its shape. Light curves of RSOs in geostationary orbit (GEO) have been a main research focus for many years due to the availability of long time series data spanning hours. Given that a large portion of RSOs are in low Earth orbit (LEO), it is of great importance to study trends in LEO light curves as well. The challenge with LEO light curves is that they tend to be short, typically no longer than a few minutes, which makes them difficult to analyze with typical time series techniques. This study presents a novel approach to observational LEO light curve classification. We extract features from light curves using a wavelet scattering transformation which is used as an input for a machine learning classifier. We performed light curve classification using both a conventional machine learning approach, namely a support vector machine (SVM), and a deep learning technique, long short-term memory (LSTM), to compare the results. LSTM outperforms SVM for LEO light curve classification with a 92% accuracy. This proves the viability of RSO classification by object type and spin rate from real LEO light curves.

RSOnet: An Image-Processing Framework for a Dual-Purpose Star Tracker as an Opportunistic Space Surveillance Sensor.

A catalogue of over 22,000 objects in Earth's orbit is currently maintained, and that number is expected to double within the next decade. Novel data collection regimes are needed to scale our ability to detect, track, classify and characterize resident space objects in a crowded low Earth orbit. This research presents RSOnet, an image-processing framework for space domain awareness using star trackers. Star trackers are cost-effective, flight proven, and require basic image processing to be used as an attitude-determination sensor. RSOnet is designed to augment the capabilities of a star tracker by becoming an opportunistic space-surveillance sensor. Our research demonstrates that star trackers are a feasible source for RSO detections in LEO by demonstrating the performance of RSOnet on real detections from a star-tracker-like imager in space. RSOnet convolutional-neural-network model architecture, graph-based multi-object classifier and characterization results are described in this paper.

Uncertainty Quantification for Space Situational Awareness and Traffic Management.

This paper presents a sensor-orientated approach to on-orbit position uncertainty generation and quantification for both ground-based and space-based surveillance applications. A mathematical framework based on the least squares formulation is developed to exploit real-time navigation measurements and tracking observables to provide a sound methodology that supports separation assurance and collision avoidance among Resident Space Objects (RSO). In line with the envisioned Space Situational Awareness (SSA) evolutions, the method aims to represent the navigation and tracking errors in the form of an uncertainty volume that accurately depicts the size, shape, and orientation. Simulation case studies are then conducted to verify under which sensors performance the method meets Gaussian assumptions, with a greater view to the implications that uncertainty has on the cyber-physical architecture evolutions and Cognitive Human-Machine Systems required for Space Situational Awareness and the development of a comprehensive Space Traffic Management framework.