This project seeks to automate the identification of higher order patterns in ISR (Intelligence, Surveillance and Reconnaissance) sensed detections along with establishing normalcy. The intention is for significant changes from normalcy – anomalies – to be reported to operators as alerts requiring human assessment, decision, and action. In addition, the rationale of the alerts will also be computed and presented in a transparent way to instil user confidence in the results.

Two novel aspects for this project are: (1) the use of multiple strategies for pattern detection, including deep learning and advanced statistical modelling (e.g., Bayesian Computation); and (2) the incorporation of a Pattern Question Answering (PQA) capability to enable intuitive interaction and interrogation of the reported patterns for their rationale. PQA will build on and generalise existing capabilities in Visual Question Answering (VQA) in the fields of Artificial Intelligence and Machine Learning.

Specific application domains will be considered to support the development and demonstration of capability, including domains such as maritime traffic, space situational patterns, and land use patterns.

This project aims to focus on existing SATCOM enterprise architectures to quantify the performance gains achievable through the incorporation of Artificial Intelligence techniques.

When a satellite stops communicating it is difficult for an operator to determine the cause or nature of the failure and to determine an appropriate response.

Failures can be caused by many events including space based sub-system failures, impaired access to communication spectrum or spacecraft loss due to a collision with space debris. This project aims to advance the concept of a small, system independent suite of sensors and processors feeding information into an Artificial Intelligence (AI) based interpreter that will identify the potential jeopardy of the platform as well as propose an appropriate response.

This work is an important precursor to the development of cognitive satellites – satellites that are “context aware” of their operating environment and are able to independently self-configure to achieve increased mission resilience in a hazardous environment.

When a satellite stops communicating it is difficult for an operator to determine the cause or nature of the failure and to determine an appropriate response.

Failures can be caused by many events including space based sub-system failures, impaired access to communication spectrum or spacecraft loss due to a<br>collision with space debris. This project aims to advance the concept of a small, system independent suite of sensors and processors feeding information into an Artificial Intelligence (AI) based interpreter that will identify the potential jeopardy of the platform as well as propose an appropriate response.

This work is an important precursor to the development of cognitive satellites – satellites that are “context aware” of their operating environment and are able to independently self-configure to achieve increased mission resilience in a hazardous environment.

Satellite infrastructure provides vital communications links for a number of critical industries, including; defence, transportation, utilities, oil and gas, emergency services, banking, environment, and others. It is therefore essential that such systems are protected from adversarial interference. Cybersecurity, in particular, has proven to be an immense challenge for satellite infrastructure, especially given the inaccessibility and long life-cycle of deployed space systems. Adding to the already complex security environment, satellite systems are evolving to include a vast array of new technologies, such as the Internet of Things (IoT), which introduces even more potential for vulnerabilities to be exploited by cyber adversaries.

Although there are many aspects to satellite protection that can and should be considered, this project addresses the specific issue of control system resilience to cyber-physical threat. Simply put, the project goal is to develop a satellite-centric resilience framework that considers all aspects of cybersecurity (i.e. technology, policy, and people), thereby supporting the generation of metrics to measure a satellite’s physical resilience (i.e. the ability to anticipate, withstand, survive, recover, and adapt) to cyber threats (i.e. nation states, terrorists, criminal groups, hacktivists, and individual hackers). With this framework satellite manufacturers and operators will be able to adequately assess their resilience posture in order to understand their risk exposure, and thus make any necessary changes to ensure they are protected against cyber actors wanting to maliciously degrade, deny, disrupt, or destroy their satellites.

Tuneable Photonic Crystals for the millimeter-wave, Terahertz, and Infrared regimes have important applications for satellite communications and remote sensing.

In this application, we are proposing the fabrication of a novel metamaterial for frequency-tuneable, photonic-crystal (PhC) bandpass filters in the 0.03-30 THz region; this corresponds to wavelengths in the 10 mm to 10 𝜇𝑚 regime–which encompass mm-wave, terahertz, and far- to mid-infrared communications. As the photonic crystal filters are dynamically tuneable, they will be used to modulate carrier waves in the 0.03-30 THz frequency band, e.g. to generate FM or AM modulated signals. These wavelengths are especially useful in space, as they can be used for communications between satellites and/or high-altitude balloons. The PhC filters can also be used to “tune into” specific frequencies which are amplified, as occurs in an RF receiver. Finally, where transmitters and receivers are modulated synchronously, the encoded information can be sent securely between satellites &amp; balloons at useful rates.

The research fits best within the SmartSat “Dynamic Payloads for Communications and Earth Observations” and will provide SmartSat CRC with a key technological edge.