This project will research a novel deep learning pipeline for achieving robust and reliable forecasting of natural disaster events with hyperspectral satellite imagery. The majority of the existing machine learning algorithms do not possess the ability to forecast the occurrence of natural disasters in advance and they are only able to detect their occurrence when the disaster event happens. To address this limitation, we propose novel research which leverages the spatiotemporal modelling capability of deep learning to forecast the occurrence of natural disasters in advance using a satellite onboard execution environment. The research will be conducted using the example use cases from the application area of bushfire event forecasting considering the practical significance to Australia. The developed framework will be deployable on a CubeSat Kanyini-type mission with Hyperscout-2 payload and will use onboard hardware to execute the algorithm.

This project aims to develop a distributed testbed for satellite testing, more commonly known as FlatSat integration testing. This phase of the project will develop node devices and a minimal software ecosystem that will enable geographically separated satellite hardware to undergo integration and hardware in the loop testing over the internet.

The aim of this project is to research, develop and test goal-oriented algorithms and software that will grant a spacecraft autonomous capability to undertake its mission robustly and adaptively in real-time. The activities will focus on coupling optimisation and machine learning techniques to orbital and sensing prediction models, such that when sensing data is obtained in real time the next most optimal action can be determined.

The autonomy will be experimentally tested using the DSTG Buccaneer Main Mission (BMM) spacecraft scheduled to launch in 2023. BMM features the MANTIS payload with a controllable, deployable arm for self-inspection imaging. The project output will be a set of algorithms, methodologies, and approach to grant the spacecraft the ability to take an optimal image of itself against a backdrop of Australia in real-time. The outcomes will be learnings of the relationship between on-board and off-board autonomy that will be applicable to other spacecraft missions.

Space is becoming increasingly congested, contested, and competitive due to increased economic access to orbit, launches of distributed satellite systems, and conjunction events due to debris and conflict. For future satellite missions, on-board algorithms that can detect, track, identify, and characterise events and hazards that occur on-orbit will be required for space activities. One activity, autonomous maneuvering, is yet to be fully realised with the latest developments in artificial intelligence. Ability to test these
algorithms on the ground is limited and the capability does not exist in Australia. This project will commence with the development of a facility, and develop novel machine perception, navigation, guidance, and machine learning algorithms on space-based hardware.

Secure, reliable, timely and resilient access to information is critical to success in any modern enterprise. This is especially true for military operations across the spectrum from humanitarian assistance and disaster relief (HADR) to battle in highly contested and congested environments.

Currently, the Australian Defence Force relies upon technology developed in the 1970’s to provide network connectivity for its arguably most at risk deployed forces. These systems have well known limitations yet there has been limited research into alternate technologies to support command and control and situational awareness for the tactical warfighter. The project seeks to identify and develop technology for advanced satellite communications as a long-term option to replace or augment these current high mobility satellite communications services.

The project builds on previous SmartSat funded research with a clear focus on three critical technologies to address this gap:

1. Flexible and adaptive communications waveforms designed for the tactical user
2. System wide network management to optimise resource allocation for capacity, coverage and resilience
3. Reconfigurable, agile coverage using multi-frequency, multi-beam antenna arrays (pending future external funding)

This project will refine designs of the tactical communications waveform and initiate research into algorithms that optimise coverage and capacity of heterogeneous/hybrid satellite constellations including an initial demonstration implemented in software. The aim is to accelerate the technology development and understand risks in order to define a follow-on project, funded externally to SmartSat, that will develop a prototype space payload capable of integration with an experimental satellite. This subsequent phase will use the results from this project to inform the agile, multi-beam, multi-band phased array design and the development of initial user terminals. It is expected maturing this technology to the point it can be demonstrated in space will cost $5M – $10M and take three years. This is beyond the resource available from SmartSat so this project will include the
submission of a bid for Defence innovation/prototyping funding to support maturation of the critical underlying technology from TRL4/5 to TRL8.

The target technology demonstration and experimentation program for this research is the Defence STaR Shot for Resilient Multi-mission Space (RMS). The demonstration will showcase a game-changing approach to the provision of resilient satellite communications to the tactical warfighter.

Note: Within this project, tactical communications means systems supporting high levels of user mobility which requires the use of very small aperture terminals (e.g. handheld) and the ability to operate over complex RF propagation channels.

Immense growth in the use of spacecraft and the orbital debris population is driving an urgent need for effective space traffic management (STM) and responsible use of space. Currently, orbital knowledge (position and velocity) is primarily obtained by ground-based remote sensing (e.g., radar, optical, etc.) which results in significant position and velocity uncertainty.

These uncertainties complicate conjunction assessments and subsequent collision avoidance manoeuvres.
The goal is to develop a self-sufficient, bolt-on system that can be used for active and real-time orbital knowledge (position and velocity) from the spacecraft.

A design approach to improve Space Traffic Management (STM):

• Like an ADS-B for Spacecraft (analogous to air trafic management moving from radar to active GPS broadcast)
• Chip continuously broadcasts a ‘ping’ to listeners
• Determine position and velocity through RF geolocation (and/or GPS)
• Low SWAP and no interface/interaction with spacecraft (‘bolt-on’)
• Simple processor + Transmitter + Battery + Mini Solar array (+ GPS)
• Provides information even for dead spacecraft or rocket bodies

We propose a short-term scoping study to evaluate the feasibility of this onboard beacon that can be used to provide high-precision, real-time orbital information – assessing ITU and RF broadcasting limitations, technical extent of existing capabilities and connecting with relevant Australian (and international) entities and regulatory bodies to advance the concept to implementation.