The key innovation of this project is the development of robust methods for the integration of radar-based EO data into current and emerging systems for monitoring the impact of fire on vegetation. Rapid fire extent mapping, including fire progression of large wildfires, will be based on dense time-series of synthetic aperture radar (SAR), optical data and machine learning. The research will also explore the capabilities of SAR and LiDAR data, integrated with optical data, for distinguishing structural characteristics of post-fire recovery dynamics.

The overarching focus of the research is on the integration of multi-sensor EO data to fill key gaps in operational monitoring of the impacts of wildfire. The project aims to support land and fire managers to make more informed decisions, by developing more accurate and timely measures of burnt area extent and tools for monitoring post-fire recovery.

Flooding is a common and extremely impactful event within Australia and around the world. For example, the March 2021 Australian floods are a series of floods that began from 18 March 2021 which have affected New South Wales, from the North Coast to the Sydney metropolitan area in the south, in a disaster described as a “one-in-100-year event”. Additionally, far-south and far-southeast communities in Queensland were also greatly affected by flooding and heavy rainfall.

The aim of this project is to develop and operationalise smart analysis of SAR and optical satellite imagery (primarily NovaSAR and Sentinel missions) to address time-critical applications such as flood mapping (2D) and floodplain water harvesting (3D), based on many years of research in this area by the project team since 2009. Project activities include feasibility studies, remote sensing software
development (analytic toolbox) and extensive case studies.

The expected outcomes are:

1. A suite of near real-time, cross platform, scalable and operational tools for mapping floods with satellite remote sensing, ready for flood management agencies to takeover and/or private sector to commercialise, and improve volume estimate during the floodplain harvesting event for the Murray-Darling Basin states;
2. A comprehensive report on feasibility studies to inform a Phase 2 project; and
3. A comprehensive report on the case studies, targeting a range of users and promoting SmartSat CRC research through the mass media. The project brings together core partners such as UNSW, NSW Department of Planning and Environment, and Geoplex / Nova Systems, an ideal mix of academia, end user and geospatial service provider. The proposed project has also attracted strong support from the Federal Department of Agriculture, Water and Environment (DAWE) because of its significant national benefits (Letter of Support attached), as well as other key players such as Airbus and Geospatial Intelligence Pty Ltd.

Driven by the booming amount of transmission information, modern communication systems have developed to the fifth generation, and are expected to integrate different radio access technologies, including the satellite component. As outlined in the 3GPP, the future integrated satellite and terrestrial architectures will lead to manifold advantages and make satellite communications essential to the evolution fo the 5G network. Thus, the future 5G satellite network is required to have low latency, high capacity, and strong adaptability to complex environments, and these requirements are aligned to our research objectives, “developing advanced communication networks which are efficient and stable”.

However, the traditional satellite communication systems only have a limited ability to face challenges in 5G scenarios, including high attenuation, the complex and unreliable communication environment and resulting transmission errors. Though there are some existing solutions for satellite communications to combat these channel impairments, they cannot work well enough for 5G. To ensure the accuracy, efficiency and reliability of the future wireless communications system, our research aims to develop DL based wireless physical layer frameworks (i.e., leveraging deep-learning to redesign the module of the conventional communication system) for performance improvement, which can also be used to implement 5G satellite communications.

Synthetic aperture radar (SAR) is a key technology for Earth observation, that allows the unobstructed Earth observation and imaging including change detection and disaster management with high spatial resolution and independence of distance and weather conditions. Advancement in processing techniques and analyses will soon make it possible to have realtime monitoring. Due to the increasing ubiquity of wireless communications and the ever-increasing utilization of the radio spectrum, radio frequency interference is expected to become a major issue impacting spaceborne SAR technologies.

This research project aims to investigate interference topic in modern spaceborne SAR systems. It will construct a modelling framework to capture terrestrial interference using both analytic tools from stochastic geometry and simulation tools. It will then develop novel machine learning methods to detect interfering regions in reflected SAR signal based on both training samples, supervised and unsupervised learning methods. The research will thus develop interference mitigation techniques that will enhance SAR observation under the increasingly crowded radio spectrum.

The results of this project are expected to enhance the reliability of spaceborne SAR earth observation with direct applications in defence & security as well as in agriculture farming which is totally aligned with SmartSat CRC second research area “Earth observations from space” objectives and applications.

This research aims to provide a solution for energy-efficient AI-based on-board processing of hyperspectral imagery supporting automated early detection of fire smoke. We propose using modified and resampled MODIS imagery data that emulates the swath as well as spectral, spatial, and radiometric resolution of HyperScout-2 channel 1 hyperspectral imagery. In doing so, we intend to provide a solution that meets on-board processing limitations and up/downlink data transfer restrictions of the Kanyini – HyperScout-2/ with Intel’s Myriad X VPU chip.

Based on a semi-automatically created fire smoke training dataset, our proposed AI processing approach is performed at two levels: a) on-board feature and band selection, and b) ground AI neural network tasks – in order to optimize on-board processing and downlink data transfer. Expected outputs include on-board and ground AI algorithms for fire smoke detection, applicable for various hyperspectral imagery datasets.

The project will develop the concept of an intelligent payload termed Satellite Proximity Surveillance System or SatProx that can automatically monitor the near region (< 30km) of a geostationary (GEO) satellite for potential approaches by an adversarial satellite. Such unexpected rendezvous manoeuvres, which occur surreptitiously at low relative speeds (< 0.7 m/s), could indicate hostile on orbit activities such as shadowing, interference and hijacking. By providing early warning, SatProx buys valuable time for the host satellite to engage in mitigation strategies.

The project will produce the design and specification of SatProx, including the sensor suite (e.g., optical, IR, thermal, LiDAR) and edge data processing subsystem that can support real-time inference on the data stream to automatically detect and raise alarm on potential incoming spacecraft. The project will also develop graphical simulation software that can render the GEO environment for the optical channel (visible spectrum) under varying conditions environmental conditions, including simulated encroachment by other adversarial satellites. Based on the simulation software, machine learning algorithms for real-time adversarial satellite detection and physical characterisation (shape, pose and trajectory of adversarial satellite) will be developed. The algorithms will then be demonstrated on the simulation environment with edge processing hardware (embedded GPU or FPGA) in the loop.