Australian scientists are advancing in the quest to detect bushfires swiftly, leveraging cube satellites equipped with artificial intelligence. These satellites can now identify fires from space 500 times faster than traditional ground-based methods.
Remote sensing and computer science experts have tackled the challenge of processing and compressing vast amounts of hyperspectral imagery on board the cost-effective cube satellites. This innovation saves critical time and energy, facilitating quicker ground responses and potentially preventing the devastating impacts seen in previous wildfires.
The breakthrough, spearheaded by a project funded by the SmartSat CRC and led by the University of South Australia (UniSA), has resulted in an energy-efficient early fire smoke detection system for South Australia’s first cube satellite, Kanyini. The mission, a collaboration between the SA Government, SmartSat CRC, and industry partners, aims to launch a 6U CubeSat into low Earth orbit to detect bushfires and monitor inland and coastal water quality.
The satellite’s hyperspectral imager captures reflected light from Earth in various wavelengths, producing detailed surface maps for multiple applications, including bushfire monitoring, water quality assessment, and land management. UniSA geospatial scientist Dr. Stefan Peters explains that traditionally, Earth observation satellites lacked onboard processing capabilities for real-time analysis of complex Earth images.
Dr. Peters and his team, comprising scientists from UniSA, Swinburne University of Technology, and Geoscience Australia, have developed a lightweight AI model that detects smoke within the processing, power, and storage constraints of cube satellites. This AI model has significantly reduced the volume of data downlinked to 16% of its original size while consuming 69% less energy. Remarkably, it detects fire smoke 500 times faster than traditional methods.
“Smoke is usually the first sign visible from space before a fire becomes large and hot enough for sensors to detect it, so early detection is crucial,” Dr. Peters states. Using simulated satellite imagery of recent Australian bushfires, the team trained the AI model to detect smoke accurately. This innovation has allowed the model to distinguish smoke from clouds, enhancing efficiency.
The team used a past fire event in the Coorong as a case study, where the simulated Kanyini AI onboard approach detected smoke and transmitted data to the South Pole ground station in less than 14 minutes. Dr. Peters highlights the substantial advantages of onboard AI over traditional ground processing, noting its potential as an early warning system for other natural disasters.
The research team aims to demonstrate the onboard AI fire detection system in orbit in 2025 when the Kanyini mission becomes operational. They also plan to commercialise the technology, deploying it on a CubeSat constellation to facilitate early fire detection within an hour.
Details of their experiment have been published in the latest issue of the IEEE Journal of Selected Topics in Applied Earth and Remote Sensing. This advancement represents a significant step towards mitigating the catastrophic effects of bushfires and improving response times, marking a pivotal moment in wildfire management technology.
Support independent community journalism. Support The Indian Sun.
Follow The Indian Sun on X | Instagram | Facebook
Australian scientists use AI-equipped cube satellites to detect #bushfires 500 times faster than ground methods, enhancing early warning systems. This technology will launch with the Kanyini mission in 2025. 🚀🔥🌍🛰️🌳 #TheIndianSunhttps://t.co/jESFBriyTb
— The Indian Sun (@The_Indian_Sun) June 5, 2024
Donate To The Indian Sun
Dear Reader,The Indian Sun is an independent organisation committed to community journalism. We have, through the years, been able to reach a wide audience especially with the growth of social media, where we also have a strong presence. With platforms such as YouTube videos, we have been able to engage in different forms of storytelling. However, the past few years, like many media organisations around the world, it has not been an easy path. We have a greater challenge. We believe community journalism is very important for a multicultural country like Australia. We’re not able to do everything, but we aim for some of the most interesting stories and journalism of quality. We call upon readers like you to support us and make any contribution. Do make a DONATION NOW so we can continue with the volume and quality journalism that we are able to practice.
Thank you for your support.
Best wishes,
Team The Indian Sun
