Onboard AI for CubeSats enables earlier bushfire detection

A new project led by the University of South Australia (UniSA) has used cutting-edge onboard AI technology to develop an energy-efficient early fire detection system for South Australia’s first cube satellite, Kanyini.

The Kanyini mission is a collaboration between the SA Government, SmartSat CRC and industry partners to launch a 6U CubeSat satellite into low Earth orbit to detect bushfires as well as monitor inland and coastal water quality. Equipped with a hyperspectral imager, the satellite sensor captures reflected light from Earth in different wavelengths to generate detailed surface maps for various applications, including bushfire monitoring, water quality assessment and land management.

Lead researcher UniSA Dr Stefan Peters said that, traditionally, Earth observation satellites have not had the onboard processing capabilities to analyse complex images of Earth captured from space in real time. His team, which includes scientists from UniSA, Swinburne University of Technology and Geoscience Australia, has overcome this by building a lightweight AI model that can detect smoke within the available onboard processing, power consumption and data storage constraints of cube satellites.

“For most sensor systems, only a fraction of the data collected contains critical information related to the purpose of a mission,” Peters said. “Because the data can’t be processed onboard large satellites, all of it is downlinked to the ground where it is analysed, taking up a lot of space and energy. We have overcome this by training the model to differentiate smoke from cloud, which makes it much faster and more efficient.”

Compared to the on-ground-based processing of hyperspectral satellite imagery to detect fires, the AI model reduced the volume of data downlinked to 16% of its original size, while consuming 69% less energy. The model also detected smoke 500 times faster than traditional on-ground processing — even before they take hold and generate large amounts of heat — allowing on-ground crews to respond more quickly and prevent loss of life and property.

“Smoke is usually the first thing you can see from space before the fire gets hot and big enough for sensors to identify it, so early detection is crucial,” Peters said.

The team demonstrated their AI model with simulated satellite imagery of recent Australian bushfires, having used machine learning to train the model to detect smoke in an image. Using a past fire event in the Coorong, south of Adelaide, as a case study, the simulated Kanyini AI onboard approach took less than 14 minutes to detect the smoke and send the data to the South Pole ground station.

“This research shows there are significant benefits of onboard AI compared to traditional on-ground processing,” Peters said. “This will not only prove invaluable in the event of bushfires but also serve as an early warning system for other natural disasters.”

With their results now published in the IEEE Journal of Selected Topics in Applied Earth and Remote Sensing, the research team hopes to demonstrate the onboard AI fire detection system in orbit in 2025 when the Kanyini mission is operational.

“Once we have ironed out any issues, we hope to commercialise the technology and employ it on a CubeSat constellation, aiming to contribute to early fire detection within an hour,” Peters said.

Image credit: iStock.com/gece33