Forest fires

From space: ActiveEon solution helps early forest fires detection from orbiting satellites

December 19th, 2022

In 2022, France experienced very important heat waves, including a very early one. With climate change, this phenomenon is likely to recur every year, increasing the risk of forest fires, as was unfortunately observed this summer.

Activeeon has been working in partnership with the IRT Saint Exupéry studying technological solutions based on AI and artificial neural networks to detect forest fires as early as possible from orbiting satellites.

The results of this work were published in the paper presented at the CNIA (International Conference on Artificial Intelligence) 2022: “Model and dataset for multi-spectral detection of forest fires on board satellites”. The authors of the publication (Houssem Farhat, Lionel Daniel, Michael Benguigui and Adrien Girard) decided to make the model available to the scientific community to promote research on this topic.

This work was done as part of the CIAR project (“Chaîne Images Autonome et Réactive”), which studies technologies for deploying AI to process images on embedded systems (satellites, delivery drones…). It was conducted at IRT Saint Exupéry in partnership with Thales Alenia Space, Activeeon, Avisto, ELSYS Design, MyDataModels, Geo4i, INRIA and LEAT/CNRS.

According to the “Model and dataset for multi-spectral detection of forest fires on-board satellites” study, the number of wildfires will likely increase by +50% before the end of the century. In this article, its authors focus on detecting wildfires onboard satellites to raise early warnings directly from space. In this context, a neural network was trained to segment multispectral Sentinel-2 images, which the authors annotated semi-automatically and verified manually. Then they deployed this network on a GPU that can be embedded into a low-orbit satellite.

Two examples of patches

For several years, the CIAR team has been collaborating with ESA (the European Space Agency) on the OPS-SAT mission. On March 22, 2021, the team accomplished two space premieres:

  • Remotely updating, from a ground station, an artificial neural network embedded in a satellite.
  • Running this neural network on an FPGA (Field-Programmable Gate Array) in orbit.

Learn more about CIAR project here:

More news  

Published on December 19, 2022