“Denoising” radar satellite images with artificial intelligence (IP Paris)

07 February 2025

SAR radar image of crop fields, raw (left) and processed by statistical learning (right) © Florence Tupin via IP Paris

Mounted on a satellite or an aircraft, Synthetic Aperture Radars (SAR) have revolutionized space imagery by making it possible to obtain high-resolution images of the Earth, whether it is day or night, in clear or cloudy skies. The problem is that, however good they are, SAR radars are full of “noise”.

Florence Tupin, a researcher at the Information Processing and Communications Laboratory (LTCI), at Télécom Paris, is using deep learning to obtain images cleared from the fluctuations inherent in radar imagery. Focus on the researcher’s work on the occasion of the AI, Science and Society event organized by the Institut Polytechnique de Paris on February 6 and 7, 2025.

“The images obtained have often a lot of fluctuations that result in altered “colours” and a kind of granularity that makes them difficult to interpret,” says Florence Tupin, a professor at the Information Processing and Communications Laboratory (LTCI) at Télécom Paris. The researcher, who specialized in “denoising” these images with the help of artificial intelligence (AI) – more precisely with statistical learning – has developed innovative methods for “drastically improving” them.

In image processing, artificial neural networks – an adaptive AI system that teaches algorithms to process data from a large number of examples – are generally trained to obtain an image without “noise” by showing them the type of image to obtain from the acquired “noisy” image. On the other hand, Florence Tupin and her colleagues’ deep learning approach makes it possible to work without a “ground truth image”. “In short, we provide the network with two noisy versions of the same scene, that is images that present the same information but with different noises, or speckle fluctuations,” says the researcher. “The network will be able to predict the part that is identical to the two images, in other words the scene without noise.”

Full story on IP Paris site