"Quantifying trade-offs in satellite hardware configurations using a super-resolution framework with realistic image degradation" - White et al. (2024)

Earth Observation is a powerful tool for mapping and monitoring the world from space, but satellites have limitations in their ability to scan - but can AI enhance that scanning capability? An extraordinary project that included the biggest EO fleet operator in history with Planet Labs, the leading Space Lab team at EY, and of course our own team at Swinburne with Stephen Petrie and Kai Qin - and our former student Jack White (now at EY!)

The results were promising, that a state-of-the-art SR technique called Enhanced Deep Super-Resolution Network (EDSR), without domain-specific pre-training, can recover encoded pixel data on images with poor ground sampling distance, provided the ground resolved distance is sufficient. In other words, new satellite hardware should prioritise optical performance/quality over minimising pixel size as deep SR can overcome a lack of the latter but not the former.