🔭 AI Helps Fix the James Webb Space Telescope

The James Webb Space Telescope captures images of distant stars and exoplanets in ultra-high resolution. After it started operating in 2022, an unexpected problem arose.

The AMI interferometer combines infrared light from different sections of the telescope's main mirror to achieve the clearest possible image. However, when pixels receive too much charge from a powerful light source in space, bright spots in the photo appear to "bloom" and the image becomes blurry.
Astronauts could fix the defect, but the telescope is about 1.6 million km from Earth. No space mission has ever flown that far.

Scientists in Sydney solved this problem using AI. They created a virtual model of the telescope's optics and used it to train algorithms to correct image blurriness.

Thanks to this, the telescope has already received images of the galaxy NGC 1068, Jupiter's moon Io, and the star Wolf-Rayet 137 with previously unattainable clarity (from left to right ⤴️).

"Instead of sending astronauts to bolt on new parts, they managed to fix things with code," explains Professor Peter Tuthill of the Sydney Institute for Astronomy.

@hiaimediaen