Two PhD students from the University of Sydney have developed innovative software to correct blurring in images from NASA's James Webb Space Telescope. Their tool, AMIGO, restores the telescope's sharp vision using AI without requiring a space mission. This breakthrough enhances observations of distant celestial objects.
Researchers at the University of Sydney have achieved a significant advancement in space science by addressing a technical issue in NASA's James Webb Space Telescope (JWST) entirely from Earth. PhD students Louis Desdoigts and Max Charles, working with Professor Peter Tuthill and Associate Professor Ben Pope, created AMIGO (Aperture Masking Interferometry Generative Observations), a software solution that corrects distortions in the telescope's infrared camera detector.
The problem stemmed from the brighter-fatter effect, where electric charge spreads to neighboring pixels, causing subtle image fuzziness. This issue affected the Aperture Masking Interferometer (AMI), an Australian-designed component developed by Professor Tuthill at the University of Sydney's School of Physics and the Sydney Institute for Astronomy. AMI enables ultra-high-resolution imaging of stars and exoplanets through interferometry, combining light from different sections of the telescope's main mirror.
Instead of a physical repair like those needed for the Hubble Space Telescope, the team used advanced simulations and neural networks to model the telescope's optics and electronics. Their algorithms digitally correct the images, fully restoring AMI's performance. "Instead of sending astronauts to bolt on new parts, they managed to fix things with code," Professor Tuthill said. "It's a brilliant example of how Australian innovation can make a global impact in space science."
The results are impressive. AMIGO has enabled the JWST to produce its clearest images yet, including direct views of a dim exoplanet and a red-brown dwarf orbiting the star HD 206893, located 133 light years from Earth. A related study by Max Charles demonstrated AMI's improved precision with sharp images of a black hole jet, the surface of Jupiter's moon Io, and the dust-filled stellar winds of WR 137.
"This work brings JWST's vision into even sharper focus," Dr. Desdoigts said. "It's incredibly rewarding to see a software solution extend the telescope's scientific reach -- and to know it was possible without ever leaving the lab." Desdoigts is now a postdoctoral researcher at Leiden University in the Netherlands. The studies were published on arXiv on October 10 and 13, 2025, with Desdoigts' paper accepted for publication in the Publications of the Astronomical Society of Australia. Associate Professor Pope presented the findings at SXSW Sydney and aims to distribute the code to JWST researchers soon.