An interdisciplinary team at Tsinghua University in China has developed an artificial intelligence model designed to improve astronomical imaging and push the boundaries of deep space exploration. Named ASTERIS (Astronomical Spatiotemporal Enhancement and Reconstruction for Image Synthesis), this system combines computational optics and AI algorithms.
The results, published in the journal Science, show that the model makes it possible to extract extremely weak astronomical signals, to identify galaxies located more than 13 billion light-years away and to produce the deepest images ever obtained of the cosmos.
Observing very distant celestial objects is essential for understanding the origin and evolution of the universe. However, astronomers face a major obstacle: the faint signals from these objects are often masked by background noise in the sky and by thermal radiation from the instruments.
ASTERIS introduces a technique called "spatiotemporal self-learning denoising." Applied to data from the James Webb Space Telescope (JWST), it extends the observation coverage from the visible spectrum (approximately 500 nanometers) to the mid-infrared (5 micrometers). The model also increases the detection depth by one magnitude, making it possible to identify objects 2,5 times fainter than before.
Using this technology, the team identified more than 160 high-redshift candidate galaxies dating back to the period known as the "cosmic dawn," between 200 and 500 million years after the Big Bang. This figure represents a threefold increase compared to previous methods, according to Cai Zheng, associate professor in the Department of Astronomy at Tsinghua University.
Unlike traditional noise reduction techniques, which assume uniform interference, ASTERIS reconstructs images as a three-dimensional spatiotemporal volume. Using an adaptive photometric analysis mechanism, it distinguishes noise fluctuations from the extremely weak signals emitted by distant stars and galaxies.
Researchers believe the model can process enormous volumes of data from different telescopes, potentially making it a universal platform for enhancing space data. The goal is to integrate it into future generations of telescopes to further the study of dark energy, dark matter, cosmic origins, and exoplanets.
Experts believe this breakthrough could have a major impact on modern astronomy by improving the ability to detect and analyze the oldest and most distant objects in the universe.
