Scientists at Northwestern University in the US and Tsinghua University in Beijing created a neural network that was used to clean images of space from interference. The conclusions of the work are published in the arXiv preprint repository.

Typically, photographs taken by the world's best ground-based telescopes appear blurry due to moving pockets of air in the atmosphere. This is because light from distant stars, planets, and galaxies passes through the Earth's atmosphere. The atmosphere not only blocks certain waves of light, but also distorts it. Even in a clear night sky, stars twinkle due to air vibrations.

Related content:Space dashMoon landing, Mars flight and new rockets: why 2021 will go down in astronautics history?January 9, 2021Raise everything. How Elon Musk's SpaceX creates the most powerful rocket in historyAugust 9, 2021

This interference obscures the shapes of objects in astronomical images, leading to erroneous physical measurements for studying the universe. Thus, an elliptical galaxy may appear more round or stretched out than it really is.

To solve the problem, the experts modified the artificial intelligence algorithm used to sharpen photos and combined it with a deep learning program. Astrophysicists use similar tools to remove blur, but the new program is faster and produces more realistic and beautiful images. As a result, the neural network cleaned up images that had 38.6 percent less distortion than traditional deblurring methods.

Moreover, the program has an open source code and an accessible online guide to use for all astronomers who want to use the development.