AI provides an imaging solution for the moon shadow crater

Researchers at the Max Planck Institute for Solar System Research (MPS) in Germany paper Emphasizes AI solutions for imaging moon shadow craters.

HORUS (Super Effective nOise Removal U-net Software) is a machine learning algorithm that allows you to map these dark craters with unprecedented resolution.

The software uses over 70,000 calibrated images taken on the dark side of the moon by NASA’s Lunar Reconnaissance Orbiter to reduce the large amount of noise produced by low light images.

It also takes into account information about camera temperature and spacecraft orbit to further reduce artifacts and distinguish between actual geological features. With HORUS, researchers can achieve a resolution of about 1-2 meters per pixel. This is 5-10 times the resolution of all images available so far.

So far, researchers have used HORUS to map and image 17 craters in the South Pole of the Moon.

This feature is especially important because many of these craters are believed to contain frozen water.

Dr. Valentin Bickel, an MPS scientist who is the first author of the new paper, said:

In this “eternal night”, the temperature is so cold in some places that frozen water is expected to last for millions of years. This proved to be the case in 2009 when NASA’s Lunar Crater Observation and Detection Satellite (LCROSS) found a significant amount of water in the Antarctic crater Caveus.

Currently, three of the 17 craters envisioned by MPS researchers are in the mission area of ​​NASA’s Volatiles Investigating Polar Exploration Rover (VIPER), which is scheduled to land on the moon in 2023.

In the preparatory phase of this mission, MPS researchers want to use HORUS to study as many shadow areas as possible.

Bickel concludes: “In our current publication, we wanted to show what the algorithm could do. Now we want to apply it as comprehensively as possible.”

Learn more about Digital Transformation Week Virtual events and conferences in North America, November 9-10, 2021, exploring advanced DTX strategies for the world of “digital everything”.

tag: algorithm, HORUS, Machine learning, Max Plan Quinty Institute, Month, Moon crater, MPS, NASA AI provides an imaging solution for the moon shadow crater

Back to top button