Where on the Moon should we go and explore first? AI is now able to tell us



Robots on the moon aren’t new, but a computer brain that can tell us which destinations are worth exploring certainly is.

What if the astronauts who finally landed on the moon for the first time since the Apollo era had a robot that could tell them exactly where to go so they didn’t have to worry about themselves? Ditto for mission control handling an orbiter or an unmanned lunar rover. Today, scientists at King Abdullah University of Science and Technology (KAUST) developed a deep learning AI that they were able to train using telescope images. Siyuan Chen, who led a study recently published in Applied Energy, created the technology with his research team at KAUST.

“The biggest training challenge we faced in exploring lunar features was the problem of insufficient data,” he told SYFY WIRE. “There is no dataset that maps the grooves on the lunar surface. Therefore, the first thing we did was build the dataset ourselves. It is the first high-quality dataset that maps both lunar craters and grooves for energy resources.

Because it can check all craters and grooves (canyon-like features that look like cracks on the face of the Moon from afar), this bot will be able to detect all hot spots. It will also find energy resources like uranium and the helium isotope He-3, as no one wants a heavy propellant on their payload, especially if the Moon is used as an intermediate station to Mars in the future. Chen’s team used the transfer learning method to get the bot thinking. Transfer learning is exactly what it sounds like, transferring prior knowledge from one machine to another. The new AI will already have information that would otherwise have required hours of training.

By preforming the model with the groove data set they created, the team was able to see what was needed before further refining this data for the AI ​​to understand and identify. They also fixed more precision issues with a framework called high-resoution-moon-net. Two independent networks, one for finding craters and one for grooves, make up this high-resolution system. They share the same network structure that allows them to identify both craters and grooves and save time that would otherwise be spent on their careful research.

“High-resolution moon-net can be fed with images containing different kinds of features,” Chen said. “Technically, an image would traverse a deep residual grating that contains several oversampling, downsampling, and merging of feature maps, and the grating would produce a mask of the desired lunar feature.”

The reason why the grooves are so sought after for energy resources is because of ancient lunar volcanism. Lava tubes on the Moon, which could eventually be explored by soft robots or even used for habitats, are visible evidence of this. The grooves are believed to be the result of erosion from the lava that flowed to the surface billions of years ago, and lava (at least on Earth) is a primary source of He-3, the one of the natural isotopes of helium. He-3 is believed to have seeped from the Earth’s mantle into this lava. The same thing probably happened on the Moon.

Rare on Earth but common on the Moon, He-3 could eventually power spacecraft through nuclear fusion. In this process, the lighter atomic nuclei merge to form a heavier nucleus when they release energy. This phenomenon occurs naturally in stars which merge hydrogen into helium. It’s also free from radioactive sludge, which is the last thing we would want to pollute space with. Nuclear fusion between He-3 and deuterium in a reactor that would create fuel helium and additional protons. This would minimize wasted energy and cancel out harmful radiation.

Lunar craters are also potential mines for He-3 as some of them could have been caused by the solar wind, which carried the isotope there. It is at least an advantage to have a thin atmosphere which allows intense radiation.

“We believe our AI can be applied to detecting characteristics of energy reservoirs on the Moon for future Artemis missions,” Chen said. “More data can be obtained for information on the reservoir than information on the lunar surface.”


Leave A Reply

Your email address will not be published.