A moon-scanning method that can automatically classify important lunar features from telescope images could significantly improve the efficiency of selecting sites for exploration.

There is more than meets the eye to picking a landing or exploration site on the moon. The visible area of the lunar surface is larger than Russia and is pockmarked by thousands of craters and crisscrossed by canyon-like rilles. The choice of future landing and exploration sites may come down to the most promising prospective locations for construction, minerals or potential energy resources. However, scanning by eye across such a large area, looking for features perhaps a few hundred meters across, is laborious and often inaccurate, which makes it difficult to pick optimal areas for exploration.

Siyuan Chen, Xin Gao and Shuyu Sun, along with colleagues from The Chinese University of Hong Kong, have now applied machine learning and artificial intelligence (AI) to automate the identification of prospective lunar landing and exploration areas.

"Suborbital" is a term you'll be hearing a lot as Sir Richard Branson flies aboard Virgin Galactic's VSS Unity winged spaceship and Jeff Bezos flies aboard Blue Origin's New Shepard vehicle to touch the boundary of space and experience a few minutes of weightlessness.

But what exactly is "suborbital?" Simply put, it means that while these vehicles will cross the ill-defined boundary of space, they will not be going fast enough to stay in space once they get there.

If a spacecraft—or anything else, for that matter—reaches a speed of 17,500 mph (28,000 km/h) or more, instead of falling back to the ground, it will continuously fall around the Earth. That continuous falling is what it means to be in orbit and is how satellites and the Moon stay above Earth.