Let’s be honest, it’s much easier for robots to explore space than it is for us humans. Robots don’t need fresh air and water, or carrying a bunch of food to stay alive. However, they require humans to lead them and make decisions. Advances in machine learning technology could change that, making computers a more active collaborator in planetary science.
Last week at the 2022 Fall Meeting of the American Geophysical Union (AGU), planetary scientists and astronomers discussed how new machine learning techniques are changing the way we learn about our planet. solar systemplanning for future mission landings on Jupiter’s icy moon Europe to identify volcanoes on tiny Mercury.
Machine learning is a way of training computers to identify patterns in data and then exploit those patterns to make decisions, predictions, or classifications. Another major advantage of computers – besides not requiring survival – is their speed. For many tasks in astronomy, it can take months, years, or even decades of human effort to sift through all the necessary data.
Related: Our Solar System: A Photo Tour of the Planets
An example is the identification of rocks in images of other planets. For a few rocks, it’s as simple as saying “Hey, there’s a rock!” but imagine doing this thousands of times. The task would become quite boring and take up a lot of the scientists’ precious working time.
“You can find up to 10,000, hundreds of thousands of rocks, and it takes a long time,” said Nils Prieur, a planetary scientist at Stanford University in California during his AGU talk. Prieur’s New Machine Learning Algorithm Can Detect Rocks All Over moon in just 30 minutes. Knowing where these large chunks of rock are is important to ensure new missions can land safely at their destination. The boulders are also useful for geology, providing clues as to how impacts break up the rocks around them to create craters.
Computers can also identify a number of other planetary phenomena: exploding volcanoes on Mercury, vortices in Jupiterthe thick atmosphere and craters of the moon, to name a few.
During the conference, planetary scientist Ethan Duncan, from NASA’s Goddard Space Flight Center in Maryland, demonstrated how machine learning can identify not pieces of rock, but pieces of ice on Europa, the icy moon of Jupiter. The so-called chaos terrain is a messy strip of Europa’s surface, with glowing chunks of ice scattered across a darker background. With its subterranean ocean, Europa is a prime target for astronomers interested in extraterrestrial life, and mapping these chunks of ice will be key to planning future missions.
Future missions could also integrate artificial intelligence into the team, using this technology to allow probes to react to hazards in real time and even land autonomously. Landing is a notorious challenge for spacecraft, and always one of the most dangerous parts of a mission.
“The ‘seven minutes of terror’ on Mars [during descent and landing], it’s something we talk about a lot,” Bethany Theiling, planetary scientist at NASA Goddard, said during her keynote. “It gets a lot more complicated the further you go through the solar system. We’re many hours behind in communication.”
A message from a probe landing on Saturn’s methane-filled moon Titan would take just under an hour and a half to get back to Earth. By the time the humans’ response reached its destination, the communication loop would last nearly three hours. In a situation like landing where real-time responses are needed, that kind of back-and-forth with Earth isn’t enough. Machine learning and AI could help solve this problem, Theiling says, by providing a probe with the ability to make decisions based on its observations of its environment.
“Scientists and engineers, we’re not trying to get rid of you,” Theiling said. “What we’re trying to do is say that the time you spend with this data will be the most useful time we can manage.” Machine learning won’t replace humans, but we hope it can be a powerful addition to our toolbox for scientific discovery.
Follow the author on @briles_34 on Twitter and follow us on Twitter @Espacedotcom and on Facebook.
//platform.twitter.com/widgets.js