NASA used AI to capture lava lakes from orbit

NASA, AI, lava lake

AI might be all the rage now, but NASA has been using an AI system for over a decade to quickly direct satellites to capture disasters.

In a post on NASA’s website, the space agency detailed how its Autonomous Sciencecraft Experiment (ASE) AI system was able to quickly capture a volcano’s changing lava lake.

“On 21 January, a fissure opened at the top of Ethiopia’s Erta Ale volcano — one of the few in the world with an active lava lake in its caldera. Volcanologists sent out requests for NASA’s Earth Observing 1 (EO-1) spacecraft to image the eruption, which was large enough to begin reshaping the volcano’s summit,” the agency wrote.

“As it turned out, that spacecraft was already busy collecting data of the lava lake. Alerted by a detection from another satellite, an artificial intelligence system [ASE – ed] had ordered it to look at the volcano. By the time scientists needed these images, they were already processed and on the ground.”

The ASE system has been guiding the EO-1 satellite for 12 years now, focusing on natural disasters. Notable events covered by ASE and EO-1 include the Iceland volcanic ash cloud of 2010 and flooding in Thailand.

NASA has been using an AI system for 12 years, being capable of quickly capturing disaster hotspots without human intervention

NASA explained that, in addition to EO-1, the ASE AI system has a network of other satellites and ground sensors that feed info to it. This information is used by the AI to prioritise coverage areas.

The system generally notifies scientists of an event within 90 minutes, then takes a few hours to “re-task” the EO-1 satellite. The latter process would traditionally take weeks.

“It’s a milestone in AI application,” said Steve Chien, principal investigator of ASE and head of the Artificial Intelligence Group at JPL. “We were supposed to do this for six months, and we were so successful that we did it for more than 12 years.”

Ashley Davies, lead scientist for ASE and a volcanologist at JPL, said that the AI system translated into a ton of time saved and insights gained.

“We caught this event at the perfect time, during an early, developing phase of the eruption,” Davies said. Now he and other scientists had a much better sense of how the discharge of lava is evolving over time. “This simply wouldn’t have happened without the Volcano Sensor Web.”

The agency suggests that similar AI systems could be used to capture passing comets or volcanic eruptions on distant moons.



Sign up to our newsletter to get the latest in digital insights. sign up

Welcome to Memeburn

Sign up to our newsletter to get the latest in digital insights.