Nasa is turning to artificial intelligence to get a better look at the Moon.
The US space agency and IBM have released an open-source AI model that can analyse decades of lunar observations and help scientists map craters, search for ice and study the Moon’s volcanic features.
Called the Nasa-IBM Lunar Foundation Model, the tool is designed to bring together information collected by different instruments instead of making researchers examine each dataset separately.
AI MEETS THE MOON
The model was trained on more than 30 layers of data collected by nine instruments across four Nasa missions, including the Lunar Reconnaissance Orbiter (LRO).
It can help identify potential ice deposits in permanently shadowed regions, map craters and study volcanic formations.
In benchmark tests, Nasa and IBM said the model identified key lunar features with up to 23% greater accuracy than widely used methods.
That could make a difference as scientists prepare for a new era of lunar exploration.
Craters are more than just marks on the Moon’s surface. Their size, distribution and age can reveal clues about the Moon’s geological history, while detailed crater maps can help planners identify safer locations for future landings and infrastructure.
“Nasa has spent decades building an extraordinary scientific record of the Moon, but collecting data is only part of the job,” Kevin Murphy, Nasa’s chief science data officer and acting chief data and AI officer, told news agency Reuters. “We also have to make data easier for scientists to explore and use.”
WHY IS LUNAR ICE IMPORTANT?
The search for lunar ice is one of the model’s most important applications.
Permanently shadowed craters near the lunar poles receive little or no sunlight and are among the hardest places to study.
Scientists are particularly interested in them because lunar ice means access to water. Water could eventually provide drinking supplies and oxygen for astronauts, while its components could also be used to produce rocket fuel for future missions.
Nasa’s Artemis programme aims to return astronauts to the Moon in 2028 and develop technologies for longer stays before eventual missions to Mars.
Better maps could therefore help determine where humans can safely explore and where useful resources may be found.
“Uncovering the mysteries of the Moon requires an ability to learn from an extraordinary volume of scientific data,” Juan Bernabe-Moreno of IBM Research told Reuters.
The model is open source, meaning researchers around the world can access and build on it as lunar exploration expands.
“We hope that our AI model can help the science community explore the lunar landscape and help the next generation of astronauts find their way around before heading into space.”
– Ends
Leave a Reply