NASA trains artificial intelligence systems that will direct the search for alien life in rock samples on Mars during the European Space Agency ExoMars mission in 2022
- It is expensive and time intensive to send data back from Mars and other worlds
- Researchers have trained artificial intelligence systems to cut unnecessary data
- It will be tested when the European Space Agency sends a rover to Mars in 2022
- The goal is to use it in more distant planetary missions to the moons of Jupiter and Saturn in the future where it can take hours for a signal to return to Earth
Artificial intelligence will help scientists search for signs of ancient life on Mars and other planets thanks to work by NASA scientists in training the system.
The European Space Agency (ESA) Rosalind Franklin ‘ExoMars’ rover will be the first to have the new AI system when it leaves for the Red Planet in 2022/2023.
Allowing these intelligent systems to choose both what to analyse and what to tell us back on Earth will overcome severe limits on how information is transmitted over huge distances in the search for life from distant planets.
The system is being tested on Mars but has been designed to be used in future missions to the icy moons of Jupiter and Saturn where distance is more of an issue.
The European Space Agency (ESA) Rosalind Franklin ‘ExoMars’ rover will be the first to have the new AI system when it leaves for the Red Planet in 2022/2023
Presenting the work at the Goldschmidt Geochemistry conference, lead researcher Victoria Da Poian from NASA said this was a ‘visionary step in space exploration’.
Giving AI the ability to decide where and when to search for signs of life means the ‘most pressing information’ will be sent back to Earth saving time and resources.
‘It means that over time we’ll have moved from the idea that humans are involved with nearly everything in space, to the idea that computers are equipped with intelligent systems,’ said Da Poian.
These computers ‘are trained to make some decisions and are able to transmit in priority the most interesting or time-critical information’.
Eric Lyness, software lead in the Planetary Environments Lab at NASA Goddard Space Flight Center, said smart instruments were essential for planetary exploration.
The system is being tested on Mars but has been designed to be used in future missions to the icy moons of Jupiter and Saturn where distance is more of an issue
‘It costs a lot of time and money to send the data back to Earth which means scientists can’t run as many experiments or analyse as many samples,’ said Lyness.
‘By using AI to do an initial analysis of the data after it is collected but before it is sent back to Earth, NASA can optimise what we receive, which greatly increases the scientific value of space missions.’
Da Poian and Lyness have been working to train artificial intelligence systems to analyse hundreds of rock samples and thousands of other data points.
These points of information come from the Mars Organic Molecule Analyser (MOMA), an instrument that will land on Mars within the European Space Agency ExoMars Rosalind Franklin Rover in 2023.
MOMA is a state-of-the-art mass spectrometer-based instrument, capable of analysing and identifying organic molecules in rocks samples.
It will search for past or present life on the Martian surface and subsurface through analysis of those samples – selected for study by the AI system.
The ExoMars rover will still transmit most data back to Earth, but later systems for the outer solar system will be given autonomy to decide what information to return.
First results show that when the system’s neural network algorithm processes a spectrum from an unknown compound, this can be categorised with up to 94 per cent accuracy and matched to previously seen samples with 87 per cent accuracy.
This will be further refined until being incorporated into the 2022/2023 mission.
Victoria Da Poian said these uncrewed missions involve a lot of data and sending data over hundreds of millions of miles can be challenging and expensive.
‘We need to prioritize the volume of data we send back to Earth, but we also need to ensure that in doing that we don’t throw out vital information,’ she said.
‘This has led us to begin to develop smart algorithms which can for now help the scientists with their analysis of the sample and their decision-making process regarding subsequent operations.’
Sending raw data back from missions to the moons of Jupiter and Saturn, including Enceladus (pictured) will take five to seven hours so the amount of data sent needs to be controlled
‘As a longer-term objective, algorithms that will analyse the data itself, will adjust and tune the instruments to run next operations without the ground-in-the-loop, and will transmit home only the most interesting data.’
The team used the raw data from initial laboratory tests with an Earth-based MOMA instrument to train computers to recognise familiar patterns.
When new raw data is received, the software tells the scientists what previously encountered samples match this new data.
“When we will be operating on Mars, samples will only remain in the rover for at most a few weeks before the rover dumps them,’ said Lyness.
‘So, if we need to retest a sample, we need to do it quickly, sometimes within 24 hours,’ he added, saying time will be even more pressing for more distant missions.
‘In the future, as we move to explore the moons of Jupiter such as Europa, and of Saturn such as Enceladus and Titan, we will need real-time decisions.’
With the icy moons of the gas giants it can take five to seven hours for a signal from Earth to reach the instruments, so this will not be like controlling a drone.
‘We need to give the instruments the autonomy to make rapid decisions to reach our science goals on our behalf,’ said Lyness.
The data coming in from MOMA won’t shout ‘I’ve found life’, it will need to be analysed by scientists – but it will have been filtered so will be more focused than data coming in from previous missions to Mars and elsewhere.
In the future, as NASA moves to explore the moons of Jupiter such as Europa (pictured), and of Saturn such as Enceladus and Titan, they will need real-time decisions from instruments on board the spacecrafts sent to do the work
The results will largely tell us about the geochemistry that the instruments find but it will give scientists directions such as ‘I’ve got 91 per cent confidence that this sample corresponds to a real world sample’.
The researchers note that data is expensive to send back from Mars, and gets more expensive as landers get further from Earth.
“Data from a rover on Mars can cost as much as 100,000 times as much as data on your cell phone, so we need to make those bits as scientifically valuable as possible.” said Lyness.
Dr Joel Davis, a postdoctoral researcher in planetary geology at the Natural History Museum, London said data was one of the biggest challenges in these missions.
‘On Mars, the travel time delay is around 20 minutes and this gets more the further you go out in the solar system,’ he said.
‘These results certainly seem promising; having greater autonomy onboard spacecraft is one way of ensuring the usefulness of the data returned.’
ExoMars is a joint European-Russian, project that was due to launch for Mars this summer but was delayed until 2022/2023 due to coronavirus.
One of the central mission goals is to search for traces of past and present life.
A key instrument in achieving this goal is the Mars Organic Molecule Analyser (MOMA), which is a joint German-French-American investigation led by the Max Planck Institute for Solar System Research in Göttingen.
The newly trained AI system will be incorporated into this instrument and if successful will be used in future missions to the gas giant moons.
EUROPE AND RUSSIA ARE WORKING TOGETHER ON THE EXOMARS MISSION TO SEARCH FOR SIGNS OF MARTIAN LIFE
The main goal of ExoMars is to find out if life has ever existed on Mars – it will do this through a series of instruments on the surface and in orbit.
This includes an orbiting spacecraft called the Trace Gas ORbiter (TGO) that carries a probe to study trace gasses such as methane around the planet.
Scientists believe methane, a chemical that on Earth is strongly tied to life, could help identify areas where life does or could have once existed.
The second part of the ExoMars mission, delayed to 2022/2023 due to coronavirus, will deliver a rover to Mars’ surface.
The rover is being built in Stevenage, UK and is named after British scientist Rosalind Franklin.
It will be the first with the ability to both move across the planet’s surface and drill into the ground to collect and analyse samples.
The rover will include a technology called the Mars Organic Molecule Analyser (MOMA) that will allow it to analyse samples and send data back to Earth.
Source: Read Full Article