Published 18:28 IST, June 27th 2020
NASA to use AI to help search for life on Mars and beyond
Scientists from the NASA Goddard Space Flight Center (GSFC) have announced first results from new intelligent systems, to be installed in space probes for Mars
Advertisement
US ncy NASA has stepped closer to allowing remote onboard computers to direct search for life on or planets. Scientists from NASA Goddard Flight Center (GSFC) have anunced first results from new intelligent systems, to be installed in probes, capable of identifying geochemical signatures of life from rock samples.
Allowing se 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 search for life from distant planets. systems will debut on 2022/23 ExoMars mission, before fuller implementation on more distant bodies in solar system.
Advertisement
Presenting work at Goldschmidt Geochemistry Conference, le researcher Victoria Da Poiana (GSFC) said, “This is a visionary step in exploration. It means that over time we’ll have moved from idea that humans are involved with nearly everything in , to idea that computers are equipped with intelligent systems, and y are trained to make some decisions and are able to transmit in priority most interesting or time-critical information.”
Eric Lyness, software le in Planetary Environments Lab at NASA GSFC, emphasised need to have smart instruments for planetary exploration.
Advertisement
“It costs a lot of time and money to send data back to Earth which means scientists can’t run as many experiments or analyse as many samples as y would like. By using AI to do an initial analysis of data after it is collected but before it is sent back to Earth, NASA can optimise what we receive, which greatly increases scientific value of missions.”
Advertisement
Mars Organic Molecule Analyser (MOMA)
Victoria Da Poian and Eric Lyness have trained artificial intelligence systems to analyse hundreds of rock samples and thousands of experimental spectra from Mars Organic Molecule Analyser (MOMA), an instrument that will land on Mars within ExoMars Rosalind Franklin Rover in 2023.
Advertisement
MOMA is a state-of--art mass spectrometer-based instrument, capable of analysing and identifying organic molecules in rocks samples. It will search for past or present life on Martian surface and subsurface through analysis of rock samples. system to be sent to Mars will still transmit most data back to Earth, but later systems for outer solar system will be given automy to decide what information to return to Earth.
First results show that when system’s neural network algorithm processes a spectrum from an unkwn compound, this can be categorized with up to 94% accuracy and matched to previously seen samples with 87% accuracy. This will be furr refined until being incorporated into 2023 mission.
Advertisement
Victoria Da Poian continued: “What we get from se unmanned missions is data, lots of it; and sending data over hundreds of millions of kilometres can be very challenging in different environments and extremely expensive; in or words, bandwidth is limited. We need to prioritize 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. This has led us to begin to develop smart algorithms which can for w help scientists with ir analysis of sample and ir decision-making process regarding subsequent operations, and as a longer-term objective, algorithms that will analyse data itself, will just and tune instruments to run next operations without ground-in--loop, and will transmit home only most interesting data.”
team used raw data from initial laboratory tests with an Earth-based MOMA instrument to train computers to recognize familiar patterns. When new raw data is received, software tells scientists what previously encountered samples match this new data.
researchers te that data is expensive to send back from Mars, and gets more expensive as landers get furr 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 EricLyness.
(With inputs from ncy) (Im Twitter/NASA)
18:28 IST, June 27th 2020