by When you make a purchase through links on our article, Future and its syndicate partners may earn a commission.
Scientists are turning to machine learning to help analyze extraterrestrial samples.
“This machine learning algorithm can help us by quickly filtering the data and indicating which data is likely to be the most interesting or important for us to examine,” said Xiang “Shawn” Li, mass spectrometry scientist in the Planetary Environments laboratory at NASA Goddard.
The new technology will first be applied to data collected by the Mars Organic Molecule Analyzer (MOMA), a cutting-edge instrument that squeezes “a laboratory full of chemistry equipment into a package the size of a toaster.”
MOMA will be sent to the Red Planet aboard the Rosalind Franklin Rover as part of the upcoming ExoMars mission, led by the European Space Agency (ESA). The rover, due to launch no earlier than 2028, will take a sample of the surface of Mars to determine if life ever existed.
Related: Possible signs of life on Mars: Astrobiologist explains Perseverance rover’s exciting discovery
The rover will be able to drill down an impressive 6.6 feet (2 meters) into the surface of Mars; previous rovers only reached about 2.8 inches (7 centimeters) below the surface.
“Organic materials on the surface of Mars are more likely to be destroyed by exposure to radiation at the surface and cosmic rays that penetrate the subsurface,” Li said, “but two meters depth should be enough for most of organic matter. MOMA therefore has the potential to detect preserved ancient organs, which would be an important step in the search for past life.”
To do this, MOMA will be looking for organic compounds — those with one or more carbon atoms covalently bonded to atoms of other elements, typically hydrogen, oxygen, or nitrogen — that could be found in drilled samples and may come from. living matter.
To look for these molecules, MOMA houses the most sophisticated mass spectrometer ever launched on Earth. Mass spectrometers are common in laboratories on Earth, offering scientists a basic way to identify molecules based on molecular weight. Although there are more sophisticated and accurate techniques that scientists use to determine the structure of a molecule, the MOMA mass spectrometer is perfectly suited for sorting samples of complex mixtures.
Like its predecessor, SAM, sent on the Curiosity rover, MOMA can prepare samples collected by the rover, vaporizing materials in a high-temperature oven before sending volatile molecules through a gas chromatograph that separates and analyzes the chemical components of the mixtures. Separation occurs because the samples interact with two phases within the chromatograph column: a mobile gaseous phase and a stationary solid or liquid phase.
As they are transported through the instrument in the gaseous phase, depending on their structure, elements, and general chemistry, different molecules in a sample mixture will interact differently with the stationary phase of the column – some of them will remain, forming bonds temporary weak and others will be straight. blast through. This causes them to travel through the column at different speeds, which separates the mixture and then identifies individual components based on their masses and how they ionize.
What’s exciting about MOMA is that it has a complementary mode of operation called “laser desorption mass spectrometry.” Here, pulsed ultraviolet light is used to release and ionize organic molecules from the surface of a sample.
The duration of each laser pulse is extremely short, less than two nanoseconds to be exact (where one nanosecond is one billionth of a second). This ultrafast pulse ensures that the process occurs very quickly, allowing weak chemical bonds to be preserved and improving the accuracy of molecular identification.
While the instrumentation is impressive in its own right, however, scientists are now training machine learning models to help them sort through the data MOMA will be sending home. This is being done using laboratory data collected over the past ten years.
“The more we do to optimize the data analysis, the more information and time scientists will have to interpret the data,” said Victoria Da Poian, a data scientist at NASA Goddard who co-leads the development of the machine learning algorithm . “In this way, we can react quickly to results and plan the next steps as if we are there with the rover, much faster than we would have before.”
Related Stories:
— Mars Express orbiter takes a deep dive into the Red Planet’s ancient lake (images)
— ‘Oasis in the desert’: NASA’s Curiosity rover finds pure sulfur in Martian rocks
— Little Mars snowman seen by NASA’s Perseverance rover (photo)
The scientists train the machine learning algorithm by feeding it examples of samples that MOMA might find on Mars, recognizing what they are so that the algorithm can identify them in real samples on its own, saving time the team.
“The long-term dream is a very autonomous mission,” said Da Poian. “Currently, MOMA’s machine learning algorithm is a tool to help scientists on Earth more easily study this critical data.”
Li and Da Poian see their algorithm as potentially helping future exploration beyond Mars, including Saturn’s moons Titan and Enceladus, and Jupiter’s moon Europa.
