Human WorldSpace

New AI tool can help find alien life in the solar system

Circuit board-type pattern, shaped like a brain, inside a sphere of thousands of tiny dots.
View larger. | Artist’s visualization of an artificial neural network. Scientists are talking about using AI to help find alien life in our solar system. Image via mikemacmarketing/ Wikimedia Commons (CC BY 2.0 DEED).

Artificial intelligence (AI) is fast becoming an integral part of our modern society. The number of things it can be used for seems almost endless. Astronomers are already using it to study galaxies, stars and planets. And one of the potential uses could help us solve the biggest question of all … are we alone? A new machine learning technique offers that possibility: testing for current or past life in our solar system with 90% accuracy. Researchers at Carnegie Science developed the new AI-based technique and announced it on September 25, 2023. They called it the holy grail of astrobiology.

The researchers, led by Robert Hazen at Carnegie, published their peer-reviewed findings in Proceedings of the National Academy of Sciences on September 25, 2023.

The 2024 lunar calendars are here! Best Christmas gifts in the universe! Check ’em out here.

The paper stated:

We report a significant advance to one of the most important problems in astrobiology, the development of a simple, reliable and practical method for determining the biogenicity of organic materials in planetary samples, both on other worlds and for the earliest traces of life on Earth.

AI could make searching for alien life easier

The purpose of the new AI tool is to analyze and distinguish between biological and non-biological origins of samples from Mars or other potentially habitable places in the solar system. The technique is touted as being able to more easily tell the difference between biological and non-biological origin. New spacecraft missions could use it on samples that they obtain. As Hazen explained:

This routine analytical method has the potential to revolutionize the search for extraterrestrial life and deepen our understanding of both the origin and chemistry of the earliest life on Earth. It opens the way to using smart sensors on robotic spacecraft, landers and rovers to search for signs of life before the samples return to Earth.

Another possible application would be the Sample Analysis at Mars (SAM) instrument on NASA’s Curiosity rover. Lead author Jim Cleaves at the Tokyo Institute of Technology said:

The search for extraterrestrial life remains one of the most tantalizing endeavors in modern science. The implications of this new research are many, but there are three big takeaways: First, at some deep level, biochemistry differs from abiotic organic chemistry; second, we can look at Mars and ancient Earth samples to tell if they were once alive; and third, it is likely this new method could distinguish alternative biospheres from those of Earth, with significant implications for future astrobiology missions.

Testing for life with 90% accuracy

So how does it work? Unlike other types of testing, the technique doesn’t just search for particular kinds of molecules or compounds. Rather, it looks for subtle differences in a sample’s molecular patterns that are revealed by pyrolysis gas chromatography analysis. This analysis separates and identifies the component parts of the sample. Then, scientists use mass spectrometry (the mass-to-charge ratio) to analyze the molecular weights of those components.

For the new technique, the researchers used 134 known abiotic (not produced by life) or biotic (originating from life) carbon-rich samples. Molecular analysis then used multidimensional data from the samples to train the AI algorithm. Now, it could “predict” the origin of a sample with 90% accuracy. Impressive! The paper said:

We have developed a robust method that combines pyrolysis GC-MS measurements of a wide variety of terrestrial and extraterrestrial carbonaceous materials with machine-learning-based classification to achieve ~90% accuracy in the differentiation between samples of abiotic origins vs. biotic specimens, including highly degraded, ancient, biologically derived samples.

The predicted origins fall into three categories:

– Living things, like shells, teeth, bones, insects, leaves, rice, human hair and cells preserved in fine-grained rock.

– Remnants of ancient life altered by geological processing (e.g. coal, oil, amber and carbon-rich fossils).

– Samples with abiotic origins, such as pure laboratory chemicals (e.g., amino acids) and carbon-rich meteorites.

Finding evidence of life isn’t easy

Determining whether samples of carbon are biological in origin is not always easy, as carbon degrades over time. Despite that, the new technique successfully found evidence of ancient biology in samples hundreds of millions of years old. Hazen said:

We began with the idea that the chemistry of life differs fundamentally from that of the inanimate world; that there are ‘chemical rules of life’ that influence the diversity and distribution of biomolecules. If we could deduce those rules, we can use them to guide our efforts to model life’s origins or to detect subtle signs of life on other worlds.

The new tool can find more nuanced attributes in the samples than other techniques. The researchers likened it to separating coins by their various attributes, such as monetary value, type of metal, year of minting, weight or radius. Anirudh Prabhu at Carnegie Science said:

And when hundreds of such attributes are involved, AI algorithms are invaluable to collate the information and create highly nuanced insights.

AI: Numerous small, slightly wriggly rod-like objects on a gray rocky surface.
Scientists discovered these microscopic rod-like objects inside Martian meteorite ALH84001 in 1996. The debate still rages today as to whether these could be fossilized microorganisms or if they’re non-biological structures. Now, with a new artificial intelligence (AI) technique, scientists can better determine whether formations such as these and others are biological in origin or not. Image via NASA/ JSC/ Stanford University.

Learning more about life on Earth with AI

Scientists could also use the AI test to learn more about the history of ancient geology and life on Earth. This includes the origin of 3.5-billion-year-old black sediments from Western Australia. Scientists are still debating the origins of these rocks. Some think they contain Earth’s oldest fossil microbes, while others claim they are devoid of any remnants of life. Other rocks are still being debated as well, including ones from Northern Canada, South Africa and China. Hazen said:

We’re applying our methods right now to address these long-standing questions about the biogenicity of the organic material in these rocks.

In addition, the new AI tool could assist researchers in other fields of study, including palaeontology and even archeology. As Hazen surmised:

If AI can easily distinguish biotic from abiotic, as well as modern from ancient life, then what other insights might we gain? For example, could we tease out whether an ancient fossil cell had a nucleus, or was photosynthetic? Could it analyze charred remains and discriminate different kinds of wood from an archeological site? It’s as if we are just dipping our toes in the water of a vast ocean of possibilities.

Perhaps the earliest known wood structure found so far – just reported late last month – would be a good candidate for this? Almost half a million years old and discovered in central Africa, the evidence suggests that early hominins made it … long before Homo sapiens appeared.

Bottom line: Researchers in the U.S. and Japan have developed a new AI technique that can determine if there is evidence for past or present life, or not, with 90% accuracy.

Source: A robust, agnostic molecular biosignature based on machine learning

Via Carnegie Science

Read more: Astronomers report success with machine deep learning

Read more: Artificial intelligence: Thoughts by astronomer Guy Ottewell

October 15, 2023
Human World

Like what you read?
Subscribe and receive daily news delivered to your inbox.

Your email address will only be used for EarthSky content. Privacy Policy
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

More from 

Paul Scott Anderson

View All