AI’s quest to reveal life beyond earth’s borders...
In a paper published in the journal Proceedings of the National Academy of Sciences, a team of seven researchers reveals that their AI-driven approach can effectively tell apart modern and ancient biological samples from non-living ones with an accuracy rate of 90%.
This test has immediate applications in uncovering the origins of enigmatic ancient Earth rocks and potentially shedding light on samples gathered by the Mars Curiosity rover’s onboard analytical tool known as SAM, Sample Analysis at Mars.
AI was trained using extensive multidimensional data obtained from the molecular analysis of 134 known carbon-rich samples, both living and non-living. It achieved an accuracy rate of approximately 90% in identifying the origin of new samples. These origins included:
- Living organisms like shells, teeth, bones, insects, leaves, rice, human hair, and cells preserved in fine-grained rock.
- Traces of ancient life transformed by geological processes, such as coal, oil, amber, and carbon-rich fossils.
- Samples with non-living origins, such as pure laboratory chemicals (e.g., amino acids) and carbon-rich meteorites.
This innovative approach has sparked fresh concepts regarding its potential applications in other domains, including biology, palaeontology, and archaeology.
image: @NicoElNino