An experiment on a Martian analogue in northern Chile has proven the usefulness of teaming planetary robots with artificial intelligence to focus the search for life in the most efficient way.
In an article published in Nature Astronomy, an interdisciplinary study led by Kim Warren-Rhodes, Principal Investigator at the SETI Institute, mapped the scant life hidden in salt domes, rocks and crystals in the Salar de Pajonales, on the border between the Chilean desert of Atacama and the Altiplano.
Next, Warren-Rhodes worked with co-investigators Michael Phillips (Johns Hopkins Applied Physics Laboratory) and Freddie Kalaitzis (University of Oxford) to train a machine learning model that would recognize the patterns and rules associated with their distributions so that they could learn to predict and find those same distributions in data on which he had not been trained.
In this case, by combining statistical ecology with artificial intelligence/machine learning, scientists were able to locate and detect biosignatures up to 87.5% of the time (versus 10% using random search) and decrease the area needed to search up to 97%.
“Our framework allows us to combine the power of statistical ecology with machine learning to discover and predict the patterns and rules by which nature survives and distributes itself in the harshest landscapes on Earth,” Rhodes said in a statement. “We hope other astrobiology teams will adapt our approach to mapping other habitable environments and biosignals. With these models, we can tailor roadmaps and algorithms to guide rovers to locations most likely to harbor past or present life, no matter how hidden or rare it is”.
Ultimately, similar algorithms and machine learning models for many different types of habitable environments and biosignatures could be automated aboard planetary robots to effectively guide mission planners to zones of any scale most likely to contain life.
Rhodes and the SETI Institute’s NASA Astrobiology Institute (NAI) team used the Salar de Pajonales as an analogue for Mars. Pajonales is a dry, hyperarid, high altitude (3,541 m) and high U/V saline bed, considered inhospitable to many forms of life, but still habitable.
During the NAI project field campaigns, the team collected more than 7,765 images and 1,154 samples and tested instruments to detect photosynthetic microbes living inside salt domes, rocks and alabaster crystals. These microbes exude pigments that represent a possible biosignature in NASA’s Ladder of Life Detection.
At Pajonales, drone flight imagery connected simulated orbital data (HiRISE) with ground surveys and 3D topographic mapping to extract spatial patterns. The results of the study confirm (statistically) that microbial life in the Pajonales terrestrial analogue site is not randomly distributed, but is concentrated in irregular biological points strongly linked to water availability at km to cm scales.
Next, the team trained convolutional neural networks (CNNs) to recognize and predict macroscale geological features on Pajonales – some of which, such as patterned soil or polygonal networks, are also found on Mars – and microscale substrates (or “microhabitats”) most likely to contain biosignatures.
Like the Perseverance team on Mars, the researchers tested how to effectively integrate a UAV/drone with rovers, drills, and ground-based instruments (for example, VISIR on ‘MastCam-Z’ and Raman on ‘SuperCam’ on the Perseverance Mars rover). 2020).
