A Mars analogue experiment in northern Chile has proven the usefulness of combining planetary robots and artificial intelligence to focus on searching 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, found hidden in the salt domes, rocks and crystals of the Pajonales salt flats on the border with the Chilean desert. A few lives have been mapped. Atacama and Altiplano.
Warren-Rhodes then collaborated with collaborators Michael Phillips (Johns Hopkins Applied Physics Laboratory) and Freddie Kalaitzis (University of Oxford) to train machine learning models to recognize patterns and rules related to distributions. Did. Predict and find the same distribution on the data he was not trained on.
In this case, by combining statistical ecology with artificial intelligence/machine learning, scientists have up to 87.5% chance of finding and detecting biosignatures (10% when using random search) and identifying the region needed for search. can be reduced by 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 in some of the most extreme landscapes on Earth. ”
Rose said in a statement.
“We hope other astrobiology teams will adapt our approach to map other habitable environments and biosignals. We will use these models to adjust our roadmaps and algorithms.” to guide the rover to where past or present life is most likely hidden.”.
Ultimately, similar algorithms and machine learning models for different types of habitable environments and biosignatures will be loaded and automated on planetary robots, allowing mission planners to adapt to any scale where life is most likely to exist. can effectively lead to the zone of
The NASA Astrobiology Institute (NAI) team on Rhodes and the SETI Institute used the Pahonales salt flats as a Mars analogue. Pajonales is a dry, ultra-arid highland (3,541 m) high-ultraviolet saline formation that is considered inhospitable to many organisms, but is nevertheless habitable.
During field campaigns for the NAI project, the team collected over 7,765 images and 1,154 samples to test instruments and detect photosynthetic microbes living inside salt domes, rocks and alabaster crystals. These organisms exude pigments that represent potential biosignatures in NASA’s Ladder of Life Detection.
Pajonales combined drone flight imagery with simulated trajectory data (HiRISE) with ground surveys and 3D terrain mapping to extract spatial patterns. The results of this study suggest that the microbial life of the Pajonales terrestrial analogue sites is not randomly distributed, but rather concentrated at irregular biological points strongly associated with water availability on the km to cm scale. It is (statistically) confirmed that
The team then trained a convolutional neural network (CNN) to identify Pajonales’ macro-scale geological features (some of which are also found on Mars, such as patterned soil and polygonal networks) and micro-scale geological features. Substrates (or “microhabitats”) were recognized and predicted. Contains a biosignature.
Similar to the Perseverance team on Mars, researchers are investigating how to effectively integrate UAV/drone with rovers, drills, and ground equipment (e.g., VISIR on Perseverance Mars rover ‘MastCam-Z’ and Raman on ‘SuperCam’). tested. ) 2020).