We already have AI to create images, to create texts, to make videos, to answer emails, to identify health problems… AI is even in the soup, but not only in the soup here, no, also in the soup on Mars.

As you already know, the search for life on Mars has been one of the greatest challenges in astrobiology. However, the use of artificial intelligence (AI) and machine learning can help identify patterns in geographic data and find signs of life on the red planet. In a study published in Nature Astronomy, an international team of researchers led by SETI Institute astrobiologist Kimberley Warren-Rhodes shows that these tools can identify hidden patterns in geographic data that could indicate the presence of life.

The Search for Life on Mars

Despite the fascination aroused by the possibility of finding life on Mars, the task is arduous. Mars has almost the same land area as Earth, but its life history is a big unanswered question. Therefore, it is essential to know where to look and make optimal use of the available opportunities in order not to miss the trip.

The use of artificial intelligence and machine learning can make the search for life on Mars much less difficult. Warren-Rhodes and her colleagues have shown that these approaches can identify hidden patterns in geographic data and uncover and predict the patterns and rules by which nature survives and thrives in Earth’s most hostile landscapes.

The use of Artificial Intelligence in the study

The team of researchers focused on a region on the border between the Atacama Desert and the Altiplano in Chile, called Salar de Pajonales. This basin is an ancient riverbed and one of the best Mars analogues on Earth. At 3,541 meters altitude, it receives high UV exposure and is extremely dry and salty. However, life can be found there, living in mineral formations.

For the study, the researchers took 7,765 images and 1,154 samples, looking for biosigns that reveal the presence of photosynthetic microbes. They used drones to take aerial images and added 3D topographic maps to train the AI ​​to recognize structures in the basin that are more likely to be teeming with life. The results demonstrated that the CNNs identified patterns in the distribution of microbial life in the basin, despite the uniformity of its mineral composition.

The gypsum ore domes were about 40 percent inhabited, while the gypsum-striped ribbed land was about 50 percent inhabited. The researchers found microhabitats in these structures and discovered that the microbes were attracted to sections of alabaster, a thin, porous form of plaster that retains water. These alabaster microhabitats turned out to be the most reliable predictor of biosigns, suggesting that water content is the main driver of microhabitat distribution.

Results and Potential of the Study

The results of the study demonstrate that the use of AI and machine learning can identify biosigns on Mars with much higher accuracy than random searches. Reducing the area that needs to be covered can save valuable time and resources in the search for life on Mars. In addition, the study also yielded valuable information about life in extreme environments here on Earth.

The researchers plan to expand their study and train their CNNs on other biosignatures, such as stromatolites and halophile communities. The goal is to design custom roadmaps and algorithms to guide rovers to the places most likely to harbor past or present life, regardless of how hidden or rare they may be.

The study demonstrates the potential of AI and machine learning in astrobiology and space exploration in general. Combining statistics and ecology with cutting-edge technology can help uncover patterns and rules that guide life in the most hostile landscapes on our planet and beyond.

Ultimately, the use of technology to search for life on other planets raises profound questions about our place in the universe and the possibility of life on other worlds. The search for life on Mars is just the beginning of a new era of exploration and discoveries that could change our understanding of life and the universe itself.