Life, as we know it on Earth, requires a certain environment to survive. Even so, there are creatures on Earth that seem to survive in harsh environments, where the temperatures are very cold or where there is little water or oxygen. It is environments like these that are similar to those found on other planets. 

The quest for founding life on Mars has been going on for decades. In 1996 scientists mistakenly thought they had discovered life on Mars, but there has not been any concrete evidence. 

 A new study led by an international team of over 50 researchers ensures that the Mars research can be supported using AI and ML methods. This technology can be used to identify hidden patterns within geographical data that could indicate the presence of life on Mars.

History of Research 

In the past, Mars was different from today. Both Earth and Mars should have been frozen in their early history because the sun was weak at first. However, water was flowing in both the planets, which suggests that they both must have had thick atmospheres. 

Earth and Mars had volcanoes, but the Martian ones were never very active. This is an essential fact as volcanic eruptions produce large quantities of water.  

The Viking program of the 1970s was the first to return data that there is currently no evidence of life on Mars. As part of more thorough research, the Mars Surveyor Program was implemented. Five spacecraft were to be sent to Mars between 1996 and 2005. Those spacecrafts were to include the Mars Global Surveyor, the Mars Climate Orbiter and Polar Lander.  

Unfortunately, the Mars Climate Orbiter and Polar Lander were lost. However, scientists still hope that after all the information is gathered, they might be able to provide more information about the evolution of Mars and its potential to harbor life. 

Finding bio signatures- AI research 

During the first part of the study using the AI/ML model, led by Dr Kimberley Warren-Rhodes at the SETI Institute, was an ecological survey of a three km² area in the Salar de Pajonales basin at the boundary of the Chilean Atacama Desert and Altiplano in South America. This analyzed the distribution of microorganisms.  

The resulting model could locate and detect biosignatures up to 87.5% of the time on data on which it was not trained. This decreased the search area required to find the positive result by up to 97%. In the future, life on Mars could be detected through the identification of the areas most likely to contain signs of life. 

According to NASA, Warmth, Oxygen, and Water are the three most important life factors. 

One of the most similar analogues to Mars is the Pajonales, a four-million-year-old lakebed on Earth. This area is considered to be inhospitable to most forms of life. Comparable to the evaporitic basins of Mars, the high-altitude basin experiences strong levels of ultraviolet radiation, hyper salinity, and low temperatures.  

Presence of Water 

The researchers collected over 7700 images using the model. They tested for the presence of photosynthetic microbes living with the salt domes, rocks, and alabaster crystals that make up the basin’s surface.  

The ground sampling data and 3D topographical mapping were combined with the drone images to classify regions into four macro-habitats and six microhabitats. The team found that the microbial organisms across the study site were clustered in distinct regions.  

According to Dr Freddie Kalaitzis from the University of Oxford’s Department of Computer Science, the model demonstrated high predictive capability for the presence of geological materials strongly likely to contain biosignatures. Furthermore, the results aligned well with ground-truth data. 

Studying harsh ecosystems 

The researchers aim to test the model’s ability to predict the location of similar yet different natural systems. The data from these studies will inform and test hypotheses on the mechanisms that living organisms use to survive in extreme environments. 

The research demonstrated the power of ML methods to accelerate scientific discovery through its ability to analyze immense volumes of different data and identify patterns that would be indiscernible to a human being. The scientific community hopes the approach will facilitate the compilation of a databank of biosignature probability and habitability algorithms, roadmaps, and models that can guide the exploration of life on Mars. 

Image source: Unsplash

Content: NASA, Nature.com