New Machine Learning Model Poised to Aid Researchers Searching For Life on Mars And Elsewhere

A team of multidisciplinary scientists led by Kim Warren-Rhodes of the SETI Institute in California has developed a new machine learning tool that could help scientists search for signs of life on Mars and other alien worlds by training it on some of Earth’s most alien landscapes. The push to use machine learning and other tools comes from the limited ability of scientists to study signs of life up close.

Because they are unable to collect samples from other planets directly, they have to rely on remote sensing methods to hunt for signs of alien life. However, with the new tool developed by the team, it will be possible to direct or refine the search for signs of life more effectively. If successful, this new machine learning model could prove to be an effective way of unearthing evidence of life that originates outside of Earth.

But how does this machine learning model know what to look for? Well according to the report, the team mapped the sparse lifeforms that dwell in salt domes, rocks, and crystals in the Salar de Pajonales, a salt flat on the boundary of the Chilean Atacama Desert and Altiplano. The similarities between this and the martial landscape were a big reason why they choose it to train the model.

The choice of using Salar de Pajonales as a testing stage for their machine learning model because it is a suitable analog for the dry and arid landscape of modern-day Mars. The team collected almost 8,000 images and over 1,000 samples from Salar de Pajonales to detect photosynthetic microbes living within the region’s salt domes, rocks, and alabaster crystals. This allowed the machine learning model to recognize the patterns and rules associated with the distribution of life across the harsh region.

The goal of which is for both to be applied to a wide range of landscapes, including those that may lie on other planets. And it seems to have done well. According to the report, the team discovered that their system could locate and detect biosignatures up to 87.5% of the time, compared to no more than a 10% success rate achieved by random searches. Additionally, the program could decrease the area needed for a search by as much as 97%, thus helping scientists significantly hone in their hunt for potential chemical traces of life or biosignatures.

One of the immediate benefits of the machine learning tool, in theory, could be applied to robotic planetary missions like that of NASA’s Perseverance rover, which is currently hunting for traces of life on the floor of Mars’ Jezero Crater. The researchers say such models could help design tailor-made roadmaps and algorithms to guide rovers to places with the highest probability of harboring past or present life, no matter how hidden or rare.

If proven successful, this could be a landmark achievement as Mars still has swaths of land yet to be properly explored and documented. By zeroing on areas most likely to house evidence of life, mission time and resources can be saved and used elsewhere.  But their work isn’t done yet. The team plans to continue training their AI at Salar de Pajonales, aiming to test the machine learning model’s ability to predict the location and distribution of ancient stromatolite fossils and salt-tolerant microbiomes.

This should help it to learn if the rules it uses in this search could also apply to the hunt for biosignatures in other similar natural systems. The team aims to begin mapping hot springs, frozen permafrost-covered soils, and the rocks in dry valleys all of which have very similar conditions to planets and moons in the solar system researchers hope to find evidence for life.

This isn’t the first case of a team of researchers looking to machine learning to aid their quest in finding alien life. Back in early February, it was reported that with aid of machine learning eight potential technosignatures were found around five nearby stars. In that report, researchers analyzed over 150 terabytes of data, which represented the observations of 820 nearby stars.  Due to the vast distances and resource constraints faced by researchers, AI and machine learning are fast becoming methods in their quest to solve the biggest mysteries of the cosmos.