MARS — PHOTOGRAPHED BY NASA'S PERSEVERANCE ROVER (IMAGE CREDIT: NASA/JPL-CALTECH/ASU/MSSS)
A new machine-learning model has been developed to help scientists search for signs of life on Mars and other planets.
The model was trained using data from the Salar de Pajonales in Chile, a harsh environment with sparse lifeforms.
By combining statistical ecology with AI, the system can locate and detect biosignatures up to 87.5% of the time, compared to a 10% success rate for random searches.
- The program can decrease the area needed for a search by as much as 97%, helping scientists significantly hone their quest for potential chemical traces of life.
- The model could be applied to robotic planetary missions, like NASA's Perseverance rover, which is currently hunting for traces of life on Mars.
- Salar de Pajonales was chosen as a testing stage because it is a suitable analog for the arid landscape of modern-day Mars.
- The team collected almost 8,000 images and over 1,000 samples to detect photosynthetic microbes within the region's salt domes, rocks, and alabaster crystals.
The researchers will continue to train their AI at Salar de Pajonales and aim to begin mapping hot springs, frozen permafrost-covered soils, and rocks in dry valleys.
