AI studied the effect of radioactive radiation on astronauts

Scientists from the Frontier Development Lab (FDL) and Intel AI Mentors focused on studying the physical condition of astronauts to

find out how radiation affects themthe radiation they receive while working in space. To do this, experts used an AI model for the first time and developed an algorithm that independently finds markers of cancer development. The algorithm was trained on a large array of data - images of irradiation of mice and people.

To do this, scientists first had to prove thatradiation affects rodents in the same way as humans. After that, they were able to take as a basis an AI model and accurately predict what would happen to genes that were exposed to radiation.

25 sunsets and sunrises in three days: how ordinary people live in the SpaceX Dragon space capsule

At the same time, data on how much harmcosmic radiation, almost never published. Therefore, the researchers had to gain access to classified information about the astronauts. To do this, Intel and FDL specialists developed a causal machine learning algorithm - they were able to train AI by loading their data into it.

To obtain information, we used the clouda platform used by experts from NASA and the Mayo Clinic. The primary analysis was carried out locally, and the results were sent to a central repository for joint study by researchers.

Scientists have noted that radiation canbe very toxic to the body of astronauts. It penetrates through several layers of steel and affects all tissues. This leads to complications, the most dangerous of which is the risk of cancer.

Read more

Hawking was right, but sometimes wrong: the scientist's most daring ideas

Astronomers have figured out that the Earth and solar system are in a giant magnetic tunnel

Frozen mammoth and a man in the "asphalt": how nature stops time