In an effort to locate life somewhere else in the universe, NASA’s Frontier Development Lab has begun working with Google Cloud to develop capable simulations and machine-learning technology, according to The Register. Right now Earth is the only reference we have for what type of conditions are needed to foster life on a planet, but this new technology could produce “concrete models” of the ideal conditions on to support life, which would help to filter the billions of extraterrestrial bodies with such capabilities.
Atmos, the first of Google Cloud’s projects aimed at creating these simulations, “models a planet’s atmospheric properties, such as its density, temperature, chemical makeup, pressure, and the concentration of specific biological compounds,” wrote The Register. The software creates simulations that are then juxtaposed with real data in order to determine if a planet could potentially support life.
“Interestingly, Atmos starts with the concentrations of these molecules found on Earth, and then adjusts the concentrations in small increments to simulate an effectively limitless number of permutations, within rational or physically stable bounds,” Massimo Mascaro, technical director of applied AI at Google Cloud, explained.
NASA and Google are also collaborating on a project called INARA, which studies high-resolution photos to determine the chemical compounds that exist in the atmosphere of a rocky exoplanet. These exoplanets exist in habitable spaces around certain parent stars and possibly hold water on the surface.
In order to create INARA, which is a machine-learning-based software, the developers had to simulate snapshots of the chemical makeups of three million planets’. These snapshots are known as spectral signatures, and by entering this information into the convolutional neural network (CNN), the software can compare those spectral signatures with images and light curves of a planet atmosphere taken from NASA’s Kepler spacecraft to estimate that planet’s chemical composition.
Mascaro continued, “Given the scale of the datasets produced by the Kepler telescopes, and the even greater volume of data that will return to Earth from the soon-to-be-launched Transiting Exoplanet Survey Satellite (TESS) satellite, minimizing analysis time per planet can accelerate this research and ensure we don’t miss any viable candidates.”