老司机直播

Google and Netflix use it: algorithms can also predict our solar system's stability, say 老司机直播 researchers

photo illustration of planets colliding
Artist's depiction of a collision between two planetary bodies (photo illustration by NASA/JPL-Caltech)

Machine learning is used today for everything from detecting fraud and sorting spam in Google to recommending movies on Netflix. 

Now a team of University of Toronto researchers has developed a novel approach to using algorithms to determine whether planetary systems are stable. 

鈥淢achine learning offers a powerful way to tackle a problem in astrophysics, and that鈥檚 predicting whether planetary systems are stable,鈥 says Dan Tamayo, lead author of a report published online in the .

The postdoctoral researcher in the Centre for Planetary Science at 老司机直播 Scarborough and his team have developed a method that's 1,000 times faster than traditional means of predicting solar system stability.

Planetary system stability can tell us a great deal about how these systems formed, Tamayo said, adding that it can also offer valuable new information about exoplanets that is not offered by current methods of observation. 

The findings could come in handy when analyzing data from NASA鈥檚 Transiting Exoplanet Survey Satellite (TESS) set to launch next year.  The two-year mission will focus on discovering new exoplanets by focusing on the brightest stars near our solar system. 

鈥淚t could be a useful tool because predicting stability would allow us to learn more about the system from the upper limits of mass to the eccentricities of these planets,鈥 says Tamayo. 鈥淚t could be a very useful tool in better understanding those systems.鈥 


老司机直播 Scarborough planetary science researcher Dan Tamayo wants to use algorithms to study solar system stability (photo by Ken Jones)

There are several methods of detecting exoplanets that provide information such as the size of the planet and its orbital period. But they may not provide the planet鈥檚 mass or how elliptical their orbit is, which are all factors that affect stability, notes Tamayo. 

鈥淚n the past we鈥檝e been hamstrung in trying to figure out whether planetary systems are stable by methods that couldn鈥檛 handle the amount of data we were throwing at it,鈥 he says. 

The method developed by Tamayo and his team is the result of a series of workshops at 老司机直播 Scarborough covering how machine learning could help tackle specific scientific problems. 

鈥淲hat鈥檚 encouraging is that our findings tell us that investing weeks of computation to train machine learning models is worth it because not only is this tool accurate, it also works much faster,鈥 he adds.

Topics

The Bulletin Brief logo

Subscribe to The Bulletin Brief