Neural networks predict planet mass

March 13, 2019, University of Bern
Julia Venturini, NCCR PlanetS. Credit: © NCCR PlanetS

To find out how planets form, astrophysicists run complicated and time-consuming computer calculations. Members of the NCCR PlanetS at the University of Bern have now developed a totally novel approach to speed up this process dramatically. They use deep learning based on artificial neural networks, a method that is well known in image recognition.

Planets grow in stellar disks, accreting solid material and gas. Whether they become bodies like Earth or Jupiter depends on different factors like the properties of the solids, the pressure and temperature in the disk and the already accumulated material. With computer models the astrophysicists try to simulate the growth process and determine the interior planetary structure. For given boundary conditions they calculate the masses of the gas envelope of a planet. "This requires solving a set of differential equations," explains Yann Alibert, science officer of the NCCR PlanetS at the University of Bern: "Solving these equations has been a specialty of the astrophysicists here in Bern for the past 15 years, but it is a complicated and time consuming process."

To speed up the calculations Yann Alibert and PlanetS associate Julia Venturini of the International Space Science Institute (ISSI) in Bern adopted a method that has already captured many other fields, including smartphone development: . It is, for instance, used for face and image recognition. But this branch of artificial intelligence and has also improved automatic language translation and is crucial for self-driving cars. "There is a big hype also in astronomy," says Alibert. "Machine learning has already been used to analyze observations, but to my knowledge, we are the first to use deep learning for such a purpose." Alibert and Venturini publish their results in the journal Astronomy and Astrophysics (A&A).

Database of millions of planets

First, the researchers had to create a database. They calculated millions of possible interior structures of . "It took us three weeks to compute all these using a code developed by Julia Venturini during her Ph.D. in Bern," says Alibert. The next step was to decide the architecture of an artificial neural network, a set of algorithms that passes input data through mathematical operations and has the ability to learn without being explicitly programmed. "Then, we trained this network using our gigantic database," says the astrophysicist. "Now, our network is able to predict the mass of a planet being formed under certain conditions with a very good accuracy and tremendously faster than solving the differential equations."

The deep learning process is much more precise than previously developed methods to replace the solution of differential equations by some analytical formulas. These analytical formulas could predict that a planet should grow up to the mass of Jupiter, while in reality it could not have more mass than Neptune. "We show that our deep neural networks provide a very good approximation at the level of percents," summarizes Alibert. The researchers provide their results on the software development platform GitHub, so that colleagues working in planet formation all around the world benefit from them.

Explore further: Jupiter had growth disorders

More information: Yann Alibert, Julia Venturini: Using Deep Neural Networks to compute the mass of forming planets, Astronomy and Astrophysics (A&A), March 2019, arxiv.org/abs/1903.00320

Related Stories

Jupiter had growth disorders

August 28, 2018

Researchers of the Universities of Bern and Zürich and of ETH Zürich show how Jupiter was formed. Data collected from meteorites had indicated that the growth of the giant planet was delayed for 2 million years. Now, the ...

New theoretical models aid the search for Earth-like planets

November 14, 2013

Researchers from Bern have developed a method to simplify the search for Earth-like planets: By using new theoretical models they rule out the possibility of Earth-like conditions, and therefore life, on certain planets outside ...

How planetary age reveals water content

June 30, 2016

Water is necessary for life as we know it, but too much water is bad for habitability. Therefore, to study the habitability of extrasolar planets, determining the abundance of water is a key element. Yann Alibert, Science ...

Recommended for you

Study reveals properties of a Type Ib supernova in NGC 4080

March 25, 2019

A recent study conducted by astronomers has revealed important observational properties of a Type Ib supernova designated MASTER OT J120451.50+265946.6, which exploded in the galaxy NGC 4080. The research, presented in a ...

Catalyst advance removes pollutants at low temperatures

March 25, 2019

Researchers at Washington State University, University of New Mexico, Eindhoven University of Technology, and Pacific Northwest National Laboratory have developed a catalyst that can both withstand high temperatures and convert ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.