New AI Model Reveals Hidden Turbulence in the Sun’s Atmosphere

(ORDO NEWS) — The hidden turbulent motion that occurs inside the Sun’s atmosphere can be accurately predicted by a newly developed neural network.

Given only temperature and vertical motion data collected from the surface of the solar photosphere, the AI ​​model was able to correctly identify turbulent horizontal motion below the surface. This may help us better understand solar convection and the processes that cause explosions and jet ejections on the Sun.

“We have developed a new ultra-precise neural network to estimate the spatial distribution of horizontal velocity using the spatial distribution of temperature and vertical velocity,” said a team of researchers led by astronomer Ryohtaro Ishikawa of Japan‘s National Astronomical Observatory.

“This resulted in effective detection of spatially scattered objects and concentrated objects. [..] Our network has shown superior performance across almost all spatial scales compared to those reported in previous studies.”

The solar photosphere is the region of the Sun’s atmosphere that is commonly referred to as its surface. This is the lowest layer of the solar atmosphere and the region in which solar activity occurs, such as sunspots, solar flares, and coronal mass ejections.

If you look closely, the surface of the photosphere is not uniform. It is covered with areas smoothed to each other, lighter in the middle and darker towards the edges.

They are called granules, and they are the tops of the convection cells in the solar plasma. The hot plasma rises in the middle and then falls down at the edges, moving outward and cooling.

When we observe these cells, we can measure their temperature as well as their movement through the Doppler effect, but horizontal movement cannot be directly detected.

However, the smaller scale currents in these cells can interact with the solar magnetic fields, causing other solar phenomena. In addition, turbulence is thought to play a role in heating the solar corona, so scientists are keen to understand exactly how plasma behaves in the photosphere.

Ishikawa and his team developed a numerical simulation of plasma turbulence and used three different simulation datasets to train their neural network. They found that based solely on temperature and vertical flux data, AI can accurately describe horizontal fluxes in simulations that cannot be detected on the real Sun.

This means that we can feed it data and expect the results it returns to be consistent with what is actually happening on our charming, unapproachable star.

Online:

Contact us: [email protected]

Our Standards, Terms of Use: Standard Terms And Conditions.