301 exoplanets discovered by artificial intelligence

⇧ [VIDÉO] You may also like the content of this partner (after the ad)

ExoMiner, from its little name, is an artificial intelligence capable of processing data to determine whether a celestial object is an exoplanet or not. Recently, he was able to validate the existence of no less than 301 of them.

As a reminder, an exoplanet is a planet located outside the Solar System, which therefore revolves around a star other than the Sun. To date, 4,569 planets have already been validated. Yet there are millions of them, scientists say. However, the last 301 little ones were added to this cohort recently.

The person responsible for this acceleration is ExoMiner. This artificial intelligence is a “deep neural network”. To use Techtarget’s definition, “neural network deep learning, or ‘deep learning’, is an aspect of artificial intelligence (AI) that mimics the learning method humans use to acquire certain types of knowledge. In its simplest form, deep learning can be seen as a way to automate predictive analytics. “

In other words, ExoMiner can learn independently when sufficient data is provided. This AI was based on all confirmed and false positive exoplanets. It is backed by Pleiades, NASA’s supercomputer, that is, one of the most powerful in the world.

How does ExoMiner confirm the existence of exoplanets?

Let’s remember the definition of “planet”, which has also changed a lot over time. It is, according to the International Astronomical Union, a celestial body that orbits around the Sun or another star. It must also have enough mass for its gravity to keep it in a hydrostatic equilibrium situation. That is, it must be almost spherical in shape. It also eliminated any “rival” bodies moving in its orbit or in a close orbit. A planet is confirmed when different observation techniques reveal particular features that can only be explained by the presence of a planet. Finally, it is validated based on statistics, which determine the probability that it is actually one based on existing data.

When a planet passes directly between us and its star, we see that the star darkens slightly because the planet is blocking some of the light. Measuring these drops in starlight is a technique, known as the “transit method,” that scientists use to identify exoplanets. The researchers make a diagram called a “light curve” that shows the star’s brightness over time. Using this graph, they can see what percentage of the star’s light is blocking the planet and how long it takes to pass through the star’s disk, information that helps them estimate the distance from the star, the planet to the star, and its mass. . © Goddard Space Flight Center, NASA.

It is in this final step that ExoMiner is particularly useful. In fact, NASA’s Kepler Space Telescope and its successor, K2, have collected a great deal of data. Interpreting them is a colossal task. However, artificial intelligence did not do everything on its own: “The 301 machine-validated planets were initially detected by the pipeline of Kepler’s Science Operations Center and promoted to candidate planet status by the Kepler Office of Science,” he says. the Jet Propulsion Laboratory, a research arm of NASA. On the other hand, ExoMiner made it possible to validate these candidate planets efficiently.

For the laboratory, this tool is proving to be excellent in assisting humans in their work on these issues. Ya, because obviously it can calculate much faster, but also because it is free from the inevitable human biases. Finally, it is always possible to subsequently verify the reason for the AI ​​decisions: “Unlike other machine learning programs for the detection of exoplanets, ExoMiner is not a black box. We can easily explain what characteristics of the data lead ExoMiner to reject or confirm a planet, “said Jon Jenkins, an exoplanet scientist at NASA’s Ames Research Center in California.

Other exoplanet search missions, such as TESS (Transiting Exoplanet Reconnaissance Satellite) or PLATO (the European Space Agency’s upcoming PLAnetary Transits and Oscillations of stars mission), which use the transit photometry technique (see animation below ). Progress. So many opportunities to make your new exploration buddy work and evolve, for scientists who intend to switch them to these new missions after a few adjustments.

PHP Script, Elementor Pro Weadown, WordPress Theme, Fs Poster Plugin Nulled, Newspaper – News & WooCommerce WordPress Theme, Wordfence Premium Nulled, Dokan Pro Nulled, Plugins, Elementor Pro Weadown, Astra Pro Nulled, Premium Addons for Elementor, Yoast Nulled, Flatsome Nulled, Woocommerce Custom Product Ad, Wpml Nulled,Woodmart Theme Nulled, PW WooCommerce Gift Cards Pro Nulled, Avada 7.4 Nulled, Newspaper 11.2, Jannah Nulled, Jnews 8.1.0 Nulled, WP Reset Pro, Woodmart Theme Nulled, Business Consulting Nulled, Rank Math Seo Pro Weadown, Slider Revolution Nulled, Consulting 6.1.4 Nulled, WeaPlay, Nulledfire

Back to top button