The algorithm "deep learning" reveals the huge storm of Saturn in a new light



[ad_1]

A new "in-depth learning" algorithm that could help scientists better understand planetary atmospheres has passed its first major test, according to a new study.

The software, called PlanetNet, has detailed a 2008 monster 2008 Saturn storm system using data collected by Cassini spacecraft from NASA, who studied the planet encircled from almost 2004 to 2017.

"Missions like Cassini gather huge amounts of data, but conventional analysis techniques have drawbacks, both in terms of the accuracy of the information that can be retrieved or the time needed to execute it. In-depth learning allows pattern recognition in various data sets "The author of the study, Ingo Waldmann, deputy director of the Center for Space and Exoplanet Data at University College London in England, said in a statement.

Related: Cassini Orbiter Saturn's Amazing Photos from NASA

Distribution of the cloud as mapped by the PlanetNet algorithm on six overlapping datasets. The stormy region function (blue) appears near dark storms (purple / green), unlike undisturbed regions (red / orange). The area covered by the multiple storm system is about 70% of the Earth's surface.

(Image: © Waldmann and Griffith / Nature Astronomy)

"This gives us the potential to analyze atmospheric phenomena over large areas and from different viewing angles and to establish new associations between the shape of the features and the chemical and physical properties that create them," added Waldmann.

PlanetNet searches datasets for evidence of "clustering" in cloud structure and atmospheric composition, and then uses this information to generate accurate maps. Waldmann and Caitlin Griffith, co-head of the lunar and global laboratory study at the University of Arizona, have trained and tested the algorithm using data collected by the spectrometer Visualization and Infrared Visualization (VIMS) of Cassini.

For the new study, published online today (April 29) in the journal Nature Astronomy, the duo chose a dataset containing VIMS observations from a multi-storm system that boiled at Saturn in February 2008. This was a challenge because the system was complex and quite large. Together, its various components cover an area equivalent to about 70% of the Earth's surface, the researchers said.

PlanetNet has used this information to provide new information on storms. For example, his maps showed that a previously observed S-shaped ammonia cloud was actually part of a much larger upwelling that surrounded a dark storm. And PlanetNet has detected a similar feature around a different storm, suggesting that ammonia ice rises are common in the Saturn atmosphere, the researchers said.

"PlanetNet allows us to analyze much larger volumes of data, which allows us to better understand the large-scale dynamics of Saturn, "Griffith said in the same statement." The results reveal atmospheric features that were previously undetected. PlanetNet can easily be adapted to other data sets and planets, making it an invaluable potential tool for many future missions. "

Mike Wall's book on the search for extraterrestrial life, "Over there"(Grand Central Publishing, 2018, illustrated by Karl Tate), is out now. Follow him on Twitter @michaeldwall. Follow us on twitter @Spacedotcom or Facebook.

[ad_2]

Source link