MSGID: 1:317/3 6447576c   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Researchers use AI to discover new planet outside solar system    
    The exoplanet was detected using machine learning, a branch of artificial   
   intelligence    
      
     Date:   
         April 24, 2023   
     Source:   
         University of Georgia   
     Summary:   
         A research team has confirmed evidence of a previously unknown   
         planet outside of our solar system, and they used machine learning   
         tools to detect it. A recent study by the team showed that machine   
         learning can correctly determine if an exoplanet is present by   
         looking in protoplanetary disks, the gas around newly formed   
         stars. The newly published findings represent a first step toward   
         using machine learning to identify previously overlooked exoplanets.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
      
   ==========================================================================   
   FULL STORY   
   ==========================================================================   
   A University of Georgia research team has confirmed evidence of a   
   previously unknown planet outside of our solar system, and they used   
   machine learning tools to detect it.   
      
   A recent study by the team showed that machine learning can correctly   
   determine if an exoplanet is present by looking in protoplanetary disks,   
   the gas around newly formed stars.   
      
   The newly published findings represent a first step toward using machine   
   learning to identify previously overlooked exoplanets.   
      
   "We confirmed the planet using traditional techniques, but our models   
   directed us to run those simulations and showed us exactly where the   
   planet might be," said Jason Terry, doctoral student in the UGA Franklin   
   College of Arts and Sciences department of physics and astronomy and   
   lead author on the study.   
      
   "When we applied our models to a set of older observations, they   
   identified a disk that wasn't known to have a planet despite having   
   already been analyzed.   
      
   Like previous discoveries, we ran simulations of the disk and found   
   that a planet could re-create the observation."  According to Terry,   
   the models suggested a planet's presence, indicated by several images   
   that strongly highlighted a particular region of the disk that turned   
   out to have the characteristic sign of a planet -- an unusual deviation   
   in the velocity of the gas near the planet.   
      
   "This is an incredibly exciting proof of concept. We knew from our   
   previous work that we could use machine learning to find known forming   
   exoplanets," said Cassandra Hall, assistant professor of computational   
   astrophysics and principal investigator of the Exoplanet and Planet   
   Formation Research Group at UGA. "Now, we know for sure that we can use   
   it to make brand new discoveries."  The discovery highlights how machine   
   learning has the power to enhance scientists' work, utilizing artificial   
   intelligence as an added tool to expand researchers' accuracy and more   
   efficiently economize their time when engaged in such a vast endeavor   
   as investigating deep, outer space.   
      
   The models were able to detect a signal in data that people had already   
   analyzed; they found something that previously had gone undetected.   
      
   "This demonstrates that our models -- and machine learning in general --   
   have the ability to quickly and accurately identify important information   
   that people can miss. This has the potential to dramatically speed up   
   analysis and subsequent theoretical insights," Terry said. "It only took   
   about an hour to analyze that entire catalog and find strong evidence for   
   a new planet in a specific spot, so we think there will be an important   
   place for these types of techniques as our datasets get even larger."   
       * RELATED_TOPICS   
             o Space_&_Time   
                   # Extrasolar_Planets # Eris_(Xena) # Astronomy   
             o Matter_&_Energy   
                   # Physics # Engineering # Solar_Energy   
             o Computers_&_Math   
                   # Computer_Modeling # Neural_Interfaces #   
                   Mathematical_Modeling   
       * RELATED_TERMS   
             o Extrasolar_planet o Data_mining o Wind_turbine o   
             Alan_Turing o History_of_Earth o Artificial_intelligence o   
             Definition_of_planet o Full_motion_video   
      
   ==========================================================================   
   Story Source: Materials provided by University_of_Georgia. Original   
   written by Alan Flurry.   
      
   Note: Content may be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. J. P. Terry, C. Hall, S. Abreau, S. Gleyzer. Kinematic Evidence   
      of an   
         Embedded Protoplanet in HD 142666 Identified by Machine   
         Learning. The Astrophysical Journal, 2023; 947 (2): 60 DOI:   
         10.3847/1538-4357/acc737   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/04/230424133426.htm   
      
   --- up 1 year, 8 weeks, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 218/700 226/30 227/114   
   SEEN-BY: 229/110 112 113 307 317 400 426 428 470 664 700 292/854 298/25   
   SEEN-BY: 305/3 317/3 320/219 396/45   
   PATH: 317/3 229/426