ICEINSPACE
Most Read Articles
Moon Phase
CURRENT MOON Waning Gibbous
97.5%
The Sun Now
Time Zones
Sydney
1:41 am
Perth
11:41 pm
Auckland
3:41 am
New York*
11:41 am
Paris*
5:41 pm
GMT
3:41 pm




Go Back   IceInSpace > General Astronomy > Astronomy and Amateur Science

Reply
 
Thread Tools Rate Thread
  #1  
Old 15-12-2017, 10:21 AM
gary
Registered User

gary is offline
 
Join Date: Apr 2005
Location: Mt. Kuring-Gai
Posts: 4,832
Google neural network helps discover two new exoplanets by scrutinizing Kepler data

In a widely published story today, NASA and Google have used a neural
network developed at Google to crunch through data from the Kepler space
telescope and in the process discovered two new exoplanets.

Quote:
Originally Posted by Ry Crozier, IT News
The neural model runs using Google-developed TensorFlow technology and was trained on a dataset of 15,000 - out of a possible 35,000 - suspected planetary “signals”.

These signals are in the light readings recorded by Kepler - what NASA says are “minuscule changes in brightness captured when a planet passed in front of, or transited, a star".

“The measured brightness of a star decreases ever so slightly when an orbiting planet blocks some of the light,” Google said.

“The Kepler space telescope observed the brightness of 200,000 stars for 4 years to hunt for these characteristic signals caused by transiting planets.”

The TensorFlow model was trained to “detect the pattern of a transiting exoplanet”, and when the model was shown to work on a new sample of data, “the researchers directed their model to search for weaker signals in 670 star systems that already had multiple known planets".
Story here :-
https://www.itnews.com.au/news/nasa-...planets-479890
Reply With Quote
  #2  
Old 15-12-2017, 10:27 AM
gary
Registered User

gary is offline
 
Join Date: Apr 2005
Location: Mt. Kuring-Gai
Posts: 4,832
Quote:
Originally Posted by tensorflow.org
About TensorFlow

TensorFlow™ is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API. TensorFlow was originally developed by researchers and engineers working on the Google Brain Team within Google's Machine Intelligence research organization for the purposes of conducting machine learning and deep neural networks research, but the system is general enough to be applicable in a wide variety of other domains as well.
If you are interested in machine learning you can download TensorFlow here :-https://www.tensorflow.org/install/

Available for :-
• MacOS X 10.11 (El Capitan) or later.
• Ubuntu 14.04 or later
• Windows 7 or later.


Build your own deep learning machine running TensorFlow on a graphics cards GPU's.
How-to guide here at computer book publisher O'Reilly :-
https://www.oreilly.com/learning/bui...for-under-1000

Last edited by gary; 15-12-2017 at 10:38 AM.
Reply With Quote
  #3  
Old 15-12-2017, 05:05 PM
gary
Registered User

gary is offline
 
Join Date: Apr 2005
Location: Mt. Kuring-Gai
Posts: 4,832
"Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90" by Christopher J. Shallue & Andrew Vanderburg submitted to arXiv on 13 Dec 2017.

Quote:
Originally Posted by Abstract, Sallue, Vandenburg
NASA's Kepler Space Telescope was designed to determine the frequency of Earth-sized planets orbiting Sun-like stars, but these planets are on the very edge of the mission's detection sensitivity.

Accurately determining the occurrence rate of these planets will require automatically and accurately assessing the likelihood that individual candidates are indeed planets, even at low signal-to-noise ratios.

We present a method for classifying potential planet signals using deep learning, a class of machine learning algorithms that have recently become state-of-the-art in a wide variety of tasks.

We train a deep convolutional neural network to predict whether a given signal is a transiting exoplanet or a false positive caused by astrophysical or instrumental phenomena.

Our model is highly effective at ranking individual candidates by the likelihood that they are indeed planets: 98.8% of the time it ranks plausible planet signals higher than false positive signals in our test set.

We apply our model to a new set of candidate signals that we identified in a search of known Kepler multi-planet systems. We statistically validate two new planets that are identified with high confidence by our model.

One of these planets is part of a five-planet resonant chain around Kepler-80, with an orbital period closely matching the prediction by three-body Laplace relations. The other planet orbits Kepler-90, a star which was previously known to host seven transiting planets.

Our discovery of an eighth planet brings Kepler-90 into a tie with our Sun as the star known to host the most planets.
Paper here :-
https://arxiv.org/pdf/1712.05044.pdf
Reply With Quote
Reply

Bookmarks

Thread Tools
Rate This Thread
Rate This Thread:

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT +10. The time is now 01:41 AM.

Powered by vBulletin Version 3.8.7 | Copyright ©2000 - 2018, Jelsoft Enterprises Ltd.
Advertisement
NexDome Observatories
Advertisement
OzScopes Authorised Dealer
Advertisement
Lunatico Astronomical
Advertisement
Bintel
Advertisement
SkyWatcher WiFi Adaptor
Advertisement
SkyWatcher 2018 Catalogue
Advertisement
FLI Cameras and Imaging Accessories
Advertisement
Atik Horizon
Advertisement
Interest Free Finance
Advertisement
Astronomy and Electronics Centre
Advertisement