A MACHINE LEARNING TECHNIQUE TO IDENTIFY TRANSIT SHAPED SIGNALS

@article{Thompson2015AML,
  title={A MACHINE LEARNING TECHNIQUE TO IDENTIFY TRANSIT SHAPED SIGNALS},
  author={Susan E. Thompson and Fergal Robert Mullally and J. Coughlin and Jessie L. Christiansen and Christopher E. Henze and Michael R. Haas and Christopher J. Burke},
  journal={The Astrophysical Journal},
  year={2015},
  volume={812}
}
We describe a new metric that uses machine learning to determine if a periodic signal found in a photometric time series appears to be shaped like the signature of a transiting exoplanet. This metric uses dimensionality reduction and k-nearest neighbors to determine whether a given signal is sufficiently similar to known transits in the same data set. This metric is being used by the Kepler Robovetter to determine which signals should be part of the Q1–Q17 DR24 catalog of planetary candidates… 

Figures and Tables from this paper

Transit shapes and self-organizing maps as a tool for ranking planetary candidates: application to Kepler and K2
A crucial step in planet hunting surveys is to select the best candidates for follow up observations, given limited telescope resources. This is often performed by human ‘eyeballing’, a time
Classical Machine Learning Techniques in the Search of Extrasolar Planets
TLDR
A supervised learning approach is presented to refine the results produced by a case-by-case analysis of light-curves, harnessing the generalization power of machine learning techniques to predict the currently unclassified light-Curves.
Autoregressive Planet Search: Methodology
TLDR
The methodology of the Autoregessive Planet Search (ARPS) project is presented, which uses Autoregressive Integrated Moving Average (ARIMA) and related statistical models that treat a wide variety of stochastic processes, as well as nonstationarity, to improve detection of new planetary transits.
Automatic vetting of planet candidates from ground based surveys: Machine learning with NGTS
State of the art exoplanet transit surveys are producing ever increasing quantities of data. To make the best use of this resource, in detecting interesting planetary systems or in determining
Autoregressive Planet Search: Application to the Kepler Mission
The 4 yr light curves of 156,717 stars observed with NASA’s Kepler mission are analyzed using the autoregressive planet search (ARPS) methodology described by Caceres et al. The three stages of
Automation Of Transiting Exoplanet Detection, Identification and Habitability Assessment Using Machine Learning Approaches
TLDR
Experimental results suggest that the proposed stacked GBDT model outperformed the conventional models in detecting transiting exoplanets and the incorporation of ATA scores in habitability classification enhanced the performance of models.
Identifying Exoplanets with Deep Learning: A Five-planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
TLDR
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, is presented and two new planets are identified with high confidence by this model.
Searching for exoplanets using artificial intelligence
TLDR
The study indicates that machine learning will facilitate the characterization of exoplanets in future analysis of large astronomy data sets by allowing data to be evaluated from different time series after interpolation without compromising performance.
Kepler Data Validation I—Architecture, Diagnostic Tests, and Data Products for Vetting Transiting Planet Candidates
TLDR
The Kepler Pipeline has been modified to support the TESS Mission which will commence in 2018, and the DV architecture and diagnostic tests, and a brief overview of the data products are described.
Transiting Exoplanet Discovery Using Machine Learning Techniques: A Survey
TLDR
It is concluded that multiresolution analysis in the time-frequency domain can improve exoplanet signal identification, because of the characteristics of light curves and transiting exoplanets signals.
...
...

References

SHOWING 1-10 OF 30 REFERENCES
AUTOMATIC CLASSIFICATION OF KEPLER PLANETARY TRANSIT CANDIDATES
In the first three years of operation, the Kepler mission found 3697 planet candidates (PCs) from a set of 18,406 transit-like features detected on more than 200,000 distinct stars. Vetting candidate
Auto-Vetting Transiting Planet Candidates Identified by the Kepler Pipeline
TLDR
Preliminary results indicate that random forests can classify potential transiting planet signatures with an accuracy of more than 98.6% as measured by the area under a receiver-operating curve.
DETECTION OF POTENTIAL TRANSIT SIGNALS IN 16 QUARTERS OF KEPLER MISSION DATA
We present the results of a search for potential transit signals in 4 yr of photometry data acquired by the Kepler mission. The targets of the search include 111,800 stars which were observed for the
MEASURING TRANSIT SIGNAL RECOVERY IN THE KEPLER PIPELINE. I. INDIVIDUAL EVENTS
The Kepler mission was designed to measure the frequency of Earth-size planets in the habitable zone of Sun-like stars. A crucial component for recovering the underlying planet population from a
A Bayesian method for the detection of planetary transits
A new algorithm is proposed for the systematic analysis of light curves produced in high accuracy photometric experiments. This method allows us to identify and reconstruct in an automated fashion
PLANETARY CANDIDATES OBSERVED BY KEPLER. III. ANALYSIS OF THE FIRST 16 MONTHS OF DATA
New transiting planet candidates are identified in 16 months (2009 May–2010 September) of data from the Kepler spacecraft. Nearly 5000 periodic transit-like signals are vetted against astrophysical
Some Tests to Establish Confidence in Planets Discovered by Transit Photometry
Increased attention is being paid to transit photometry as a viable method for discovering or confirming detections of extrasolar planets. Several ground-based efforts are underway that target
TRANSIT DETECTION IN THE MEarth SURVEY OF NEARBY M DWARFS: BRIDGING THE CLEAN-FIRST, SEARCH-LATER DIVIDE
In the effort to characterize the masses, radii, and atmospheres of potentially habitable exoplanets, there is an urgent need to find examples of such planets transiting nearby M dwarfs. The MEarth
PLANETARY CANDIDATES OBSERVED BY KEPLER. VI. PLANET SAMPLE FROM Q1–Q16 (47 MONTHS)
We present the sixth catalog of Kepler candidate planets based on nearly four years of high precision photometry. This catalog builds on the legacy of previous catalogs released by the Kepler project
PLANETARY CANDIDATES OBSERVED BY KEPLER IV: PLANET SAMPLE FROM Q1–Q8 (22 MONTHS)
We provide updates to the Kepler planet candidate sample based upon nearly two years of high-precision photometry (i.e., Q1–Q8). From an initial list of nearly 13,400 threshold crossing events, 480
...
...