A machine learning approach for GRB detection in AstroSat CZTI data. (arXiv:1906.09670v3 [astro-ph.IM] UPDATED)
<a href="http://arxiv.org/find/astro-ph/1/au:+Abraham_S/0/1/0/all/0/1">Sheelu Abraham</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Mukund_N/0/1/0/all/0/1">Nikhil Mukund</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Vibhute_A/0/1/0/all/0/1">Ajay Vibhute</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Sharma_V/0/1/0/all/0/1">Vidushi Sharma</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Iyyani_S/0/1/0/all/0/1">Shabnam Iyyani</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Bhattacharya_D/0/1/0/all/0/1">Dipankar Bhattacharya</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Rao_A/0/1/0/all/0/1">A. R. Rao</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Vadawale_S/0/1/0/all/0/1">Santosh Vadawale</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Bhalerao_V/0/1/0/all/0/1">Varun Bhalerao</a>
We present a machine learning (ML) based method for automated detection of
Gamma-Ray Burst (GRB) candidate events in the range 60 keV – 250 keV from the
AstroSat Cadmium Zinc Telluride Imager data. We use density-based spatial
clustering to detect excess power and carry out an unsupervised hierarchical
clustering across all such events to identify the different light curves
present in the data. This representation helps understand the instrument’s
sensitivity to the various GRB populations and identify the major
non-astrophysical noise artefacts present in the data. We use Dynamic Time
Warping (DTW) to carry out template matching, which ensures the morphological
similarity of the detected events with known typical GRB light curves. DTW
alleviates the need for a dense template repository often required in matched
filtering like searches. The use of a similarity metric facilitates outlier
detection suitable for capturing previously unmodelled events. We briefly
discuss the characteristics of 35 long GRB candidates detected using the
pipeline and show that with minor modifications such as adaptive binning, the
method is also sensitive to short GRB events. Augmenting the existing data
analysis pipeline with such ML capabilities alleviates the need for extensive
manual inspection, enabling quicker response to alerts received from other
observatories such as the gravitational-wave detectors.
We present a machine learning (ML) based method for automated detection of
Gamma-Ray Burst (GRB) candidate events in the range 60 keV – 250 keV from the
AstroSat Cadmium Zinc Telluride Imager data. We use density-based spatial
clustering to detect excess power and carry out an unsupervised hierarchical
clustering across all such events to identify the different light curves
present in the data. This representation helps understand the instrument’s
sensitivity to the various GRB populations and identify the major
non-astrophysical noise artefacts present in the data. We use Dynamic Time
Warping (DTW) to carry out template matching, which ensures the morphological
similarity of the detected events with known typical GRB light curves. DTW
alleviates the need for a dense template repository often required in matched
filtering like searches. The use of a similarity metric facilitates outlier
detection suitable for capturing previously unmodelled events. We briefly
discuss the characteristics of 35 long GRB candidates detected using the
pipeline and show that with minor modifications such as adaptive binning, the
method is also sensitive to short GRB events. Augmenting the existing data
analysis pipeline with such ML capabilities alleviates the need for extensive
manual inspection, enabling quicker response to alerts received from other
observatories such as the gravitational-wave detectors.
http://arxiv.org/icons/sfx.gif
