We present a novel Machine Learning (ML) based strategy to search for compact binary coalescences (CBCs) in data from ground-based gravitational wave (GW) observatories. This is the first ML-based search that not only recovers all the binary black ho
le mergers in the first GW transients calalog (GWTC-1), but also makes a clean detection of GW151216, which was not significant enough to be included in the catalogue. Moreover, we achieve this by only adding a new coincident ranking statistic (MLStat) to a standard analysis that was used for GWTC-1. In CBC searches, reducing contamination by terrestrial and instrumental transients, which create a loud noise background by triggering numerous false alarms, is crucial to improving the sensitivity for detecting true events. The sheer volume of data and and large number of expected detections also prompts the use of ML techniques. We perform transfer learning to train InceptionV3, a pre-trained deep neural network, along with curriculum learning to distinguish GW signals from noisy events by analysing their continuous wavelet transform (CWT) maps. MLStat incorporates information from this ML classifier into the standard coincident search likelihood used by the conventional search. This leads to at least an order of magnitude improvement in the inverse false-alarm-rate (IFAR) for the previously low significance events GW151012, GW170729 and GW151216. The confidence in detection of GW151216 is further strengthened by performing its parameter estimation using SEOBNRv4HM_ROM. Considering the impressive ability of the statistic to distinguish signals from glitches, the list of marginal events from MLStat could be quite reliable for astrophysical population studies and further follow-up. This work demonstrates the immense potential and readiness of MLStat for finding new sources in current data and possibility of its adaptation in similar searches.
Longitudinal control signals used to keep gravitational wave detectors at a stable operating point are often affected by modulations from test mass misalignments leading to an elevated noise floor ranging from 50 to 500 Hz. Nonstationary noise of thi
s kind results in modulation sidebands and increases the number of glitches observed in the calibrated strain data. These artifacts ultimately affect the data quality and decrease the efficiency of the data analysis pipelines looking for astrophysical signals from continuous waves as well as the transient events. In this work, we develop a scheme to subtract one such bilinear noise from the gravitational wave strain data and demonstrate it at the GEO 600 observatory. We estimate the coupling by making use of narrow-band signal injections that are already in place for noise projection purposes and construct a coherent bilinear signal by a two-stage system identification process. We improve upon the existing filter design techniques by employing a Bayesian adaptive directed search strategy that optimizes across the several key parameters that affect the accuracy of the estimated model. The scheme takes into account the possible nonstationarities in the coupling by periodically updating the involved filter coefficients. The resulting postoffline subtraction leads to a suppression of modulation sidebands around the calibration lines along with a broadband reduction of the midfrequency noise floor. The observed increase in the astrophysical range and a reduction in the occurrence of nonastrophysical transients suggest that the above method is a viable data cleaning technique for current and future generation gravitational wave observatories.
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 ex
cess 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 instruments 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.
Gravitational wave observatories have always been affected by tele-seismic earthquakes leading to a decrease in duty cycle and coincident observation time. In this analysis, we leverage the power of machine learning algorithms and archival seismic da
ta to predict the ground motion and the state of the gravitational wave interferometer during the event of an earthquake. We demonstrate improvement from a factor of 5 to a factor of 2.5 in scatter of the error in the predicted ground velocity over a previous model fitting based approach. The level of accuracy achieved with this scheme makes it possible to switch control configuration during periods of excessive ground motion thus preventing the interferometer from losing lock. To further assess the accuracy and utility of our approach, we use IRIS seismic network data and obtain similar levels of agreement between the estimates and the measured amplitudes. The performance indicates that such an archival or prediction scheme can be extended beyond the realm of gravitational wave detector sites for hazard-based early warning alerts.
Advanced LIGO and the next generation of ground-based detectors aim to capture many more binary coalescences through improving sensitivity and duty cycle. Earthquakes have always been a limiting factor at low frequency where neither the pendulum susp
ension nor the active controls provide sufficient isolation to the test mass mirrors. Several control strategies have been proposed to reduce the impact of teleseismic events by switching to a robust configuration with less aggressive feedback. The continental United States has witnessed a huge increase in the number of induced earthquake events primarily associated with hydraulic fracking-related waste water re-injection. Effects from these differ from teleseismic earthquakes primarily because of their depth which is in turn linked to their triggering mechanism. In this paper, we discuss the impact caused due to these low magnitude regional earthquakes and explore ways to minimize the impact of induced seismicity on the detector.
We present a machine learning based information retrieval system for astronomical observatories that tries to address user defined queries related to an instrument. In the modern instrumentation scenario where heterogeneous systems and talents are si
multaneously at work, the ability to supply with the right information helps speeding up the detector maintenance operations. Enhancing the detector uptime leads to increased coincidence observation and improves the likelihood for the detection of astrophysical signals. Besides, such efforts will efficiently disseminate technical knowledge to a wider audience and will help the ongoing efforts to build upcoming detectors like the LIGO-India etc even at the design phase to foresee possible challenges. The proposed method analyses existing documented efforts at the site to intelligently group together related information to a query and to present it on-line to the user. The user in response can further go into interesting links and find already developed solutions or probable ways to address the present situation optimally. A web application that incorporates the above idea has been implemented and tested for LIGO Livingston, LIGO Hanford and Virgo observatories.
Detection and classification of transients in data from gravitational wave detectors are crucial for efficient searches for true astrophysical events and identification of noise sources. We present a hybrid method for classification of short duration
transients seen in gravitational wave data using both supervised and unsupervised machine learning techniques. To train the classifiers we use the relative wavelet energy and the corresponding entropy obtained by applying one-dimensional wavelet decomposition on the data. The prediction accuracy of the trained classifier on 9 simulated classes of gravitational wave transients and also LIGOs sixth science run hardware injections are reported. Targeted searches for a couple of known classes of non-astrophysical signals in the first observational run of Advanced LIGO data are also presented. The ability to accurately identify transient classes using minimal training samples makes the proposed method a useful tool for LIGO detector characterization as well as searches for short duration gravitational wave signals.
