Detecting and Denoising Gravitational Waves from Binary Black Holes using Convolutional Neural Networks

We present a convolutional neural network, designed in the auto-encoder configuration that can detect and denoise astrophysical gravitational waves from merging black hole binaries, orders of magnitude faster than the traditional matched-filter based detection that is currently employed at Advanced LIGO (aLIGO). The Neural-Net architecture is such that it learns from the sparse representation of the data in the time-frequency domain and constructs a non-linear mapping function that maps this representation into two separate masks for signal and noise, facilitating the separation of the two, from raw data. This method is the first of its kind to apply machine learning method to gravitational wave detection/denoising in the 2D representation of the gravitational wave data. We applied our formalism to the first gravitational wave detected, GW150914, successfully recovering the signal at all three phases of the coalescence at both aLIGO detectors. This method is further tested on the gravitational wave data from the second observing run (O2) of aLIGO, reproducing all black hole mergers detected in O2 at both aLIGO detectors. This method, like many other deep learning methods, can interpolate and extrapolate between modeled templates and explore gravitational waves that are unmodeled and hence not present in the template bank of signals used in the matched filtering detection pipelines. Faster and efficient detection schemes such as this method will be instrumental as ground based detectors reach their design sensitivity, likely to result in hundreds of potential detections in a few months of observing run.