Deep Residual Networks for Gravitational Wave Detection

Paraskevi Nousi, Alexandra E. Koloniari, Nikolaos Passalis, Panagiotis Iosif, Nikolaos Stergioulas, Anastasios Tefas

Submitted on 2 November 2022


Traditionally, gravitational waves are detected with techniques such as matched filtering or unmodeled searches based on wavelets. However, in the case of generic black hole binaries with non-aligned spins, if one wants to explore the whole parameter space, matched filtering can become impractical, which sets severe restrictions on the sensitivity and computational efficiency of gravitational-wave searches. Here, we use a novel combination of machine-learning algorithms and arrive at sensitive distances that surpass traditional techniques in a specific setting. Moreover, the computational cost is only a small fraction of the computational cost of matched filtering. The main ingredients are a 54-layer deep residual network (ResNet), a Deep Adaptive Input Normalization (DAIN), a dynamic dataset augmentation, and curriculum learning, based on an empirical relation for the signal-to-noise ratio. We compare the algorithm's sensitivity with two traditional algorithms on a dataset consisting of a large number of injected waveforms of non-aligned binary black hole mergers in real LIGO O3a noise samples. Our machine-learning algorithm can be used in upcoming rapid online searches of gravitational-wave events in a sizeable portion of the astrophysically interesting parameter space. We make our code, AResGW, and detailed results publicly available at


Comment: 10 pages, 11 figures, code publicly available at

Subjects: General Relativity and Quantum Cosmology; Astrophysics - High Energy Astrophysical Phenomena


A representative 2-channel data segment of the training set containing an injection in real O3a noise from the Hanford (H1) detector (left panel) and the Livingston (L1) detector (right panel). The {\it whitened strain} of a 1 s segment around the time of coalescence is shown. The coalescence times in the detector frames are within the 0.5 s - 0.7 s range (shown as a shaded area). The injected waveform is shown scaled to match the difference between the whitened foreground and background segments. In this example, the component masses are $m_1=27.74M_\odot$, $m_2=11.50M_\odot$ and the luminosity distance is $d=1497 Mpc$. The {\it non-aligned spins} have magnitudes of 0.624 and 0.008, respectively.