Real-time gravitational-wave science with neural posterior estimation
This enables real-time data analysis for gravitational-wave astronomy without sacrificing accuracy, addressing a critical bottleneck for astrophysicists.
The researchers tackled the problem of slow gravitational-wave parameter estimation by developing DINGO, a neural network-based method that reduces inference time from days to minutes per event while maintaining accuracy comparable to standard inference codes on eight real gravitational-wave events.
We demonstrate unprecedented accuracy for rapid gravitational-wave parameter estimation with deep learning. Using neural networks as surrogates for Bayesian posterior distributions, we analyze eight gravitational-wave events from the first LIGO-Virgo Gravitational-Wave Transient Catalog and find very close quantitative agreement with standard inference codes, but with inference times reduced from O(day) to a minute per event. Our networks are trained using simulated data, including an estimate of the detector-noise characteristics near the event. This encodes the signal and noise models within millions of neural-network parameters, and enables inference for any observed data consistent with the training distribution, accounting for noise nonstationarity from event to event. Our algorithm -- called "DINGO" -- sets a new standard in fast-and-accurate inference of physical parameters of detected gravitational-wave events, which should enable real-time data analysis without sacrificing accuracy.