Deep learning for gravitational wave forecasting of neutron star mergers

We introduce deep learning time-series forecasting for gravitational wave detection of binary neutron star mergers. This method enables the identification these signals in real advanced LIGO data up to 30 seconds before merger. When applied GW170817, our identifies presence this signal 10 novel approach requires a single GPU inference, and may be used as part an early warning system time-sensitive multi-messenger searches.