Earthquake Early Warning with 3 seconds of records on a single station

We introduce the Ensemble Earthquake Early Warning System (E3WS), a set of Machine Learning algorithms designed to detect, locate and estimate the magnitude of an earthquake using 3 seconds (or more) of P waves recorded by a single station. The system is made of 6 Ensemble Machine Learning algorithms trained on attributes computed from ground acceleration time series in the temporal, spectral and cepstral domains. The training set comprises datasets from Peru, Chile, Japan, and the STEAD global dataset. E3WS consists of three sequential stages: detection, P-phase picking and source characterization. The latter involves magnitude, epicentral distance, depth and back-azimuth estimation. E3WS achieves an overall success rate in the discrimination between earthquakes and noise of 99.9%. For P-phase picking, the Mean Absolute Error (MAE) is 0.14s. For source characterization, the MAEs for magnitude, distance, depth and back-azimuth are 0.34 magnitude units, 27 km, 15.7 km and 45.2°, respectively. By updating estimates every second, the approach gives time-dependent magnitude estimates that follow the earthquake source time function. E3WS gives faster estimates than present alert systems, providing additional valuable seconds for potential protective actions.