EQTransformer is a multi-task very deep neural network with an attention mechanism that is designed for earthquake signal detection and phase (P&S) picking. It has a hierarchical architecture specifically designed for earthquake signals and has been trained on local earthquake waveforms collected in diverse settings and from seismic networks around the world. In addition to the prediction probabilities, provides estimated model uncertainties.
Download the EQTransformer software
There github page includes the EQTransformer python 3 package, which features modules for downloading continuous seismic data, preprocessing, performing earthquake signal detection, and phase (P & S) picking using pre-trained models, building and testing new models, and performing simple phase association.