Neural phase pickers—neural networks designed and trained to pick seismic phase arrivals—have proven to be a powerful tool for developing earthquake catalogs. However, these pickers suffer from prediction inconsistency in which the results they produce change, sometimes substantially, even under a small perturbation to the input waveform. This problem has not been addressed by the developers and users of these pickers. In this study, we show how prediction inconsistency can negatively affect the completeness of earthquake catalogs developed using neural phase pickers. We show that simply using a small step size for the sliding window when processing continuous waveform data and aggregating the results significantly mitigates this problem. We also highlight the importance of training datasets for increasing the consistency and other performance metrics.

You do not have access to this content, please speak to your institutional administrator if you feel you should have access.