Detecting Slow Slip Events From Seafloor Pressure Data Using Machine Learning

Detecting slow slip events (SSEs) at offshore subduction zones is important to understand the slip behavior on offshore subduction megathrusts, where tsunamis can be generated. The most widely used method to detect SSEs is to measure the vertical seafloor deformation caused by SSEs using seafloor pressure data. However, due to the small signal‐to‐noise ratio and instrumental drift, such detection is very difficult. In this study, we trained a machine learning model using synthetic data to detect SSEs and applied it to real pressure data in New Zealand between 2014 and 2015. Our method detected five events, two of which are confirmed by the onshore GPS records. Besides, our model performs better than the traditional matched filter method. We conclude that machine learning could be used to detect SSEs in real seafloor pressure data. The method can be applied to other regions, especially where near trench GPS is not available. Plain Language Summary We applied machine learning to detect a special tectonic signal recorded by pressure sensors sitting on the seafloor. This signal represents the release of tectonic stress between earthquakes, and thus, their existence indicates a lower likelihood of future large earthquakes and tsunamis. It is difficult to detect this signal because of the high noise. Here we show that machine learning successfully detected two such signals and three possible cases in data collected near New Zealand between 2014 and 2015. The method has the potential to transform our way of detecting such signals in seafloor pressure data offshore New Zealand and elsewhere, especially where the signal source is far away from the shoreline. Key Points Using a machine learning method, we detected five events in seafloor pressure data offshore New Zealand, two of which are likely SSEs Performance of the machine learning method is better than the traditional matched filter method This method can be especially useful where the trench is far from GPS onshore