The EarthScope-operated data systems of the NSF GAGE and SAGE Facilities are migrating to cloud services. To learn more about this effort and find resources, visit earthscope.org/data/cloud

The Cascadia Subduction Zone’s slow slip events, in which a portion of the plate boundary moves gradually without a perceptible earthquake, are of great interest to researchers working to understand the seismic hazard there. But because they are so subtle, they can be difficult to detect and measure—especially the smaller ones.

For example, GNSS instruments may miss some of these events that are similar in scale to the noise in position data caused by things like varying atmospheric and ionospheric conditions. But with reduced noise in the data, these slow slip events might appear clearly.

That’s the idea behind a recent paper in Seismica that uses a machine learning method to denoise GNSS data by identifying error shared by multiple stations. We connected with Loïc Bachelot to talk about how that method works, and how the team went about the data processing it required. If you’re interested in new machine learning methods, check out our conversation in the video below!