Tracking Local Sea Ice Extent in the Beaufort Sea Using Distributed Acoustic Sensing and Machine Learning

Abstract Monitoring sea ice extent is critical to understand long-term trends in climate change. Here, we show that ambient noise recorded by fiber-optic sensing technology deployed an Arctic shallow marine seafloor environment can track extent. We use a 37.4 km long section of cable offshore Oliktok Point, Alaska. Data are analyzed for two weeks: one July 2021 and another November 2021, when there incomplete evolving coverage. apply different Machine Learning algorithms identify types seismic frequency–time scalogram images. find evidence dominant related excitation oceanic gravity waves open water the presence with sufficient strength suppress wave action. Comparison Distributed Acoustic Sensing (DAS) clustering results satellite-based observations indicates DAS complement constraints from satellite imagery locally increasing spatial temporal resolution tracking which coverage diminish ocean waves.