Please join us for a UW Data Science Seminar event on Wednesday, May 3rd from 4:30 to 5:20 p.m. PST. The seminar will feature Marine Denolle, UW Earth & Space Sciences Assistant Professor.
“Data Mining the Earth’s Vibrations”
Abstract: The Earth’s near and subsurface vibrate constantly in the form of seismic waves. The sources of these vibrations may come from various geoscientific origins, from tectonic, volcanic, atmospheric, and oceanic, but also from wildlife and anthropogenic activities. Geophysical sensors for these vibrations were mainly developed to record earthquake signals, but they are increasingly demonstrated as powerful to detect these diverse sources of vibrations. Therefore, geophysicists have increasingly deployed sensors and developed new technology to increase these measurements’ spatial and temporal resolution. Extracting the seismic signature of these phenomena enables both discovery-based science and hypothesis-driven research. The volumes of seismic data of the past 40 years reach ~ 1PB, but tomorrow’s data volume will be at 1PB per year. The UW Quake group deciphers physical processes of the Earth by data mining continuous recordings of seismic data that contain diffuse ambient seismic waves and directed and distinct waves from seismic events. I will demonstrate how we extract the information from engineered or deep-learning-driven feature extraction and correlation-based methods and what phenomena we can explore, from monitoring the subsurface groundwater level change to discriminating earthquakes from landslides.
The UW Data Science Seminar is an annual lecture series at the University of Washington that hosts scholars working across applied areas of data science, such as the sciences, engineering, humanities and arts along with methodological areas in data science, such as computer science, applied math and statistics. Our presenters come from all domain fields and include occasional external speakers from regional partners, governmental agencies and industry.
The 2022-2023 seminars will be virtual, and are free and open to the public.