Karianne Bergen

• 
  Event detection in big sensor data: Applications in earthquake seismology and beyond
  Karianne Bergen
  Many observational studies in the Earth sciences rely on passive sensors to detect and monitor the events or processes of interest. For example, earthquake detection -- the extraction of weak earthquake signals from continuous waveform data recorded by sensors in a seismic network – is a fundamental and challenging task in earthquake seismology. These long-duration, continuously recorded sensor data require modern, data-driven analysis techniques that are capable of scaling to massive data sets.
  
  In this talk, I will describe the data science challenges associated with event detection in large sensor data sets, focusing on earthquake detection in seismic data. I will discuss how new algorithmic advances in “big data� and machine learning (ML) are helping to advance the state-of-the-art in earthquake monitoring. As a case study, I will present Fingerprint and Similarity Thresholding (FAST), a novel method for large-scale earthquake detection inspired by audio recognition technology (Yoon et al, 2015). I will draw parallels between developments in ML for geophysics and emerging research in bio- and ecoacoustics.