The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Machine Learning for Earthquake Seismology with Karianne Bergen - #554
Jan 20, 2022
In this engaging discussion, Karianne Bergen, an assistant professor at Brown University specializing in earthquake seismology and machine learning, delves into her innovative research. She shares insights on using machine learning to detect weak seismic signals and the challenges of distinguishing real earthquakes from noise. Karianne also emphasizes the need for tailored machine learning solutions in seismology and highlights the shifting landscape of scientists' understanding of machine learning, advocating for stronger educational frameworks in the field.
AI Snips
Chapters
Transcript
Episode notes
Karianne's Path to Data Science
- Karianne Bergen returned to Brown University, where she previously studied applied math and physics.
- She worked at MIT Lincoln Laboratory doing applied machine learning on sensor data, later realizing this was data science.
Discovering Seismology
- While at Stanford, Karianne became interested in applying data science to solve real-world problems for scientists.
- A chance encounter led her to collaborate with a seismologist, sparking her interest in geophysics.
Waveform Similarity
- Earthquake waveforms from similar locations and recorded by the same instrument look nearly identical.
- This allows for template matching, but labeled data is often scarce in earth science, necessitating unsupervised approaches.