Thread: AGU session announcements

Started: 2018-07-17 01:44:17
Last activity: 2018-07-17 01:44:17
Topics: AGU Meetings
Greg Beroza
2018-07-17 01:44:17

Dear colleagues,

We would like to draw your attention to the following session co-organized by the Seismology, Tectonophysics, Nonlinear Geophysics, and Mineral and Rock Physics sections at the upcoming 2018 AGU fall meeting:

S009: Extracting Information from Geophysical & Geochemical Signals: Applying Machine Learning Through Data Science Challenges

Session Description:

Major breakthroughs in geophysics are anticipated as more researchers turn to machine learning and other data science techniques; however, owing to the inherent complexity of machine learning methods, they are prone to misapplication, may produce uninterpretable models, and are often insufficiently documented. This combination of attributes hinders both reliable assessment of model validity and consistent interpretation of model outputs. By providing documented datasets and challenging teams to apply fully documented workflows for machine learning approaches, we expect to accelerate progress in the application of data science to longstanding research issues in geophysics. This session has two goals: (1) to announce machine learning challenges to the community that address earthquake detection and the physics of rupture and the timing of earthquakes; and (2) to solicit papers on the use of different machine learning techniques related to the identification of the physics contained in geophysical and chemical signals, as well as from images of geologic materials (minerals, fracture patterns, etc.)

Conveners:

Paul A. Johnson (paj<at>lanl.gov<paj<at>lanl.gov>) Los Alamos National Laboratory

Gregory C. Beroza (beroza<at>stanford.edu<beroza<at>stanford.edu>) Stanford University

Jim Rustad (James.Rustad<at>science.doe.gov<James.Rustad<at>science.doe.gov>) Department of Energy

Laura J. Pyrak-Nolte (ljpn<at>purdue.edu<ljpn<at>purdue.edu>) Purdue University

Page built 05:10:18 | v.ee5e54cb