Ting Chen
2020-07-13 15:27:50
Dear Colleagues,
We would like to draw your attention to the following technical session in AGU 2020 (online, Dec 07-11). Please consider submitting an abstract (deadline July 29). We look forward to your participation!
S010 - Extracting Information from Geophysical Signals with Machine Learning (https://agu.confex.com/agu/fm20/prelim.cgi/Session/101239)
Recent advances in machine learning show great promise in geophysical applications, which include earthquake detection, phase picking, source characterization, ground motion prediction, signal denoising, and subsurface imaging. Future breakthroughs in geophysics should be enabled as more researchers take advantage of the full spectrum of capabilities that machine learning and other data science techniques have to offer. Owing to the inherent complexity of machine learning methods, they are prone to misapplication, may produce uninterpretable models, and can easily be insufficiently documented. This combination of attributes hinders reliable assessment of model validity and consistent interpretation of model outputs. This session aims to engage geophysical communities to share their experience with machine learning, to address the needs (e.g., well documented datasets), and to accelerate progress in the application of data science to geophysics. We welcome contributions that are related to applying machine learning techniques to across the full range of geophysical problems.
Regards,
Ting Chen
Laura Pyrak-Nolte
Paul Johnson
Gregory Beroza
We would like to draw your attention to the following technical session in AGU 2020 (online, Dec 07-11). Please consider submitting an abstract (deadline July 29). We look forward to your participation!
S010 - Extracting Information from Geophysical Signals with Machine Learning (https://agu.confex.com/agu/fm20/prelim.cgi/Session/101239)
Recent advances in machine learning show great promise in geophysical applications, which include earthquake detection, phase picking, source characterization, ground motion prediction, signal denoising, and subsurface imaging. Future breakthroughs in geophysics should be enabled as more researchers take advantage of the full spectrum of capabilities that machine learning and other data science techniques have to offer. Owing to the inherent complexity of machine learning methods, they are prone to misapplication, may produce uninterpretable models, and can easily be insufficiently documented. This combination of attributes hinders reliable assessment of model validity and consistent interpretation of model outputs. This session aims to engage geophysical communities to share their experience with machine learning, to address the needs (e.g., well documented datasets), and to accelerate progress in the application of data science to geophysics. We welcome contributions that are related to applying machine learning techniques to across the full range of geophysical problems.
Regards,
Ting Chen
Laura Pyrak-Nolte
Paul Johnson
Gregory Beroza