jiunting
2021-01-05 15:01:24
Dear Colleagues,
We would like to invite you to submit an abstract to our Machine Learning, HPC, Data Science in Seismology SSA 2021 session. The objective of this session is to bring together applications that facilitate with many nowadays technologies (ML, HPC, Big Data etc.) to their own seismological problems. We welcome contributors to discuss successes, challenges, and lessons learned on the application of these developing technologies. If you are interested, please submit through the 2021 SSA Annual Meeting link before Jan 13. 5pm(PT) (https://www.seismosoc.org/meetings/submission-system/).
Title: When Seismology Meets Machine Learning, Data Science, HPC, Cloud Computing and Beyond
Seismology is a data rich and data-driven science. As seismologists, we are lucky to be in an age where new tools and techniques are emerging to facilitate extracting insights from huge amounts of data. Over the past few years, there has been a new surge of interests in the applications of machine learning and data science techniques to seismological problems, as well as exploring the use of HPC and cloud computing to address computation-intensive tasks, and this new sub-field is rapidly evolving. Recent examples of seismological tasks in which machine learning applications have been shown to be promising include earthquake signal detection, seismic phase picking, phase association, first polarity determination, magnitude estimation, source location determination, event discrimination, seismic image pre-processing and interpretation, signal denoising, subsurface characterization, ground motion prediction and simulation, lab earthquake and aftershock prediction and exploratory data analyses. Though the progress on these tasks is not even, there is huge potential and more room for improvement in the near future. In this session, we invite contributions discussing the application of machine learning, data science, high performance computing, cloud computing and other recent data driven related efforts in all seismological problems. We welcome contributors to discuss successes, challenges and lessons learned in the application of these developing technologies.
Conveners:
Qingkai Kong, Berkeley Seismology Lab, University of California, Berkeley (kongqk<at>berkeley.edu)
S. Mostafa Mousavi, Stanford University (mmousavi<at>stanford.edu)
Jiun-Ting Lin, University of Oregon (jiunting<at>uoregon.edu)
We would like to invite you to submit an abstract to our Machine Learning, HPC, Data Science in Seismology SSA 2021 session. The objective of this session is to bring together applications that facilitate with many nowadays technologies (ML, HPC, Big Data etc.) to their own seismological problems. We welcome contributors to discuss successes, challenges, and lessons learned on the application of these developing technologies. If you are interested, please submit through the 2021 SSA Annual Meeting link before Jan 13. 5pm(PT) (https://www.seismosoc.org/meetings/submission-system/).
Title: When Seismology Meets Machine Learning, Data Science, HPC, Cloud Computing and Beyond
Seismology is a data rich and data-driven science. As seismologists, we are lucky to be in an age where new tools and techniques are emerging to facilitate extracting insights from huge amounts of data. Over the past few years, there has been a new surge of interests in the applications of machine learning and data science techniques to seismological problems, as well as exploring the use of HPC and cloud computing to address computation-intensive tasks, and this new sub-field is rapidly evolving. Recent examples of seismological tasks in which machine learning applications have been shown to be promising include earthquake signal detection, seismic phase picking, phase association, first polarity determination, magnitude estimation, source location determination, event discrimination, seismic image pre-processing and interpretation, signal denoising, subsurface characterization, ground motion prediction and simulation, lab earthquake and aftershock prediction and exploratory data analyses. Though the progress on these tasks is not even, there is huge potential and more room for improvement in the near future. In this session, we invite contributions discussing the application of machine learning, data science, high performance computing, cloud computing and other recent data driven related efforts in all seismological problems. We welcome contributors to discuss successes, challenges and lessons learned in the application of these developing technologies.
Conveners:
Qingkai Kong, Berkeley Seismology Lab, University of California, Berkeley (kongqk<at>berkeley.edu)
S. Mostafa Mousavi, Stanford University (mmousavi<at>stanford.edu)
Jiun-Ting Lin, University of Oregon (jiunting<at>uoregon.edu)
