Japan Geoscience Union Meeting 2022

Presentation information

[J] Oral

S (Solid Earth Sciences ) » S-TT Technology & Techniques

[S-TT40] Seismic Big Data Analysis Based on the State-of-the-Art of Bayesian Statistics

Sun. May 22, 2022 1:45 PM - 3:15 PM 301A (International Conference Hall, Makuhari Messe)

convener:Hiromichi Nagao(Earthquake Research Institute, The University of Tokyo), convener:Aitaro Kato(Earthquake Research Institute, the University of Tokyo), Keisuke Yano(The Institute of Statistical Mathematics), convener:Takahiro Shiina(National Institute of Advanced Industrial Science and Technology), Chairperson:Hiromichi Nagao(Earthquake Research Institute, The University of Tokyo), Aitaro Kato(Earthquake Research Institute, the University of Tokyo), Keisuke Yano(The Institute of Statistical Mathematics)

1:45 PM - 2:15 PM

[STT40-01] Simulation-based machine learning and its application to seismic data analysis

★Invited Papers

*Naonori Ueda1 (1.RIKEN Center for Advanced Intelligence Project)

Keywords:simulation based machine learning, deep learning, seismic data analysis

In recent years, based on AI technology that links big data and deep learning, the performance that surpasses conventional technology has been achieved, especially in the field of pattern recognition such as image recognition, speech recognition, and language translation. On the other hand, the limitations of the data-driven approach such as the small data and black-box problems in deep learning have been pointed out. In the field of science, simulation by first-principles calculation (model-driven approach) is the mainstream, but there is a problem that accurate modeling is difficult for complicated phenomena. In this talk, I will introduce an overview of "simulation-based machine learning" that complementarily integrates the shortcomings of both the model-driven approach and the data-driven approach, and introduces application examples for seismic data analysis.