Solid Earth Sciences (S)
Session Sub-category Technology & Techniques(TT)
Session ID S-TT51
Title State-of-the-Art Seismic Data Analysis Based on Bayesian Statistics
Short Title Bayesian Analysis of Seismic Data
Main Convener Name Hiromichi Nagao
Affiliation Earthquake Research Institute, The University of Tokyo
Co-Convener 1 Name Aitaro Kato
Affiliation Earthquake Research Institute, the University of Tokyo
Co-Convener 2 Name Keisuke Yano
Affiliation The Institute of Statistical Mathematics
Co-Convener 3 Name Daisuke Sato
Affiliation Japan Agency for Marine-Earth Science and Technology
Session Language 
E
Scope 
Bayesian statistics forms the mathematical foundation of various data anaysis methods, such as machine learning including artificial intelligence. This session mainly accepts presentations that focus on seismic data analysis, especially related to analysis methods based on Bayesian statistics such as machine learning, deep learning and data assimilation, and their applications to real seismic data. Presentations related to mathematical or statistical theories beneficial to data analyses, feasibility studies of algorithms eventually applicable to real seismic data, and the current status of seismic observations and analysis results are also highly welcome.
Presentation Format Oral and Poster presentation
Time Presentation No Title Presenter
Oral Presentation May 28 AM2
10:45 - 11:00 STT51-01 Deep Generative Modeling of Ground Motions toward Integrated Seismic Hazard and Risk Analysis Itoi Tatsuya
11:00 - 11:15 STT51-02 Application of a fine-tuned BERT model for seafloor DAS data processing Gerardo Manuel Mendo Perez
11:15 - 11:30 STT51-03 Benchmarking Deep Learning Architectures for Rapid Disaster Response: A Case Study of the 2024 Noto Peninsula Earthquake Using Multi-Source Remote Sensing and Open Damage Inventories Minhaz Chowdhury
11:30 - 11:45 STT51-04 Oscillator decomposition of earthquake data Takeru Matsuda
11:45 - 12:00 STT51-05 Statistical Seismicity Models Incorporating the Effects of Slow Earthquakes Tomoaki Nishikawa
12:00 - 12:15 STT51-06 Gaussian Process Modeling of Spatio-temporal Background Seismicity Yuanyuan Niu
Presentation No Title Presenter
Poster Presentation May 28 PM3
STT51-P01 Investigating the Generalization Capabilities of Mamba-based Graybox Neural Operators for Multiscale Seismic Wave Modeling Toshiro Kusui
STT51-P02 Function-space based PDE-constrained Bayesian inversion methods using physics-informed neural networks Ryoichiro Agata
STT51-P03 Generation of Volcanic Tremor Waveforms Using Diffusion Model Shinya Katoh
STT51-P04 Optimizing Earthquake Early Warning Site Selection via Bayesian Sensitivity Analysis Keisuke Yano
STT51-P05 Teleseismic fractography: discontinuous smooth surface reconstruction of earthquake faults from the 2025 Myanmar earthquake Daisuke Sato
STT51-P06 Seismic Detection Based on Unsupervised Station-wise Phase Picks Using Deep Learning and Its Application Hiromichi Nagao