Room C

[S22]AM-1

Wed. Sep 18, 2019 9:15 AM - 10:30 AM ROOM C (Research Bldg No 8 NS Hall)

chairperson:Takahiko Uchide(Geological Survey of Japan, AIST), Hisahiko Kubo(NIED)

+Add all to schedule

9:15 AM - 9:45 AM

[S22-01] [INVITED]Data-Driven Anomaly Detection Based on Machine Learning: Smart Maintenance for Wind Energy

*Jun Ogata¹ (1. Data-Driven Anomaly Detection Based on Machine Learning: Smart Maintenance for Wind Energy)

9:45 AM - 10:00 AM

[S22-02] Seismic Phase Picking based on Sparsity-Aware Change Detection

*Hiroki Kuroda¹, Jun Ogata¹, Hidenori Sakanashi¹, Takahiko Uchide² (1. Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, 2. Geological Survey of Japan, National Institute of Advanced Industrial Science and Technology)

10:00 AM - 10:15 AM

[S22-03] Automatic P-wave detection using deep learning and visualization of the decision process

*Shota Hara¹, Yukitoshi Fukahata², Yoshihisa Iio² (1. Graduate School of Science, Kyoto University, 2. Disaster Prevention Research Institute, Kyoto University)

10:15 AM - 10:30 AM

[S22-04] Application of convolutional neural networks to continuous seismic network records

*Keisuke Yano¹, Takahiro Shiina², Sumito Kurata¹, Aitaro Kato², Fumiyasu Komaki¹, Shin'ichi Sakai², Naoshi Hirata² (1. Department of Mathematical Informatics, The University of Tokyo, 2. Earthquake Research Institute, University of Tokyo)

Room C

[S22]AM-2

Wed. Sep 18, 2019 10:45 AM - 12:00 PM ROOM C (Research Bldg No 8 NS Hall)

chairperson:Hisahiko Kubo(NIED), Yuki Kodera(Meteorological Research Agency, JMA)

+Add all to schedule

10:45 AM - 11:00 AM

[S22-05] Development of 3D Convolutional Neural Network to locate hypocenter with theoretical seismograms of time series as training data.

*Daisuke Sugiyama¹, Seiji Tsuboi¹ (1. JAMSTEC)

11:00 AM - 11:15 AM

[S22-06] Discrimination of earthquakes and tectonic tremor signals by applying a convolutional neural network to running spectral images

*Masaru Nakano¹, Daisuke Sugiyama¹, Takane Hori¹, Tatsu Kuwatani¹, Seiji Tsuboi¹ (1. JAMSTEC)

11:15 AM - 11:30 AM

[S22-07] An unsupervised automatic classification algorithm for continuous seismic records using a nonparametric Bayesian approach

*Yuki Kodera¹, Shin'ichi Sakai², Takahito Nishimiya¹ (1. Meteorological Research Institute, Japan Meteorological Agency, 2. Earthquake Research Institute, the University of Tokyo)

11:30 AM - 11:45 AM

[S22-08] Study on Site-specific Ground Motion Evaluation Models Utilizing Machine Learning Method Considering Epicentral Directions

*Toru Ishii¹, Atsuko Oana¹, Kensuke Wada¹ (1. Shimizu Corporation)

11:45 AM - 12:00 PM

[S22-09] Study on Ground Motion Evaluation Models for Kanto Region Utilizing Machine Learning Method

*Atsuko Oana¹, Toru Ishii¹, Kensuke Wada¹ (1. Shimizu Corporation)

Room C

[S22]PM-1

Wed. Sep 18, 2019 2:30 PM - 4:00 PM ROOM C (Research Bldg No 8 NS Hall)

chairperson:Yuki Kodera(Meteorological Research Agency, JMA), Takahiko Uchide(Geological Survey of Japan, AIST)

+Add all to schedule

2:30 PM - 2:45 PM

[S22-10] Improving the symmetry of ambient seismic field correlation functions with machine learning

*Loic Viens¹, Tomotaka Iwata¹ (1. Kyoto University, DPRI)

2:45 PM - 3:00 PM

[S22-11] A hybrid approach of Machine learning and Ensemble Kalman Filter for estimating frictional parameters in Nankai megaquake cycle simulator

*Yu Yamamoto¹, Kazuro Hirahara^1,3, Hirotaka Hachiya^1,2, Atsushi Takahashi¹, Naonori Ueda¹ (1. Center for Advanced Intelligence Project, RIKEN, 2. Univ. of Wakayama, 3. Univ. of Kagawa)

3:00 PM - 3:15 PM

[S22-12] Acceleration of matched-filter search and slip inversion of deep tectonic tremor using nearest neighbor search

*Naoto Mizuno¹, Satoshi Ide¹ (1. School of Science, The University of Tokyo)

3:15 PM - 3:30 PM

[S22-13] Machine learning of postseismic deformation of the 2011 Tohoku-Oki earthquake based on recurrent neural network

*Norifumi Yamaga¹, Yuta Mitsui² (1. Graduate School of Integrated Science and Technology, Shizuoka University, 2. Faculty of Science, Shizuoka University)

3:30 PM - 3:45 PM

[S22-14] Automatic detection and classification of the uplifted marine terrace by clustering DEM dataset

*Junki Komori¹, Ryosuke Ando¹, Masanobu Shishikura² (1. The University of Tokyo, 2. The National Institute of Advanced Industrial Science and Technology)

3:45 PM - 4:00 PM

[S22-15] Investigation of Prediction Model for Engineering Geomorphologic Classification using Convolutional Neural Network

*Sho Akagi¹, Toshihiko Hayakawa¹ (1. Mitsubishi Space Software Co., Ltd.)

Poster session (Sept. 18th)

S22P

Wed. Sep 18, 2019 1:00 PM - 2:30 PM ROOM P (International Conference Halls II and III)

+Add all to schedule

1:00 PM - 2:30 PM

[S22P-01] Detection of seismic signals under low SNR condition using an artificial neural network: Toward the development of low cost seismic network

Ahyi Kim¹, *Hiroki Uematsu¹ (1. Yokohama City University)

1:00 PM - 2:30 PM

[S22P-02] Earthquake/Noise Discrimination with Convolutional Neural Network

*Shota Kudo¹, Kengo Shimojo¹, Koji Tamaribuchi² (1. Japan Meteorological Agency, 2. Meteorological Research Institute)

1:00 PM - 2:30 PM

[S22P-03] Development of neural network to locate hypocenter with theoretical seismograms as learning data II

*Seiji Tsuboi¹, Daisuke Sugiyama¹ (1. Japan Agency for Marine-Earth Science and Technology)

1:00 PM - 2:30 PM

[S22P-04] Attempt to detect LFTs by clustering short-period OBS records

*Hidenobu Takahashi¹, Ryota Hino¹, Yusaku Ohta¹, Naoki Uchida¹, Syuichi Suzuki¹, Masanao Shinohara² (1. Tohoku University, 2. The University of Tokyo)

1:00 PM - 2:30 PM

[S22P-05] Insight into machine-learning model and prediction result: Case of random forest predictor for ground-motion intensit

*Hisahiko Kubo¹, Takashi Kunugi¹, Wataru Suzuki¹, Takeshi Kimura¹, Shin Aoi¹ (1. National Research Institute for Earth Science and Disaster Resilience)

1:00 PM - 2:30 PM

[S22P-06] site2vec: A Ground-Motion Predictor Learning Site Conditions from Data

*Tomohisa Okazaki¹, Tomoharu Iwata^1,2, Asako Iwaki³, Hiroyuki Fujiwara³, Naonori Ueda¹ (1. RIKEN Center for Advanced Intelligence Project, 2. NTT Communication Science Laboratories, 3. National Research Institute for Earth Science and Disaster Resilience)

1:00 PM - 2:30 PM

[S22P-07] Time series analyses of amplitude of the Earth's background free oscillations

*Ryuichi Kunugi¹, Naoki Suda¹ (1. Department of Earth and Planetary Systems Science, Graduate School of Science, Hiroshima University)

1:00 PM - 2:30 PM

[S22P-08] An Attempt to Classify a Pattern of Changes in Strain Observation Data by Machine Learning

*Takahiro Tsuyuki¹ (1. Meteorological Research Institute, Japan Meteorological Agency)

1:00 PM - 2:30 PM

[S22P-09] Machine Learning Approach for Integration of Multiple Relative Intensity Models

*Hirotaka Hachiya^1,2, Kazuro Hirahara¹, Naonori Ueda¹ (1. Center for Advanced Intelligence Project, RIKEN, 2. Faculty of System Engineering, Wakayama University)

1:00 PM - 2:30 PM

[S22P-10] Optimal distribution of offshore observation points for tsunami prediction using scenario search and regression methods

*Toshitaka Baba¹, Takuya Miyashita², Nobuhito Mori², Kenta Nakanishi³, Masato Okada⁴ (1. Tokushima University, 2. Kyoto University, 3. NITA Consultant, 4. Univ. of Tokyo)

Sessions

Special session » S22. Potentiality of Machine Learning in Seismology

[S22]AM-1

[S22-01] [INVITED]Data-Driven Anomaly Detection Based on Machine Learning: Smart Maintenance for Wind Energy

[S22-02] Seismic Phase Picking based on Sparsity-Aware Change Detection

[S22-03] Automatic P-wave detection using deep learning and visualization of the decision process

[S22-04] Application of convolutional neural networks to continuous seismic network records

[S22]AM-2

[S22-05] Development of 3D Convolutional Neural Network to locate hypocenter with theoretical seismograms of time series as training data.

[S22-06] Discrimination of earthquakes and tectonic tremor signals by applying a convolutional neural network to running spectral images

[S22-07] An unsupervised automatic classification algorithm for continuous seismic records using a nonparametric Bayesian approach

[S22-08] Study on Site-specific Ground Motion Evaluation Models Utilizing Machine Learning Method Considering Epicentral Directions

[S22-09] Study on Ground Motion Evaluation Models for Kanto Region Utilizing Machine Learning Method

[S22]PM-1

[S22-10] Improving the symmetry of ambient seismic field correlation functions with machine learning

[S22-11] A hybrid approach of Machine learning and Ensemble Kalman Filter for estimating frictional parameters in Nankai megaquake cycle simulator

[S22-12] Acceleration of matched-filter search and slip inversion of deep tectonic tremor using nearest neighbor search

[S22-13] Machine learning of postseismic deformation of the 2011 Tohoku-Oki earthquake based on recurrent neural network

[S22-14] Automatic detection and classification of the uplifted marine terrace by clustering DEM dataset

[S22-15] Investigation of Prediction Model for Engineering Geomorphologic Classification using Convolutional Neural Network

S22P

[S22P-01] Detection of seismic signals under low SNR condition using an artificial neural network: Toward the development of low cost seismic network

[S22P-02] Earthquake/Noise Discrimination with Convolutional Neural Network

[S22P-03] Development of neural network to locate hypocenter with theoretical seismograms as learning data II

[S22P-04] Attempt to detect LFTs by clustering short-period OBS records

[S22P-05] Insight into machine-learning model and prediction result: Case of random forest predictor for ground-motion intensit

[S22P-06] site2vec: A Ground-Motion Predictor Learning Site Conditions from Data

[S22P-07] Time series analyses of amplitude of the Earth's background free oscillations

[S22P-08] An Attempt to Classify a Pattern of Changes in Strain Observation Data by Machine Learning

[S22P-09] Machine Learning Approach for Integration of Multiple Relative Intensity Models

[S22P-10] Optimal distribution of offshore observation points for tsunami prediction using scenario search and regression methods

Authentication