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)

3:00 PM - 3:15 PM

[STT40-05] Detection of Deep Low-Frequency Tremors from Past Seismograms Based on Convolutional Neural Network

Ryosuke Kaneko1,2, *Hiromichi Nagao2,1, Shin-ichi Ito2,1, Hiroshi Tsuruoka2, Kazushige Obara2 (1.Graduate School of Information Science and Technology, The University of Tokyo, 2.Earthquake Research Institute, The University of Tokyo)

Keywords:Deep low-frequency tremor, Past seismogram, Deep learning, ResNet, Convolutional neural network

The establishment of the High Sensitivity Seismograph Network (Hi-net) in Japan more than 20 years ago has led to the discovery of deep low-frequency tremors. As such tremors are considered to relate to large earthquakes, it is an important issue in seismology to investigate tremors that occurred before establishing seismograph networks, which record seismic data in digital format. We use a deep learning model, convolutional neural network (CNN), to detect evidence of tremors from seismic waveforms recorded on papers more than 50 years ago. First, we construct a CNN based on the ResNet structure to detect tremors from seismogram images. Then, we conduct learning with synthetic images generated referring to the past seismograms recorded at the Kumano observatory, operated by Earthquake Research Institute, The University of Tokyo. The results show that the trained CNN can correctly determine whether tremors exist or not in the seismogram images. In addition, the Grad-CAM heatmaps to visualize the model predictions clearly indicate the tremor location in each image. Next, we conduct learning with seismogram images generated from the real data of Hi-net. Despite contaminations in the seismogram images due to a variety of noises, the CNNs trained through a fine-tuning successfully detect tremors. Finally, we apply the trained CNNs to the seismogram images at the Kumano observatory. The CNNs show a promising potential to detect tremors from the past seismogram images.