P-wave first-motion polarity determination of waveform data in western Japan using deep learning

• 資料種別: 記事
• タイトル: P-wave first-motion polarity determination of waveform data in western Japan using deep learning
• 著者・編者: Shota Hara; Yukitoshi Fukahata; Yoshihisa Iio
• 出版事項: 日本 : Springer Nature
• 出版年月日等: 2019-11-29
• 出版年（W3CDTF）: 2019-11-29
• タイトル（掲載誌）: EPS : Earth, Planets and Space
• 巻号年月日等（掲載誌）: 71(127)
• 掲載巻: 71(127)
• ISSN（掲載誌）: 1880-5981
• ISSN-L（掲載誌）: 1343-8832
• 本文の言語コード: eng
• DOI: 10.1186/s40623-019-1111-x; https://doi.org/10.1186/s40623-019-1111-x
• 国立国会図書館永続的識別子: info:ndljp/pid/11467672; https://dl.ndl.go.jp/pid/11467672
• コレクション（共通）: 障害者向け資料
• コレクション（障害者向け資料：レベル1）: テキストデータ
• コレクション（個別）: 国立国会図書館デジタルコレクション > 電子書籍・電子雑誌 > その他; https://dl.ndl.go.jp/collections/B00035
• 収集根拠: オンライン資料収集制度
• 受理日（W3CDTF）: 2020-03-23T18:58:42+09:00
• 保存日（W3CDTF）: 2020-03-23
• 記録形式（IMT）: application/pdf
• オンライン閲覧公開範囲: 国立国会図書館内限定公開
• デジタル化資料送信: 図書館・個人送信対象外
• 遠隔複写可否（NDL）: 可
• 掲載誌（URI）: https://earth-planets-space.springeropen.com/articles
• 掲載誌（国立国会図書館永続的識別子）: info:ndljp/pid/11245705; https://dl.ndl.go.jp/pid/11245705
• 連携機関・データベース: 国立国会図書館 : 国立国会図書館デジタルコレクション; https://dl.ndl.go.jp

• 要約等: P-wave first-motion polarity is the most useful information in determining the focal mechanisms of earthquakes, particularly for smaller earthquakes. Algorithms have been developed to automatically determine P-wave first-motion polarity, but the performance level of the conventional algorithms remains lower than that of human experts. In this study, we develop a model of the convolutional neural networks (CNNs) to determine the P-wave first-motion polarity of observed seismic waveforms under the condition that P-wave arrival times determined by human experts are known in advance. In training and testing the CNN model, we use about 130 thousand 250 Hz and about 40 thousand 100 Hz waveform data observed in the San-in and the northern Kinki regions, western Japan, where three to four times larger number of waveform data were obtained in the former region than in the latter. First, we train the CNN models using 250 Hz and 100 Hz waveform data, respectively, from both regions. The accuracies of the CNN models are 97.9% for the 250 Hz data and 95.4% for the 100 Hz data. Next, to examine the regional dependence, we divide the waveform data sets according to the observation region, and then we train new CNN models with the data from one region and test them using the data from the other region. We find that the accuracy is generally high (≳ 95%) and the regional dependence is within about 2%. This suggests that there is almost no need to retrain the CNN model by regions. We also find that the accuracy is significantly lower when the number of training data is less than 10 thousand, and that the performance of the CNN models is a few percentage points higher when using 250 Hz data compared to 100 Hz data. Distribution maps, on which polarities determined by human experts and the CNN models are plotted, suggest that the performance of the CNN models is better than that of human experts.
• DOI: 10.1186/s40623-019-1111-x; https://doi.org/10.1186/s40623-019-1111-x
• オンライン閲覧公開範囲: インターネット公開
• 著作権情報: © The Author(s) 2019. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
• 関連情報（URI）: http://hdl.handle.net/2433/245276; http://id.ndl.go.jp/digimeta/11467672; https://dl.ndl.go.jp/pid/11467672; http://link.springer.com/content/pdf/10.1186/s40623-019-1111-x.pdf; http://link.springer.com/article/10.1186/s40623-019-1111-x/fulltext.html
• 参照: Preparatory AE activity of hydraulic fracture in granite with various viscous fluids revealed by deep learning technique; https://cir.nii.ac.jp/crid/1050569923264368768; Neural phase picker trained on the Japan meteorological agency unified earthquake catalog; https://cir.nii.ac.jp/crid/1360588379370845824; Recent advances in earthquake seismology using machine learning; https://cir.nii.ac.jp/crid/1360865815689043456; Stochastic determination of arrival time and initial polarity of seismic waveform; https://cir.nii.ac.jp/crid/1360869855141703168; Noise classification for the unified earthquake catalog using ensemble learning : the enhanced image of seismic activity along the Japan Trench by the S-net seafloor network; https://cir.nii.ac.jp/crid/2050588892104439680; Special issue "Crustal dynamics : toward integrated view of island arc seismogenesis; https://cir.nii.ac.jp/crid/2050870367078659712
• 連携機関・データベース: 国立情報学研究所 : CiNii Research; https://cir.nii.ac.jp/
• 提供元機関・データベース: 学術機関リポジトリデータベース; https://irdb.nii.ac.jp; 雑誌記事索引データベース; https://ndlsearch.ndl.go.jp; Crossref; https://www.crossref.org; CiNii Articles
• 書誌ID（NDLBibID）: 11467672; http://id.ndl.go.jp/bib/11467672
• NII論文ID: 120006777033