• ISSN 2096-8957
  • CN 10-1702/P

机器学习应用于地震预警中的地震波判别研究

Z. F. Li M. -A. Meier E. Hauksson Z. W. Zhan J. Andrews 王林 张红才

引用本文:
Citation:

机器学习应用于地震预警中的地震波判别研究

  • 摘要: 由于天然或人为干扰产生的局部脉冲式噪声影响,使得地震预警系统出现误报。为减少此类问题,我们利用美国南加州和日本的30万条地震波形记录,训练了一个生成式对抗网络(GAN)用于识别P波初至特征。我们将GAN判别器作为自动特征提取器,并利用70万条地震事件和噪声波形记录训练了一个随机森林分类器。结果表明,该方法可以辨别99.2%的P波和98.4%的噪声信号。其优越的性能有望极大地减少因局部脉冲式噪声而造成的误触发数量。我们的研究表明,GAN判别器能获取简洁有效的地震波形特征,可广泛应用于地震学研究。
  • [1]

    Arjovsky,M.,Chintala,S.,& Bottou,L.(2017).Wasserstein generative adversarial networks.Proceedings of the 34th International Confe-rence on Machine Learning,PMLR,70,214-223.
    [2]

    Böse,M.,Allen,R.,Brown,H.,Gua,G.,Fischer,M.,Hauksson,E.,et al.(2014).CISN Shake-Alert:An earthquake early warning demonstration system for California.In Early Warning for Geological Disasters(pp.49-69).Berlin,Heidelberg:Springer.
    [3]

    Böse,M.,Hauksson,E.,Solanki,K.,Kanamori,H.,Wu,Y.M.,& Heaton,T.H.(2009).A new trigger criterion for improved real-time performance of onsite earthquake early warning in southern California.Bulletin of the Seismol-ogical Society of America,99(2A),897-905.https://doi.org/10.1785/0120080034
    [4]

    Creswell,A.,White,T.,Dumoulin,V.,Arulkuma-ran,K.,Sengupta,B.,& Bharath,A.A.(2018).Generative adversarial networks:An overview.IEEE Signal Processing Magazine,35(1),53-65.https://doi.org/10.1109/MSP.2017.2765202
    [5]

    Goodfellow,I.,Pouget-Abadie,J.,Mirza,M.,Xu,B.,Warde-Farley,D.,Ozair,S.,et al.(2014).Genke-rative adversarial nets.In Proceedings of Neural Information Processing Systems(pp.2672-2680).
    [6]

    Ho,T.K.(1995).Random Decision Forests.Proceedings of the 3rd International Conference on Document Analysis and Recognition(pp.278-282).Montreal,QC,14-16 August 1995.
    [7]

    Ho,T.K.(1998).The random subspace method for constructing decision forests.IEEE Transac-tions on Pattern Analysis and Machine Intelligence,20(8),832-844.https://doi.org/10.1109/34.709601
    [8]

    Kohler,M.D.,Cochran,E.S.,Given,D.,Guiwits,S.,Neuhauser,D.,Henson,I.,et al.(2017).Earthquake early warning ShakeAlert system:West coast wide Production Prototype.Seismological Research Letters,89(1),99-107.
    [9]

    Kong,Q.,Allen,R.M.,Schreier,L.,& Kwon,Y.-W.(2016).Myshake:A smartphone seismic net-work for earthquake early warning and beyond.Science Advances,2(2),e1501055.https://doi.org/10.1126/sciadv.1501055
    [10]

    Krishcher,L.,& Fichtner,A.(2017).Generating seismograms with deep neural networks,abs-tract S41D-03.Presented at 2017 fall meeting,AGU,New Orleans,LA,11-15 December.
    [11]

    Meier,M.-A.,Heaton,T.,& Clinton,J.(2015).The Gutenberg algorithm:Evolutionary bayesian magnitude estimates for earthquake early warn-ing with a filter bank.Bulletin of the Seismological Society of America,105(5),2774-2786.https://doi.org/10.1785/0120150098
    [12]

    Pedregosa,F.,Varoquaux,G.,Gramfort,A.,Michel,V.,Thirion,B.,Grisel,O.,et al.(2011).Scikit-learn:Machine learning in Python.Journal of Machine Learning Research,12,2825-2830.
    [13]

    Perol,T.,Gharbi,M.,& Denolle,M.(2018).Convolutional neural network for earthquake detection and location.Science Advances,4(2),e1700578.https://doi.org/10.1126/sciadv.1700578
    [14]

    Radford,A.,Metz,L.,& Chintala,S.(2016).Unsupervised representation learning with deep convolutional generative adversarial networks.In Proceedings of the 5th International Conferen-ce on Learning Representations(ICLR)-Workshop Track,2016.
    [15]

    Rouet-Leduc,B.,Hulbert,C.,Lubbers,N.,Barros,K.,Humphreys,C.J.,& Johnson,P.A.(2017).Machine learning predicts laboratory earth-quakes.Geophysical Research Letters,44,9276-9282.https://doi.org/10.1002/2017GL074677
    [16]

    Salimans,T.,Goodfellow,I.,Zaremba,W.,Cheung,V.,Radford,A.,& Chen,X.(2017).Improved techniques for training GANs.In Proceedings of Neural Information Processing Systems(pp.2234-2242).
    [17]

    Wurman,G.,Allen,R.M.,& Lombard,P.(2007).Toward earthquake early warning in northern California.Journal of Geophysical Research,112,B08311.https://doi.org/10.1029/2006JB004830
  • [1] 孙伟家王一博魏勇赵亮 . 火星地震学与内部结构研究. 地球与行星物理论评, 2021, 52(): 1-13. doi: 10.16738/j.dqyxx.2021-016
    [2] 吴忠良王龙李丽张晓东邵志刚李营孙珂车时 . 中国地震科学实验场:地震预测与系统设计. 地球与行星物理论评, 2021, 52(): 1-5. doi: 10.16738/j.dqyxx.2021-028
    [3] 魏勇 . 国家需求在行星科学一级学科建设中的导向作用. 地球与行星物理论评, 2021, 52(): 1-3. doi: 10.16738/j.dqyxx.2021-034
    [4] 刘洋吴兴刘正豪邹永廖 . 火星的地质演化和宜居环境研究进展. 地球与行星物理论评, 2021, 52(): 1-21. doi: 10.16738/j.dqyxx.2021-0025
    [5] 钟俊 . 水星磁层观测研究. 地球与行星物理论评, 2021, 52(): 1-12. doi: 10.16738/j.dqyxx.2021-021
    [6] 李坤崔峻魏勇 . 空间电场的原位测量. 地球与行星物理论评, 2021, 52(): 1-10. doi: 10.16738/j.dqyxx.2021-013
    [7] 曹雨田牛丹丹崔峻吴晓姝 . 金星与火星电离层研究现状概述. 地球与行星物理论评, 2021, (): 1-15. doi: 10.16738/j.dqyxx.2021-024
    [8] 吴兆朋李静李陶崔峻 . 火星沙尘暴及其与大气波动的相互作用. 地球与行星物理论评, 2021, 52(): 1-14. doi: 10.16738/j.dqyxx.2021-022
  • 加载中
计量
  • 文章访问数:  1547
  • HTML全文浏览量:  540
  • PDF下载量:  141
  • 被引次数: 0
出版历程

机器学习应用于地震预警中的地震波判别研究

摘要: 由于天然或人为干扰产生的局部脉冲式噪声影响,使得地震预警系统出现误报。为减少此类问题,我们利用美国南加州和日本的30万条地震波形记录,训练了一个生成式对抗网络(GAN)用于识别P波初至特征。我们将GAN判别器作为自动特征提取器,并利用70万条地震事件和噪声波形记录训练了一个随机森林分类器。结果表明,该方法可以辨别99.2%的P波和98.4%的噪声信号。其优越的性能有望极大地减少因局部脉冲式噪声而造成的误触发数量。我们的研究表明,GAN判别器能获取简洁有效的地震波形特征,可广泛应用于地震学研究。

English Abstract

参考文献 (17)

目录

    /

    返回文章
    返回