簡易檢索 / 詳目顯示

研究生: 江又靖
You-Jing Chiang
論文名稱: 基於神經網絡的地面運動預測方法應用於現地型地震預警
A Ground Motion Prediction Method Based on Neural Network for On-site Earthquake Early Warning
指導教授: 金台齡
Tai-Lin Chin
口試委員: 金台齡
Tai-Lin Chin
陳達毅
Da-Yi Chen
陳冠宇
Kuan-Yu Chen
許丁友
Ting-Yu Hsu
學位類別: 碩士
Master
系所名稱: 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
論文出版年: 2021
畢業學年度: 109
語文別: 英文
論文頁數: 62
中文關鍵詞: 地面震動預測地震預警系統卷積神經網路
外文關鍵詞: ground motion prediction, earthquake early warning, convolutional neural network
相關次數: 點閱:420下載:6
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

台灣每年都會發生很多地震,其中的破壞性地震往往會帶來重大的損失,而能有效減少這些地震災害的方法為地震預警系統,能夠在這些強震波發生之前提供警告,來減少地震災害。地震預警系統又可以分成兩種類型,一種是區域型預警,另一種則為現地型預警,區域型預警系統會收集震央附近測站的資訊,如果這些波的資訊顯示出可能會有強震波的到來,系統就會發警報給較遠的地方,但面臨到的問題是,近震央的區域無法及時收到警報,會形成一個預警盲區,等到警報發出的時候,地震早就已經搖完了。所以為了解決預警盲區的問題,才有了現地型預警系統,能夠為近震央區域提供預警,希望每一個地震測站收到地震波的很短的時間內,就可以預測出將來會不會發生劇烈地搖晃,實際上會使用初始P波信號來預測最大的地面運動,傳統方法是學者使用直覺或經驗選擇的某些標準來進行預測。但是,這些標準很難選擇,而且預測的準確性也很容易會受到這些標準的影響。本文研究了基於神經網路的方法,在P波到達地震測站後及早預測地震的最大地面運動。建立模型以使用初始P波加速度信號的幾秒鐘時間窗口進行預測。該模型由台灣1991年至2019年採集的地震波進行訓練,並透過2020年和2021年的事件進行評估。從評估結果來看,所提出的方案在準確性和平均預警時間方面皆明顯優於傳統基於閾值的方法。


On-site earthquake early warning is a challenging problem since the limited time and information collected before the warning determination. A potential solution to prevent severe disasters is to predict the greatest ground motion using the initial P-wave signal and provide warnings before the hit of the shaking. In practice, the accuracy of the prediction is the most critical issue for earthquake early warning systems. Traditional methods use certain criteria selected by intuition or experience to make the prediction. However, the thresholds for the criteria are difficult to select and may significantly affect the accuracy. This paper investigates the methods based on artificial intelligence to predict the greatest ground motion of earthquakes at the early stage when the P-wave arrives at the seismograph stations. A neural network model is built to make the predictions using a small window of the initial P-wave acceleration signal. The model is trained by the seismic waves collected from 1991 to 2019 in Taiwan and evaluated by events in 2020 and 2021. From the evaluations, the proposed scheme significantly outperforms the threshold-based method in terms of the accuracy and the average leading time.

Abstract in Chinese Abstract in English Acknowledgements Contents List of Figures List of Tables 1 Introduction 1.1 Background 1.2 Motivation 1.3 Contributions 1.4 Organization 2 Related Work 2.1 Regional EEW systems 2.2 Onsite EEW systems 2.3 Artificial intelligence techniques 3 Intelligent Ground Motion Prediction (IGMP) Model 3.1 Architecture 3.1.1 Input 3.1.2 Feature extraction 3.1.3 Classification 3.1.4 Output 3.2 Loss function 4 Performance Evaluations 4.1 Dataset 4.2 Prediction accuracy 4.3 Average leading time 4.4 Performance on the sample cases 5 Discussion 5.1 Performance on CWBSN 5.2 Performance on TSMIP 6 Conclusion References

[1] R. M. Allen, P. Gasparini, O. Kamigaichi, and M. Bose, “The status of earthquake early warning
around the world: An introductory overview,” Seismological Research Letters, vol. 80, no. 5, pp. 682–
693, 2009.
[2] C. Satriano, Y.M.
Wu, A. Zollo, and H. Kanamori, “Earthquake early warning: Concepts, methods
and physical grounds,” Soil Dynamics and Earthquake Engineering, vol. 31, no. 2, pp. 106–118, 2011.
[3] Y.M.
Wu and H. Kanamori, “Rapid assessment of damage potential of earthquakes in taiwan from the
beginning of p waves,” Bulletin of the Seismological Society of America, vol. 95, no. 3, pp. 1181–1185,
2005.
[4] A. Zollo, O. Amoroso, M. Lancieri, Y.M.
Wu, and H. Kanamori, “A thresholdbased
earthquake
early warning using dense accelerometer networks,” Geophysical Journal International, vol. 183,
no. 2, pp. 963–974, 2010.
[5] Y. Nakamura, J. Saita, and T. Sato, “On an earthquake early warning system (EEW) and its applications,”
Soil Dynamics and Earthquake Engineering, vol. 31, no. 2, pp. 127–136, 2011.
[6] E. L. Olson and R. M. Allen, “The deterministic nature of earthquake rupture,” Nature, vol. 438,
no. 7065, pp. 212–215, 2005.
[7] H. Kanamori, “Realtime
seismology and earthquake damage mitigation,” Annual Review of Earth
and Planetary Sciences, vol. 33, no. 1, pp. 195–214, 2005.
[8] Y.M.
Wu and L. Zhao, “Magnitude estimation using the first three seconds Pwave
amplitude in
earthquake early warning,” Geophysical Research Letters, vol. 33, no. 16, 2006.
[9] D. Bindi, L. Luzi, M. Massa, and F. Pacor, “Horizontal and vertical ground motion prediction equations
derived from the italian accelerometric archive (itaca),” Bulletin of earthquake engineering, vol. 8,
no. 5, pp. 1209–1230, 2010.
[10] D. Bindi, F. Pacor, L. Luzi, R. Puglia, M. Massa, G. Ameri, and R. Paolucci, “Ground motion prediction
equations derived from the Italian strong motion database,” Bulletin of Earthquake Engineering,
vol. 9, no. 6, pp. 1899–1920, 2011.
[11] W.Y.
Jean, Y.W.
Chang, K.L.
Wen, and C.H.
Loh, “Early estimation of seismic hazard for strong
earthquakes in taiwan,” Natural hazards, vol. 37, no. 12,
pp. 39–53, 2006.
[12] Y.M.
Wu and H. Kanamori, “Experiment on an onsite early warning method for the taiwan early
warning system,” Bulletin of the Seismological Society of America, vol. 95, no. 1, pp. 347–353, 2005.
[13] C.Y.
Hsieh, W.A.
Chao, and Y.M.
Wu, “An examination of the thresholdbased
earthquake early
warning approach using a lowcost
seismic network,” Seismological Research Letters, vol. 86, no. 6,
pp. 1664–1667, 2015.
[14] S. Colombelli, O. Amoroso, A. Zollo, and H. Kanamori, “Test of a thresholdbased
earthquake earlywarning
method using Japanese data,” Bulletin of the Seismological Society of America, vol. 102,
no. 3, pp. 1266–1275, 2012.
[15] M. Böse, E. Hauksson, K. Solanki, H. Kanamori, Y.M.
Wu, and T. Heaton, “A new trigger criterion for
improved realtime
performance of onsite earthquake early warning in southern california,” Bulletin
of the Seismological Society of America, vol. 99, no. 2A, pp. 897–905, 2009.
[16] M. Böse, R. Allen, H. Brown, G. Gua, M. Fischer, E. Hauksson, T. Heaten, M. Hellweg, M. Liukis,
D. Neuhauser, P. Maechling, K. Solanki, M. Vinci, I. Henson, O. Khainovski, S. Kuyuk, M. Carpio,
M.A.
Meier, and T. Jordan, “CISN ShakeAlert: An earthquake early warning demonstration system
for California,” Early warning for geological disasters, pp. 49–69, 2014.
[17] A. Caruso, S. Colombelli, L. Elia, M. Picozzi, and A. Zollo, “An onsite
alert level early warning
system for italy,” Journal of Geophysical Research: Solid Earth, vol. 122, no. 3, pp. 2106–2118,
2017.
[18] P.L.
Huang, T.L.
Lin, and Y.M.
Wu, “Application of τ c* Pd in earthquake early warning,” Geophysical
Research Letters, vol. 42, no. 5, pp. 1403–1410, 2015.
[19] N.C.
Hsiao, Y.M.
Wu, T.C.
Shin, L. Zhao, and T.L.
Teng, “Development of earthquake early warning
system in taiwan,” Geophysical research letters, vol. 36, no. 5, 2009.
[20] Y.M.
Wu, D.Y.
Chen, T.L.
Lin, C.Y.
Hsieh, T.L.
Chin, W.Y.
Chang, W.S.
Li, and S.H.
Ker,
“A highdensity
seismic network for earthquake early warning in taiwan based on low cost sensors,”
Seismological Research Letters, vol. 84, no. 6, pp. 1048–1054, 2013.
[21] D.Y.
Chen, N.C.
Hsiao, and Y.M.
Wu, “The earthworm based earthquake alarm reporting system
in taiwan,” Bulletin of the Seismological Society of America, vol. 105, no. 2A, pp. 568–579, 2015.
[22] C. E. Johnson, A. Bittenbinder, B. Bogaert, L. Dietz, and W. Kohler, “Earthworm: A flexible approach
to seismic network processing,” Iris newsletter, vol. 14, no. 2, pp. 1–4, 1995.
[23] M. Böse, T. Heaton, and E. Hauksson, “Rapid estimation of earthquake source and groundmotion
parameters
for earthquake early warning using data from a single threecomponent
broadband or strongmotion
sensor,” Bulletin of the Seismological Society of America, vol. 102, no. 2, pp. 738–750, 2012.
[24] T.Y.
Hsu, S.K.
Huang, Y.W.
Chang, C.H.
Kuo, C.M.
Lin, T.M.
Chang, K.L.
Wen, and C.H.
Loh,
“Rapid onsite
peak ground acceleration estimation based on support vector regression and pwave
features in taiwan,” Soil Dynamics and Earthquake Engineering, vol. 49, pp. 210–217, 2013.
[25] A. H. Alavi and A. H. Gandomi, “Prediction of principal groundmotion
parameters using a hybrid
method coupling artificial neural networks and simulated annealing,” Computers & Structures, vol. 89,
no. 2324,
pp. 2176–2194, 2011.
[26] T. Perol, M. Gharbi, and M. Denolle, “Convolutional neural network for earthquake detection and
location,” Science Advances, vol. 4, no. 2, p. e1700578, 2018.
[27] M. Kriegerowski, G. M. Petersen, H. VasyuraBathke,
and M. Ohrnberger, “A deep convolutional
neural network for localization of clustered earthquakes based on multistation full waveforms,” Seismological
Research Letters, vol. 90, no. 2A, pp. 510–516, 2018.
[28] Z. E. Ross, M.A.
Meier, E. Hauksson, and T. H. Heaton, “Generalized seismic phase detection with
deep learning,” Bulletin of the Seismological Society of America, vol. 108, no. 5A, pp. 2894–2901,
2018.
[29] W. Zhu and G. C. Beroza, “PhaseNet: a deepneuralnetworkbased
seismic arrivaltime
picking
method,” Geophysical Journal International, vol. 216, no. 1, pp. 261–273, 2019.
[30] D. Jozinović, A. Lomax, I. Štajduhar, and A. Michelini, “Rapid prediction of earthquake ground shaking
intensity using raw waveform data and a convolutional neural network,” Geophysical Journal
International, vol. 222, no. 2, pp. 1379–1389, 2020.
[31] J. Münchmeyer, D. Bindi, U. Leser, and F. Tilmann, “The transformer earthquake alerting model: a
new versatile approach to earthquake early warning,” Geophysical Journal International, vol. 225,
no. 1, pp. 646–656, 2021.
[32] S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal
covariate shift,” Proceedings of the 32nd International Conference on Machine Learning, vol. 37,
pp. 448–456, 2015.
[33] V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines,” Proceedings
of the 27th International Conference on International Conference on Machine Learning, pp. 807–814,
2010.
[34] I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” International Conference on
Learning Representations, 2019.
[35] P. J. Werbos, “Backpropagation through time: what it does and how to do it,” Proceedings of the IEEE,
vol. 78, no. 10, pp. 1550–1560, 1990.
[36] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein,
L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy,
B. Steiner, L. Fang, J. Bai, and S. Chintala, “Pytorch: An imperative style, highperformance
deep
learning library,” Advances in neural information processing systems, vol. 32, pp. 8026–8037, 2019.
[37] D. M. Powers, “Evaluation: from precision, recall and Fmeasure
to ROC, informedness, markedness
and correlation,” International Journal of Machine Learning Technology, vol. 2, no. 1, pp. 37–63,
2011.
48

QR CODE