進階搜尋


下載電子全文  
系統識別號 U0026-1508201810461600
論文名稱(中文) 結合訊號特徵指標及機器學習技術於崩塌地動訊號辨識之研究:以2009年莫拉克颱風為例
論文名稱(英文) The study of combining signal indicators with machine learning techniques to identify landslide-quake signals: A case study of the 2009 Typhoon Morakot, Taiwan
校院名稱 成功大學
系所名稱(中) 地球科學系
系所名稱(英) Department of Earth Sciences
學年度 106
學期 2
出版年 107
研究生(中文) 吳昱杰
研究生(英文) Yu-Jie Wu
學號 L46051073
學位類別 碩士
語文別 英文
論文頁數 113頁
口試委員 指導教授-林冠瑋
口試委員-李恩瑞
口試委員-趙韋安
口試委員-陳麒文
中文關鍵字 崩塌  地動訊號  台灣寬頻地震網  機器學習  莫拉克颱風 
英文關鍵字 landslide  landslide-quake signal  BATS  machine learning  Typhoon Morakot 
學科別分類
中文摘要 2009年莫拉克颱風後,大規模邊坡災害成為防災工作的重點之一,但是礙於崩塌的觀測紀錄不易,使得崩塌時間資訊難以獲得,而影響進行後續的各類崩塌預警的研究。近年來有關於地表振動事件自動偵測方法的研究逐漸興盛,但是針對山崩地動訊號自動偵測的研究卻相對較少。本研究利用台灣寬頻地震站所記錄到的地表振動訊號,透過計算地動訊號在時間域及頻率域的特徵值(移動平均值、閃爍指數、芮氏規模與時間規模比值、高低頻功率譜密度比值)配合機器學習技術的應用嘗試建立一套崩塌地動訊號偵測的方法(Landslide-quake Automatic Detection, LQAD),希望能夠有效縮短判釋崩塌訊號的時間。本研究中以2009年莫拉克颱風期間的地表震動紀錄為測試案例,採用LQAD進行崩塌地動訊號的自動判釋,結果顯示LQAD對崩塌地動訊號的命中率達100 %,靈敏性為79.4 %,以及準確性達到98.1 %。該結果表示,由LQAD判釋獲得的崩塌地動訊號全具有顯著地崩塌地動特徵,然而仍有部分崩塌地動訊號在LQAD自動偵測下被判釋為地震事件或是其他噪訊。藉由比對LQAD的判釋結果與地動紀錄的波形及時頻圖,本研究認為各別崩塌訊號的振幅大小以及遠震事件應是導致LQAD出現錯誤判釋的主要因素。
英文摘要 After 2009 Typhoon Morakot, large scale landslides became an important issue of disaster prevention and mitigation in Taiwan. The difficulties in observing landslides, however, hindered obtaining their temporal information and thus impeded further studies of landslide warning. Despite an increasing number of studies on automatic detection methods of ground-motion events in recent years, studies aiming to automatic detect landslide ground-motion are rare. With the application of machine learning technology, this study attempts to accelerate landslide interpretation by establishing an automatic detection of landslide-quake signals (Landslide-quake Automatic Detection, LQAD) that calculates the indicators of ground-motion signals in time and frequency domains (i.e. moving average, scintillation index, local magnitude and duration magnitude, ratio of high and low-frequency power spectrum density) based on signals recorded by broadband stations in Taiwan. The result from applying LQAD to landslide-quake signals of 2009 Typhoon Morakot shows that it has a precision value of 100 %, a sensitivity value of 79.4 %, and an accuracy value of 98.1 %. F1-score is 88 %. The result also demonstrated that all the landslide-quake signals obtained by LQAD have significant landslide characteristics, yet some of the signals were interpreted as earthquake events or other kinds of ambient noise. The comparison of LQAD-interpreted results to waveforms and spectrograms of ground motion suggested that the amplitude of landslide signals and the tele-seismic events are the main factors leading to the misinterpretation of LQAD.
論文目次 摘要 II
Abstract III
Table of Content VII
List of Table IX
List of Figures X
Chapter 1 Introduction 1
1.1 Study motivation 1
1.2 Research purpose 2
1.3 Research framework 3
Chapter 2 Literature review 5
2.1 Characteristic features of seismic signals driven by landslides 5
2.2 The studies on methods of landslide signal detection 7
2.3 The studies of signal classification using machine learning 10
Chapter 3 Study methods 13
3.1 Data source, signal processing and workflow of detection 13
3.2 Moving Average (MA) and Scintillation Index (SI) 19
3.3 Pseudo-probability time series (PPTS) 24
3.3.1 Calculation process of STA/LTA 24
3.3.2 Modified STA/LTA method 25
3.4 The ratio of low-frequency PSD to high-frequency PSD (RPSD) 30
3.5 The ratio of local magnitude (ML) to duration magnitude (MD) 32
3.5.1 Event waveform detection method 32
3.5.2 Locating seismic sources 33
3.5.3 Ratio of ML to MD 36
3.6 Machine learning applied to the detection process 38
3.6.1 Machine learning process 38
3.6.2 Assessment of LQAD results using confusion matrix 39
Chapter 4 Results 43
4.1 Results of the manual interpretation 43
4.2 The result of detection using SI and MA detectors (SIMA) 45
4.2.1 Detected landslide events by SIMA 45
4.2.2 Undetected landslide-quakes by SIMA 48
4.3 The results of detecting using RPSD 52
4.3.1 Detected landslide-quake by RPSD 52
4.3.2 Undetected landslide-quakes by RPSD 57
4.4 The results of detection using ML/MD 58
4.4.1 Detection of landslide events-quakes using ML/MD 58
4.4.2 Undetected landslide-quakes by ML/MD 62
4.5 The detection by combining SIMA, RPSD, ML/MD methods 63
4.5.1 Long-period signals detected by LQAD 66
Chapter 5 Discussion 69
5.1 Application of LQAD for Typhoon Soudelor 69
Chapter 6 Conclusions 81
Reference 83
Appendix 92


參考文獻 Aiken, C., Peng, Z., & Chao, K. (2013). Tremors along the Queen Charlotte Margin triggered by large teleseismic earthquakes. Geophysical Research Letters, Vol. 40, pp. 829-834.

Allen, R. V. (1978). Automatic earthquake recognition and timing from single traces. Bulletin of the Seismological Society of America, Vol. 68, pp. 1521-1532.

Arciniega‐Ceballos, A., Dawson, P., & Chouet, B. A. (2012). Long period seismic source characterization at Popocatépetl volcano, Mexico. Geophysical Research Letters, vol. 39, L20307.

Bakun, W. H. (1984). Seismic moments, local magnitudes, and coda-duration magnitudes for earthquakes in central California. Bulletin of the Seismological Society of America, Vol. 74, pp. 439-458.

Bartlow, N. M., Miyazaki, S. I., Bradley, A. M., & Segall, P. (2011). Space‐time correlation of slip and tremor during the 2009 Cascadia slow slip event. Geophysical Research Letters, Vol. 38, L18309

Beguería, S. (2006). Validation and evaluation of predictive models in hazard assessment and risk management. Natural Hazards, Vol. 37, pp. 315-329.

Benítez, M. C., Ramírez, J., Segura, J. C., Ibanez, J. M., Almendros, J., García-Yeguas, A., & Cortes, G. (2007). Continuous HMM-based seismic-event classification at Deception Island, Antarctica. IEEE Transactions on Geoscience and remote sensing, Vol. 45, pp. 138-146.

Beroza, G. C., & Ide, S. (2011). Slow earthquakes and nonvolcanic tremor. Annual review of Earth and planetary sciences, Vol. 39, pp. 271-296.

Bisztricany, E. (1958). A new method for determination of the magnitude of earthquakes, Geofiz. Kozlemen, Vol. 7, pp. 69–96.

Bluma, A. L., & Langley, P. (1997). Selection of relevant features and examples in machine learning. Artificial intelligence, Vol. 97, pp. 245-271.

Brodsky, E. E., Gordeev, E., & Kanamori, H. (2003). Landslide basal friction as measured by seismic waves. Geophysical Research Letters, Vol. 30, No. 24, 2236

Burtin, A., Hovius, N., & Turowski, J. M. (2016). Seismic monitoring of torrential and fluvial processes. Earth Surface Dynamics, Vol. 4, pp. 285-307.

Chao, K., Peng, Z., Wu, C., Tang, C. C., & Lin, C. H. (2012). Remote triggering of non-volcanic tremor around Taiwan. Geophysical Journal International, Vol. 188, pp. 301-324.

Chao, W. A., Zhao, L., Chen, S. C., Wu, Y. M., Chen, C. H., & Huang, H. H. (2016). Seismology-based early identification of dam-formation landquake events. Scientific reports, Vol. 6, 19259.

Chen, C. H., Chao, W. A., Wu, Y. M., Zhao, L., Chen, Y. G., Ho, W. Y., ... & Chang, J. M. (2013). A seismological study of landquakes using a real-time broad-band seismic network. Geophysical Journal International, Vol. 194, pp. 885-898.

Chen, C. S., and Wu, J. H. (2009). The Characteristics of Topography Changes Caused by the large Deep landslide of the shiandu Mountains in Xiaolin Village, Kaohsiung County. Journal of Chinese Soil and Water Conservation, Vol. 40, pp. 359-376. (in Chinese)

Chen, C. W., Saito, H., & Oguchi, T. (2015). Rainfall intensity–duration conditions for mass movements in Taiwan. Progress in Earth and Planetary Science, Vol. 2, pp. 2-14.

Chen, Y. C., Chang, K. T., Chiu, Y. J., Lau, S. M., & Lee, H. Y. (2013). Quantifying rainfall controls on catchment‐scale landslide erosion in Taiwan. Earth Surface Processes and Landforms, Vol. 38, pp. 372-382.

Chien, F. C., & Kuo, H. C. (2011). On the extreme rainfall of Typhoon Morakot (2009). Journal of Geophysical Research: Atmospheres, Vol. 116, D05104.

Chen, C. S., & Chen, Y. L. (2003). The rainfall characteristics of Taiwan. Monthly Weather Review, Vol. 131, pp. 1323-1341.

Colombelli, S., Emolo, A., & Zollo, A. (2014). A duration magnitude scale for the Irpinia Seismic Network, Southern Italy. Seismological Research Letters, Vol. 85, pp. 98-107.

Dammeier, F., Moore, J. R., Haslinger, F., & Loew, S. (2011). Characterization of alpine rockslides using statistical analysis of seismic signals. Journal of Geophysical Research: Earth Surface, Vol. 116, F04024

Dammeier, F., Moore, J. R., Hammer, C., Haslinger, F., & Loew, S. (2016). Automatic detection of alpine rockslides in continuous seismic data using hidden Markov models. Journal of Geophysical Research: Earth Surface, Vol. 121, pp. 351-371.

Del Pezzo, E., Esposito, A., Giudicepietro, F., Marinaro, M., Martini, M., & Scarpetta, S. (2003). Discrimination of earthquakes and underwater explosions using neural networks. Bulletin of the Seismological Society of America, Vol. 93, pp. 215-223.

Deparis, J., Jongmans, D., Cotton, F., Baillet, L., Thouvenot, F., & Hantz, D. (2008). Analysis of rock-fall and rock-fall avalanche seismograms in the French Alps. Bulletin of the Seismological Society of America, Vol. 98, pp. 1781-1796.

Ekström, G., & Stark, C. P. (2013). Simple scaling of catastrophic landslide dynamics. Science, Vol. 339, pp. 1416-1419.

Esposito, A. M., Giudicepietro, F., Scarpetta, S., D’Auria, L., Marinaro, M., & Martini, M. (2006). Automatic discrimination among landslide, explosion-quake, and microtremor seismic signals at Stromboli volcano using neural networks. Bulletin of the Seismological Society of America, Vol. 96, pp. 1230-1240.

Faillettaz, J., Funk, M., & Sornette, D. (2011). Icequakes coupled with surface displacements for predicting glacier break-off. Journal of Glaciology, Vol. 57, pp. 453-460.

Favreau, P., Mangeney, A., Lucas, A., Crosta, G., & Bouchut, F. (2010). Numerical modeling of landquakes. Geophysical Research Letters, Vol. 37, L15305.

Feng, Z. (2011). The seismic signatures of the 2009 Shiaolin landslide in Taiwan. Nat. Hazards Earth Syst. Sci., Vol. 11, pp. 1159-1569.

Fuchs, F., Lupi, M., & Miller, S. A. (2014). Remotely triggered nonvolcanic tremor in Sumbawa, Indonesia. Geophysical Research Letters, Vol. 41, pp. 4185-4193.

Hibert, C., Mangeney, A., Grandjean, G., & Shapiro, N. M. (2011). Slope instabilities in Dolomieu crater, Réunion Island: From seismic signals to rockfall characteristics. Journal of Geophysical Research: Earth Surface, Vol. 116, F04032.

Ho, C. S. (1986). A synthesis of the geologic evolution of Taiwan. Tectonophysics, Vol. 125, pp. 1-16.

Joachims, T. (1998, April). Text categorization with support vector machines: Learning with many relevant features. In European conference on machine learning. Springer, Berlin, Heidelberg., pp. 137-142.

Goetz, J. N., Brenning, A., Petschko, H., & Leopold, P. (2015). Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling. Computers & geosciences, Vol. 81, pp. 1-11.

Kortström, J., Uski, M., & Tiira, T. (2016). Automatic classification of seismic events within a regional seismograph network. Computers & Geosciences, Vol. 87, pp. 22-30.

Kanamori, H., & Given, J. W. (1982). Analysis of long‐period seismic waves excited by the May 18, 1980, eruption of Mount St. Helens—A terrestrial monopole?. Journal of Geophysical Research: Solid Earth, Vol. 87, pp. 5422-5432.

Kao, H., Shan, S. J., Dragert, H., Rogers, G., Cassidy, J. F., Wang, K., & Ramachandran, K. (2006). Spatial‐temporal patterns of seismic tremors in northern Cascadia. Journal of Geophysical Research: Solid Earth, Vol. 111, B03309.

Kao, H., Thompson, P. J., Rogers, G., Dragert, H., & Spence, G. (2007). Automatic detection and characterization of seismic tremors in northern Cascadia. Geophysical Research Letters, Vol. 34, L16313.

Kao, H., Shan, S. J., Bent, A., Woodgold, C., Rogers, G., Cassidy, J. F., & Ristau, J. (2012). Regional centroid-moment-tensor analysis for earthquakes in Canada and adjacent regions: An update. Seismological Research Letters, Vol. 83, pp. 505-515.

Kawakatsu, H. (1989). Centroid single force inversion of seismic waves generated by landslides. Journal of Geophysical Research: Solid Earth, Vol. 94, pp. 12363-12374.

Korup, O., & Stolle, A. (2014). Landslide prediction from machine learning. Geology Today, Vol. 30, pp. 26-33.

La Rocca, M., Galluzzo, D., Saccorotti, G., Tinti, S., Cimini, G. B., & Del Pezzo, E. (2004). Seismic signals associated with landslides and with a tsunami at Stromboli volcano, Italy. Bulletin of the Seismological Society of America, Vol. 94, pp. 1850-1867.

Lin, C. H., Kumagai, H., Ando, M., & Shin, T. C. (2010). Detection of landslides and submarine slumps using broadband seismic networks. Geophysical Research Letters, Vol. 37, L22309.

Lo, Y. Y. (2015). Report on Typhoon 1513(Soudelor)of 2015. Weather Forecast Center, Central Weather Bureau, Taipei.

Lotti, A., Saccorotti, G., Fiaschi, A., Matassoni, L., Gigli, G., Pazzi, V., & Casagli, N. (2015). Seismic monitoring of a rockslide: The Torgiovannetto quarry (central Apennines, Italy). In Engineering Geology for Society and Territory-Volume 2. Springer, Cham, pp. 1537-1540.

Manconi, A., Picozzi, M., Coviello, V., De Santis, F., & Elia, L. (2016). Real‐time detection, location, and characterization of rockslides using broadband regional seismic networks. Geophysical Research Letters, Vol. 43, pp. 6960-6967.

Manel, S., Williams, H. C., & Ormerod, S. J. (2001). Evaluating presence–absence models in ecology: the need to account for prevalence. Journal of applied Ecology, Vol. 38, pp. 921-931.

Manconi, M. P., Velio Coviello, Francesca De Santis, Luca Elia. (2016). Supporting Information for Real-time detection, location and characterization of rockslides using broadband regional seismic networks. Geophys. Res. Lett., 43,
6960–6967, doi:10.1002/2016GL069572.
Marjanovic, M., Bajat, B., & Kovacevic, M. (2009). Landslide susceptibility assessment with machine learning algorithms. International Conference on Intelligent Networking and Collaborative Systems, pp. 273-278.

Marjanović, M., Kovačević, M., Bajat, B., & Voženílek, V. (2011). Landslide susceptibility assessment using SVM machine learning algorithm. Engineering Geology, Vol. 123, pp. 225-234.

Moretti, L., Mangeney, A., Capdeville, Y., Stutzmann, E., Huggel, C., Schneider, D., & Bouchut, F. (2012). Numerical modeling of the Mount Steller landslide flow history and of the generated long period seismic waves. Geophysical Research Letters, Vol. 39, L16402.

Norris, R. D. (1994). Seismicity of rockfalls and avalanches at three Cascade Range volcanoes: Implications for seismic detection of hazardous mass movements. Bulletin of the Seismological Society of America, Vol. 84, pp. 1925-1939.

Outerbridge, K. C., Dixon, T. H., Schwartz, S. Y., Walter, J. I., Protti, M., Gonzalez, V., ... & Rabbel, W. (2010). A tremor and slip event on the Cocos‐Caribbean subduction zone as measured by a global positioning system (GPS) and seismic network on the Nicoya Peninsula, Costa Rica. Journal of Geophysical Research: Solid Earth, Vol. 115, B10408.

Peng, Z., Vidale, J. E., Wech, A. G., Nadeau, R. M., & Creager, K. C. (2009). Remote triggering of tremor along the San Andreas Fault in central California. Journal of Geophysical Research: Solid Earth, Vol. 114, B00A06.

Provost, F., Hibert, C., & Malet, J. P. (2017). Automatic classification of endogenous landslide seismicity using the Random Forest supervised classifier. Geophysical Research Letters, Vol. 44, pp. 113-120.

Rodriguez, I. V. (2011). Automatic time-picking of microseismic data combining STA/LTA and the stationary discrete wavelet transform. CSPGCSEGCWLS Convention[C], pp. 1-4.

Ross, Z. E., & Ben-Zion, Y. (2014). An earthquake detection algorithm with pseudo-probabilities of multiple indicators. Geophysical Journal International, Vol. 197, pp. 458-463.

Sasaki, Y. (2007). The truth of the F-measure. Teach Tutor mater, Vol. 1, pp. 1-5.

Schneider, D., Bartelt, P., Caplan‐Auerbach, J., Christen, M., Huggel, C., & McArdell, B. W. (2010). Insights into rock‐ice avalanche dynamics by combined analysis of seismic recordings and a numerical avalanche model. Journal of Geophysical Research: Earth Surface, Vol. 115, F04026.

Schimmel, A., & Hübl, J. (2016). Automatic detection of debris flows and debris floods based on a combination of infrasound and seismic signals. Landslides, Vol. 13, pp. 1181-1196.

Sebastiani, F. (2002). Machine learning in automated text categorization. ACM computing surveys (CSUR), Vol. 34, pp. 1-47.

Seno, T. (1977). The instantaneous rotation vector of the Philippine Sea plate relative to the Eurasian plate. Tectonophysics, Vol. 42, pp. 209-226.

Shelly, D. R., Beroza, G. C., & Ide, S. (2007). Non-volcanic tremor and low-frequency earthquake swarms. Nature, Vol. 446, pp. 305.

Shimshoni, Y., & Intrator, N. (1998). Classification of seismic signals by integrating ensembles of neural networks. IEEE Transactions on Signal Processing, Vol. 46, pp. 1194-1201.

Shin, T. C. (1993). The calculation of local magnitude from the simulated Wood-Anderson seismograms of the short-period seismograms in the Taiwan area. Terrestrial, Atmospheric and Oceanic Sciences, Vol. 4, pp. 155-170.

Sole’vev, S. L. (1965). Seismicity of Sakalin. Bull. Earthq. Res. Inst. Tokyo Univ., Vol. 43, pp. 95-102.

Sukhovich, A., Irisson, J. O., Simons, F. J., Ogé, A., Hello, Y., Deschamps, A., & Nolet, G. (2011). Automatic discrimination of underwater acoustic signals generated by teleseismic P‐waves: A probabilistic approach. Geophysical Research Letters, Vol. 38, L18605.

Suriñach, E., Vilajosana, I., Khazaradze, G., Biescas, B., Furdada, G., & Vilaplana, J. M. (2005). Seismic detection and characterization of landslides and other mass movements. Natural Hazards and Earth System Science, Vol. 5, pp. 791-798.

Suwa, H., Mizuno, T., & Ishii, T. (2010). Prediction of a landslide and analysis of slide motion with reference to the 2004 Ohto slide in Nara, Japan. Geomorphology, Vol. 124, pp. 157-163.

Trnkoczy, A. (2002). Topic Understanding and parameter setting of STA/LTA trigger algorithm. IASPEI New Manual of Seismological Observatory Practice, vol. 2, GeoForschungsZentrum Potsdam, Ch. IS 8.1, pp. 1–19.

Tsumura, K. (1967). Determination of earthquake magnitude from total duration of oscillation. Bull. Earthquake Res. Inst. Univ. Tokyo, Vol. 45, pp. 7-18.

Mather, P., & Tso, B. (2016). Classification methods for remotely sensed data. Taylor and Francis Inc, New York.

Wang, H. P., Huang, Y. H., Yeh, M. L, Fang, Y. M., Li, B. C., Chou, T. L., Yin, S.Y. (2009). Typhoon Morokot landslides observation record. Chinese soil and water conservation society. Vol. 40, pp. 311-328. (in Chinese)

Wech, A. G., & Creager, K. C. (2008). Automated detection and location of Cascadia tremor. Geophysical Research Letters, Vol. 35, L20302.

Weaver, C. S., Norris, R. D., & Jonientz-Trisler, C. (1990). Results of Seismological Monitoring in the Cascade Range, 1962-1989: Earthquakes, eruptions, avalanches and other curiosities. Geosci. Can. Vol. 17, pp. 158-162.

Withers, M., Aster, R., Young, C., Beiriger, J., Harris, M., Moore, S., & Trujillo, J. (1998). A comparison of select trigger algorithms for automated global seismic phase and event detection. Bulletin of the Seismological Society of America, Vol. 88, pp. 95-106.

Wu, C. H., Chen, S. C., & Chou, H. T. (2011). Geomorphologic characteristics of catastrophic landslides during typhoon Morakot in the Kaoping Watershed, Taiwan. Engineering Geology, Vol. 123, pp. 13-21.

Wu, Y. M., Chang, C. H., Zhao, L., Shyu, J. B. H., Chen, Y. G., Sieh, K., & Avouac, J. P. (2007). Seismic tomography of Taiwan: Improved constraints from a dense network of strong motion stations. Journal of Geophysical Research: Solid Earth, Vol. 112, B08312.

Yamada, M., Matsushi, Y., Chigira, M., & Mori, J. (2012). Seismic recordings of landslides caused by Typhoon Talas (2011), Japan. Geophysical Research Letters, Vol. 39, L13301.

論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2018-08-27起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2018-08-27起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw