大規模崩塌產生的地表振動訊號可被鄰近地震儀記錄下來，且與地震事件的訊號在波形特徵及頻率特性上有顯著的差異，因此近年來地動訊號分析被廣泛用於邊坡塊體滑動的研究。從連續地動記錄中判別出崩塌訊號以往多是仰賴人工判讀，不僅過於曠日廢時，判釋結果也深受分析人員的經驗及主觀判斷影響。將機器學習技術應用到地動訊號的自動判釋，可更加快速且客觀的找出崩塌事件的時間點，大量減少在判釋崩塌事件時的時間及人力成本。
本研究利用前人文獻中記載的33場崩塌事件發生時間點，分析中研院台灣寬頻地震網的11個寬頻測站記錄，以挑選出共214筆的崩塌地動訊號作為分類模型的訓練樣本。另外，從中央氣象局公布的台灣區域地震時間中挑選出同等數量的地震事件及噪訊地動訊號，同樣加入作為訓練樣本。藉由計算不同類型地動事件在時間域及頻率域上的訊號特徵值，配合機器學習演算法，建立出連續地震記錄的自動分類模型。經測試22種機器學習演算法後，其中隨機森林演算法(Random Forest)獲得之F1-Score最高(87.94 %)，有最為穩定之分類結果。本研究建立之分類模型也應用於自動分類2009年莫拉克颱風期間之連續地動紀錄，其結果顯示自動分類模型能成功辨識出由大規模崩塌所產生之地動訊號。

The seismic signals generated by landslides can be recorded by nearby seismometers, and there were significant differences in waveform and frequency characteristics from earthquake signals. Applying machine learning methods to the automatic identification of seismic signals could get the time points of the landslides more quickly and objectively. This study used the time information of 33 known landslide events reported in the previous literature and to the seismic records of the Broadband Array in Taiwan for Seismology (BATS) to obtain 214 signals from landslides, 214 signals from earthquakes and 214 signals from noise. Totally 642 seismic signals are used as training samples. After calculating the signal features of different types of seismic events in the time domain and frequency domain, the automatic classification model of seismic records was established based on Random Forest algorithm with the accuracy of 91.3%. The results of model testing show that the signal features used in this study could effectively distinguish different types of seismic signals.

吳昱杰 (2018)。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。國立成功大學地球科學系碩士論文，台南市。 取自https://hdl.handle.net/11296/37nxpt
李錫堤, 董家鈞, & 林銘郎. (2009). 小林村災變之地質背景探討. In: 地工技術.
張志新, 王俞婷, 傅鏸漩, 林又青, 張駿暉, 劉哲欣, 呂喬茵, 吳啟瑞, & 蘇元風. (2015). 2015 年蘇迪勒颱風災害調查彙整報告. 新北市: 國家災害防救科技中心.
陳樹群, 陳冠翰, & 吳俊鋐. (2014). 地下水引發自由端順向坡土體滑動特性分析. Journal of Chinese Soil and Water Conservation, 45(2), 110-118.
Benítez, M. C., Ramírez, J., Segura, J. C., Ibanez, J. M., Almendros, J., García-Yeguas, A., & Cortes, G. (2006). Continuous HMM-based seismic-event classification at Deception Island, Antarctica. IEEE Transactions on Geoscience and remote sensing, 45(1), 138-146.
Bernoulli, J. (1713). Ars conjectandi. Impensis Thurnisiorum, fratrum.
Breiman, L. (1996). Bagging predictors. Machine learning, 24(2), 123-140.
Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
Brodsky, E. E., Gordeev, E., & Kanamori, H. (2003). Landslide basal friction as measured by seismic waves. Geophysical Research Letters, 30(24).
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, 6, 19259.
Chao, W. A., Wu, Y. M., Zhao, L., Chen, H., Chen, Y. G., Chang, J. M., & Lin, C. M. (2017). A first near real-time seismology-based landquake monitoring system. Scientific reports, 7, 43510.
Chen, C. H., Chao, W. A., Wu, Y. M., Zhao, L., Chen, Y. G., Ho, W. Y., Lin, T. L., Kuo, K. H., & Chang, J. M. (2013). A seismological study of landquakes using a real-time broad-band seismic network. Geophysical Journal International, 194(2), 885-898.
Cortés, G., Benitez, M. C., García, L., Álvarez, I., & Ibanez, J. M. (2015). A comparative study of dimensionality reduction algorithms applied to volcano-seismic signals. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(1), 253-263.
Dahlen, F. (1993). Single-force representation of shallow landslide sources. Bulletin of the Seismological Society of America, 83(1), 130-143.
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, 116(F4).
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, 93(1), 215-223.
Eissler, H. K., & Kanamori, H. (1987). A single‐force model for the 1975 Kalapana, Hawaii, earthquake. Journal of Geophysical Research: Solid Earth, 92(B6), 4827-4836.
Esposito, A., 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, 96(4A), 1230-1240.
Huang, C. J., Yin, H. Y., Chen, C. Y., Yeh, C. H., & Wang, C. L. (2007). Ground vibrations produced by rock motions and debris flows. Journal of Geophysical Research: Earth Surface, 112(F2).
Institute of Earth Sciences, Academia Sinica, Taiwan. (1996). Broadband array in Taiwan for seismology.
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, 87(B7), 5422-5432.
Kao, H., Kan, C. W., Chen, R. Y., Chang, C. H., Rosenberger, A., Shin, T. C., Leu, P. L., Kuo, K. W., & Liang, W. T. (2012). Locating, monitoring, and characterizing typhoon-linduced landslides with real-time seismic signals. Landslides, 9(4), 557-563.
Kao, H., Shan, S. J., Dragert, H., Rogers, G., Cassidy, J. F., Wang, K., James, T. S., & Ramachandran, K. (2006). Spatial‐temporal patterns of seismic tremors in northern Cascadia. Journal of Geophysical Research: Solid Earth, 111(B3).
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, 34(16).
Kohavi, R., & Provost, F. (1998). Confusion matrix. Machine learning, 30(2-3), 271-274.
Kortström, J., Uski, M., & Tiira, T. (2016). Automatic classification of seismic events within a regional seismograph network. Computers & Geosciences, 87, 22-30.
Lin, C., Kumagai, H., Ando, M., & Shin, T. (2010). Detection of landslides and submarine slumps using broadband seismic networks. Geophysical Research Letters, 37(22).
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, 43(13), 6960-6967.
Parihar, D., Ghosh, R., Akula, A., Kumar, S., & Sardana, H. (2018). Machine Learning Based Comparative Analysis for the Classification of Earthquake Signals. Paper presented at the Proceedings of the International Conference on Computing and Communication Systems.
Provost, F., Hibert, C., & Malet, J. P. (2017). Automatic classification of endogenous landslide seismicity using the Random Forest supervised classifier. Geophysical Research Letters, 44(1), 113-120.
Provost, F., Malet, J.-P., Hibert, C., Abanco Martínez de Arenzana, C., & Hurlimann Ziegler, M. (2018). Towards a standard typology of endogenous landslide seismic sources. Earth surface dynamics, 6(4), 1059-1088.
Quinlan, J. R. (1986). Induction of decision trees. Machine learning, 1(1), 81-106.
Quinlan, J. R. (1987). Simplifying decision trees. International journal of man-machine studies, 27(3), 221-234.
Ross, Z. E., & Ben-Zion, Y. (2014). An earthquake detection algorithm with pseudo-probabilities of multiple indicators. Geophysical Journal International, 197(1), 458-463.
Scarpetta, S., Giudicepietro, F., Ezin, E. C., Petrosino, S., Del Pezzo, E., Martini, M., & Marinaro, M. (2005). Automatic classification of seismic signals at Mt. Vesuvius volcano, Italy, using neural networks. Bulletin of the Seismological Society of America, 95(1), 185-196.
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, 115(F4).
Schneider, J. (1997). Cross validation. A Locally Weighted Learning Tutorial Using Vizier, 1.
Suriñach, E., Vilajosana, I., Khazaradze, G., Biescas, B., Furdada, G., & Vilaplana, J. (2005). Seismic detection and characterization of landslides and other mass movements. Natural Hazards and Earth System Science, 5(6), 791-798.
Tian, Y., Qi, H., & Wang, X. (2002). Target detection and classification using seismic signal processing in unattended ground sensor systems. In IEEE International Conference on Acoustics Speech and Signal Processing (Vol. 4, pp. 4172-4172). IEEE; 1999.
Wech, A. G., & Creager, K. C. (2008). Automated detection and location of Cascadia tremor. Geophysical Research Letters, 35(20).
Welch, P. (1967). The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Transactions on audio and electroacoustics, 15(2), 70-73.
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, 123(1-2), 13-21.
Yeh, K. C., & Liu, C. H. (1982). Radio wave scintillations in the ionosphere. Proceedings of the IEEE, 70(4), 324-360.