請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72070完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林美聆(Meei-Ling Lin) | |
| dc.contributor.author | Hsiao-Cheng Chuang | en |
| dc.contributor.author | 莊效丞 | zh_TW |
| dc.date.accessioned | 2021-06-17T06:21:49Z | - |
| dc.date.available | 2023-08-21 | |
| dc.date.copyright | 2018-08-21 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-08-18 | |
| dc.identifier.citation | [1] Arias, A. (1970). MEASURE OF EARTHQUAKE INTENSITY. Massachusetts Inst. of Tech., Cambridge. Univ. of Chile, Santiago de Chile.
[2] Bonamassa, O., & Vidale, J. E. (1991). Directional site resonances observed from aftershocks of the 18 October 1989 Loma Prieta earthquake. Bulletin of the Seismological Society of America, 81(5), 1945-1957. [3] Bouchon, M., & Barker, J. S. (1996). Seismic response of a hill: the example of Tarzana, California. Bulletin of the Seismological Society of America, 86(1A), 66-72 [4] Bray, J. D., & Rodriguez-Marek, A. (2004). Characterization of forward-directivity ground motions in the near-fault region. Soil dynamics and earthquake engineering, 24(11), 815-828. [5] Chang, C. P., Chang, T. Y., Angelier, J., Kao, H., Lee, J. C., & Yu, S. B. (2003). Strain and stress field in Taiwan oblique convergent system: constraints from GPS observation and tectonic data. Earth and Planetary Science Letters, 214(1-2), 115-127. [6] Cultrera, G., Rovelli, A., Mele, G., Azzara, R., Caserta, A., & Marra, F. (2003). Azimuth‐dependent amplification of weak and strong ground motions within a fault zone (Nocera Umbra, central Italy). Journal of Geophysical Research: Solid Earth, 108(B3). [7] Cheng, C. T., Chiou, S. J., Lee, C. T., & Tsai, Y. B. (2007). Study on probabilistic seismic hazard maps of Taiwan after Chi-Chi earthquake. Journal of GeoEngineering, 2(1), 19-28. [8] Cochran, E. S., & Kroll, K. A. (2015). Stress-and structure-controlled anisotropy in a region of complex faulting—Yuha Desert, California. Geophysical Journal International, 202(2), 1109-1121. [9] Diah Lane (2016), Structure Geology - Brittle Faulting, https://slideplayer.com /slide/7838449/ [10] Di Giulio, G., Azzara, R. M., Cultrera, G., Giammarinaro, M. S., Vallone, P., & Rovelli, A. (2005). Effect of local geology on ground motion in the city of Palermo, Italy, as inferred from aftershocks of the 6 September 2002 M W 5.9 earthquake. Bulletin of the Seismological Society of America, 95(6), 2328-2341. [11] Del Gaudio, V., Pierri, P., & Rajabi, A. M. (2015). An Approach to Identify Site Response Directivity of Accelerometer Sites and Application to the Iranian Area. Pure and Applied Geophysics, 172(6), 1471-1490. [12] George Seif (2018). https://medium.com/swlh/ill-tell-you-why-deep-learning-is-so-popular-and-in-demand-5aca72628780 [13] Hung, J. H., Ma, K. F., Wang, C. Y., Ito, H., Lin, W., & Yeh, E. C. (2009). Subsurface structure, physical properties, fault-zone characteristics and stress state in scientific drill holes of Taiwan Chelungpu Fault Drilling Project. Tectonophysics, 466(3-4), 307-321. [14] Hara, K., Vemulapalli, R., & Chellappa, R. (2017). Designing deep convolutional neural networks for continuous object orientation estimation. arXiv preprint arXiv:1702.01499. [15] Institute of Earth Sciences, Academia Sinica, Taiwan (1996): Broadband Array in Taiwan for Seismology. Institute of Earth Sciences, Academia Sinica, Taiwan. Other/Seismic Network. doi:10.7914/SN/TW [16] Li, Y. G., & Leary, P. C. (1990). Fault zone trapped seismic waves. Bulletin of the Seismological Society of America, 80(5), 1245-1271. [17] Lund, B., & Slunga, R. (1999). Stress tensor inversion using detailed microearthquake information and stability constraints: Application to Ölfus in southwest Iceland. Journal of Geophysical Research: Solid Earth, 104(B7), 14947-14964. [18] Lin, P. S., C. T. Lee（2008）Ground-Motion Attenuation Relationships for Subduction-Zone Earthquakes in Northeastern Taiwan, Bull. Seismol. Soc. Am., 98, pp.220-240 [19] Leyton, F., Ruiz, J., Campos, J., & Kausel, E. (2009). Intraplate and interplate earthquakes in Chilean subduction zone: A theoretical and observational comparison. Physics of the Earth and Planetary interiors, 175(1-2), 37-46. [20] Madelinschiappa (2017), Man vs machine: comparing artificial and biological neural networks, https://news.sophos.com/en-us/2017/09/21/man-vs-machine-comparing-artificial-and-biological-neural-networks/ [21] Michael, A. J. (1984). Determination of stress from slip data: faults and folds. Journal of Geophysical Research: Solid Earth, 89(B13), 11517-11526. [22] Michael, A. J. (1987). Use of focal mechanisms to determine stress: a control study. Journal of Geophysical Research: Solid Earth, 92(B1), 357-368. [23] Mandl, G. (1999). Faulting in brittle rocks: an introduction to the mechanics of tectonic faults. Springer Science & Business Media. [24] Nakamura, Y. (1989). A method for dynamic characteristics estimation of subsurface using microtremor on the ground surface. QR Railway Tech. Res. Inst., 30(1), 25-33. [25] Pischiutta, M., Rovelli, A., Vannoli, P., & Calderoni, G. (2011, August). Recurrence of horizontal amplification at rock sites: a test using H/V based ground motion prediction equations. In 4th IASPEI/IAEE International Symposium: Effects of Surface Geology on Seismic Motion. [26] Pischiutta, M., Salvini, F., Fletcher, J., Rovelli, A., & Ben-Zion, Y. (2012). Horizontal polarization of ground motion in the Hayward fault zone at Fremont, California: dominant fault-high-angle polarization and fault-induced cracks. Geophysical Journal International, 188(3), 1255-1272. [27] Pischiutta, M., Rovelli, A., Salvini, F., Di Giulio, G., & Ben-Zion, Y. (2013). Directional resonance variations across the Pernicana Fault, Mt Etna, in relation to brittle deformation fields. Geophysical Journal International, 193(2), 986-996. Pischiutta, M., Fondriest, M., Demurtas, M., Magnoni, F., Di Toro, G., & Rovelli, A. (2017). Structural control on the directional amplification of seismic noise (Campo Imperatore, central Italy). Earth and Planetary Science Letters, 471, 10-18. [28] Rigano, R., Cara, F., Lombardo, G., & Rovelli, A. (2008). Evidence for ground motion polarization on fault zones of Mount Etna volcano. Journal of Geophysical Research: Solid Earth, 113(B10). [29] Spearman’s rank correlation coefficient. In Wikipedia, the free encyclopedia., from https://en.wikipedia.org/wiki/Spearman%27s_rank_correlation_coefficient [30] Somerville, P. G. (2002, April). Characterizing near fault ground motion for the design and evaluation of bridges. In Proceedings of the Third National Seismic Conference and Workshop on Bridges and Highways (Vol. 137148). MCEER Buttalo. [31] Van der Pluijm, B.A., and S. Marshak, 1997, Earth Structure, Introduction to Structural Geology and Tectonics, W.W. Norton & Company, Inc, ISBN: 0-393-92467-X. [32] Vavryčuk, V. (2014). Iterative joint inversion for stress and fault orientations from focal mechanisms. Geophysical Journal International, 199(1), 69-77. [33] Wu, Y. M., Zhao, L., Chang, C. H., & Hsu, Y. J. (2008). Focal-mechanism determination in Taiwan by genetic algorithm. Bulletin of the Seismological Society of America, 98(2), 651-661. [34] Wu, Y. M., Hsu, Y. J., Chang, C. H., Teng, L. S. Y., & Nakamura, M. (2010). Temporal and spatial variation of stress field in Taiwan from 1991 to 2007: Insights from comprehensive first motion focal mechanism catalog. Earth and Planetary Science Letters, 298(3-4), 306-316. [35] Youngs, R. R., S. J. Chiou, W. J. Silva, J. R. Humphrey（1997）Strong Ground Motion Attenuation Relationships for Subduction Zone Earthquakes, Seism. Res. Lett., 68, pp.58-73 [36] Xu, Z., Schwartz, S. Y., & Lay, T. (1996). Seismic wave-field observations at a dense, small-aperture array located on a landslide in the Santa Cruz mountains, California. Bulletin of the Seismological Society of America, 86(3), 655-669. [37] 內政部營建署，「耐震設計規範及解說」(2011) [38] 林信亨. (2000). 地理資訊系統應用於土石流危險溪流危險度判定之硏究 (Doctoral dissertation, National Taiwan University Department of Civil Engineering). [39] 林裕翔. (2008). 土石流發生潛勢-區別分析的擬合與預測. 臺灣大學土木工程學研究所學位論文, 1-152. [40] 黃雋彥. (2009). 利用微地動量測探討台灣地區之場址效應, 國立中央大學地球物理研究所碩士論文. [41] 曾美綺. (2017). 地表地形對地震震波反應影響之數值模擬. 臺灣大學土木工程學研究所學位論文, 1-136. [42] 蘇育瑞. (1995). 地理資訊系統應用於花蓮地區土石流危險溪流判定之硏究 (Doctoral dissertation, National Taiwan University Department of Civil Engineering). [43] 謝寶珊, 林柏伸, 鄭錦桐, 李錫堤. (2014). 台灣地區隱沒帶地震愛氏震度地動預估式之建立與應用. 中興工程, (125), 33-43. [44] 洪如江（1997），「台灣地區工程地質分區分佈圖」，1997年修訂 | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72070 | - |
| dc.description.abstract | 在過去的研究中發現，地震波會在某些特定的條件或因素下，會呈現明顯的方向性，如:當地剪力波速的異質性(Bonamassa & Vidale, 1991)、山脊方向的放大現象(Spudich et al., 1996)、地層破裂帶的折射反應(Xu et al., 1996)和斷層附近震波的偏震現象(Lombardo, 2008)，這些造成地震波有方向性的因素對設定地震參數(GMPE, Ground Motion Prediction Equation)有深遠的影響，並間接影響到一般建築物耐震設計規範，現行的建築物耐震設計規範對近斷層效應只考慮垂直於斷層方向的放大現象，，而過去的研究發現地震波的方向並不會完全平行於斷層的垂直方向，因此規範對此現象還沒有完整的考量，本研究將針對近斷層場址內的測站進行地震波方向性的分析。
本研究目前蒐集了全臺灣104場地震事件以及基本之地質資料。造成近斷層地震波產生方向性的原因主要可以分成三類:震波偏振、剪力波速下降以及向破裂前進方向效應(forward directivity)，另外地震的來源也有可能會影響地震波的方向性，根據這些因素選出地震、斷層和測站相關之因子，並利用統計以及類神經網路的方法探討各因子對地震波方向性之影響。本研究採用愛氏強度(Arias Intensity)來評估地震波之方向性，並嘗試利用類神經網路來預測在各種近斷層條件下的愛氏強度分佈情形。 總結統計方法的結果，主要的影響因子包括場址和震央之距離、地震震源深度、隱沒帶地震類別、場址地層主頻。在類神經網路訓練階段將重要因子一一抽離，確實會造成類神經網路的表現受到影響。而由類神經網路之權重的結果發現，現地應力狀態、斷層走向以及斷層滑動機制皆為重要之影響因子。 由本研究採用之類神經網路之訓練結果顯示，大部分近斷層場址之地震波會被歸類無方向性，且對於沒有方向性之地震波資料可以有八成以上之預測準確率，但對於有方向性之地震波資料卻只有四成的準確率。雖然在真實情況下無方向資料確實佔大多數，但有方向性資料之準確率無法再提升，可能顯示本研究所採用之參數還不足夠描述震波之方向性。 | zh_TW |
| dc.description.abstract | Based on previous research, ground motion can be amplified in certain direction and show with significant anisotropy. The causes still remain unclear, and different researchers have attributed this phenomenon to several factors, including topographic effect, local geological heterogeneities, wave polarization, wave trapped in fault zone and etc. This phenomenon might have severe impacts on buildings that cause damages, especially in the near-fault area. However, the current seismic design code focus on the perpendicular direction of fault strike only, which is not suitable enough for real situation. The objective of this study will focus on seismic wave directivity in near-fault zone.
A total of 104 earthquake events with basic geological data were collected. Causative factors were selected based on previous research. There are three main causes considered of free field stations, included wave polarization, anisotropic stiffness and forward directivity. The source of earthquake can possibly affect the seismic wave directivity. Data of influence factors were collected accordingly, and Arias Intensity is used to describe the directivity of seismic wave. The deep learning technique was applied to predict Arias Intensity distribution with the given parameters. This research used TensorFlow as the main deep learning tool. The results of neural network shows that, in most cases, there were no obvious directivity in the near-fault site, and the accuracy of non-directional data was higher than the accuracy of directional data. Although, in real situation, non-directional data is the majority, the low accuracy of directional data might suggest the parameters used in this research is not enough to describe seismic wave directivity. The results suggested that the distance between site and epicenter, focal depth and subduction earthquake are all important factors. In addition, neural network takes in-situ stress, fault strike and fault slip type as main factors. This result will be discussed in this paper. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T06:21:49Z (GMT). No. of bitstreams: 1 ntu-107-R05521110-1.pdf: 10806945 bytes, checksum: c32068f80e823f04ed23f8f1e4ed42e4 (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 誌謝 i
中文摘要 ii Abstract iii 目錄 iv 表目錄 viii 圖目錄 x 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機與目的 1 1.3 研究方法與內容 2 第二章 文獻回顧 5 2.1 震波傳遞原理 5 2.2 斷層區地震波方向性成因 6 2.2.1 震波的偏振現象 6 2.2.2 剪力波速下降 7 2.2.3 向破裂前進方向效應Forward Directivity 7 2.2.4 其他影響因素 8 2.3 機器學習簡介 9 2.4 機器學習模型設計方法 11 2.4.1 神經元運算模式 12 2.4.2 建立類神經網路(Neural Network) 14 2.4.3 選擇評估的方式 14 2.4.4 訓練類神經網路模型 15 2.5 大地現地應力反算Stress Inversion 16 2.5.1 Stress Inversion反算法簡介 17 2.5.2 Stress Inversion運算和推導 18 2.5.3 Stress Inversion之限制 20 2.6 輸出資料方向性之判定 21 2.6.1 愛氏強度簡介 21 2.6.2 愛氏強度之方向性 22 第三章 研究區域與資料庫之介紹 34 3.1 研究資料之選取 34 3.2 研究區域概況 35 3.3 基本資料庫之架構與建立 36 3.4 影響因子之選定 38 3.5 影響因子之求取 40 3.5.1 現地應力狀態 40 3.5.2 地震類型 41 3.5.3 場址與斷層關係 43 3.5.4 場址之地質條件 44 3.6 輸入資料前處理 44 3.6.1 資料特徵值縮放(Feature Scaling) 45 3.6.2 類別資料的處理 46 3.6.3 方向性資料 46 3.6.4 缺失值處理 47 3.7 衍生資料庫之建立 47 第四章 影響因子特性與類神經網路之建構 87 4.1 資料庫因子獨立性檢定 87 4.2 資料庫因子分佈特性 89 4.3 資料庫因子之影響性檢定 90 4.3.1 地震波方向性之影響因素 90 4.3.2 卡方檢定 91 4.3.3 地震波主方向角之影響因素 92 4.4 深度學習架構簡介 92 4.5 類神經網路架構之建立 93 4.5.1 迴歸式模型 93 4.5.2 多元分類式模型 94 4.6 動態參數設定 96 4.6.1 梯度下降法 96 4.6.2 丟棄法Dropout 97 4.6.3 資料批次處理 98 4.7 影響因子之討論 98 第五章 類神經網路輸出成果 125 5.1 準確度設定 125 5.2 類神經網路預測結果 127 5.2.1 Softmax Function模型之輸出結果 127 5.2.2 回歸式模型以及Sigmoid Function模型之結果 128 5.3 預測正確資料分布情形 129 5.4 實例驗證 129 5.5 統計結果和類神經網路權重值 130 5.5.1 相關係數重要因子對類神經網路之影響 130 5.5.2 類神經網路之權重值 131 5.5.3 類神經網路和統計結果之綜合比較 133 第六章 結論與建議 154 6.1 結論 154 6.2 建議 156 參考文獻 …………………………………………………………………………158 附錄A …………………………………………………………………………159 附錄B …………………………………………………………………………220 | |
| dc.language.iso | zh-TW | |
| dc.subject | 愛氏強度 | zh_TW |
| dc.subject | 向前破裂前進方向效應 | zh_TW |
| dc.subject | 地震波偏振現象 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | Stress Inversion | zh_TW |
| dc.subject | Stress Inversion | en |
| dc.subject | Arias Intensity | en |
| dc.subject | Forward Directivity | en |
| dc.subject | Shear Wave Splitting | en |
| dc.subject | Deep Learning | en |
| dc.title | 以類神經網路觀察近斷層之地震波方向性 | zh_TW |
| dc.title | The Observation of Seismic Wave Directivity in Near-Fault Zone with Deep Neural Network | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳天健(Tien-Chein Chen),王國隆(Kuo-Lung Wang) | |
| dc.subject.keyword | 愛氏強度,向前破裂前進方向效應,地震波偏振現象,深度學習,Stress Inversion, | zh_TW |
| dc.subject.keyword | Arias Intensity,Forward Directivity,Shear Wave Splitting,Deep Learning,Stress Inversion, | en |
| dc.relation.page | 237 | |
| dc.identifier.doi | 10.6342/NTU201803340 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2018-08-18 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-107-1.pdf 未授權公開取用 | 10.55 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。