臺灣位處環太平洋地震帶的海島環境，生活周遭常面臨颱洪侵襲、坡地坍滑、地震等天然災害。面對上述致災因子，甚而複合性災害發生所帶來的威脅，將造成政府及人民財產損失並危害生命安全。臺北市為臺灣政經首都且人口密度高，在既有之都市防災作業中，考慮複合型災害或極端性氣候下之災害防救作業，貴為當前急需處理的首要議題。本文針對臺北市面臨強降雨量與周圍潛勢斷層，擬定四十八個複合性災害情境，透過水文、淹水分析成果與TELES (Taiwan Earthquake Loss Estimation System)地震潛勢分析理論，進行臺北市各行政區的複合性災害潛勢圖層套疊與避難人數評估。分析結果依資料呈現方式可區分為災前靜態的災害潛勢圖與收容能量評估表，係以潛勢圖層進行地理資訊系统的空間與數據套疊，並結合市府目前規劃之臨時避難場所進行收容能量的評估；在災時動態的避難人數推估曲線，為藉由資料探勘技術建構之模式預測成果繪製而得，可即時推算臺北市各行政區遭受複合性災害時的避難人數與容受力。文末則提出結論與建議，期供相關單位作為災害防救決策資訊之依據。

Located in the circum-Pacific seismic zone, Taiwan constantly encounters the threats of natural disasters such as typhoons, floods, landslides, and earthquakes. The threats posed by the disaster-inducing factors mentioned above as well as compound disasters pose the risk of property loss to the government and the people and severely endanger safety. Because Taipei City is both the political and economic capital of Taiwan and has a high population density, it must consider disaster prevention and relief operations for compound disasters and extreme climates in addition to existing metropolitan disaster prevention operations. This is a primary issue that currently demands immediate solutions. The present study formulated 48 compound-disaster scenarios based on the threats of heavy rainfall and surrounding potential faults. Hydrology and flood analysis theories and the Taiwan earthquake loss estimation system (TELES) were employed to assess the potential for compound disasters and the number of subsequent displaced people in the various administrative districts of Taipei City. The resulting disaster potential diagrams were integrated to conduct GIS (Geographic Information System) spatial and data analysis, and temporary refuges or shelters currently planned by the city government were compared. Furthermore, a dynamic assessment curve for the number of displaced people during a multi-disasters was plotted using data mining techniques. Subsequently, a cross table was obtained and employed to predict the number of refugees in the various administrative districts of Taipei City. Finally, a conclusion and recommendations were provided for relevant departments that can be used as a basis for information when making disaster prevention and relief decisions concerning earthquakes and flooding simultaneously.

參考文獻
[1] ATC (Applied Technology Council), Seismic Evalutaion and Retrofit of Concrete Buildings, Concrete Buildings, Report No. SSC 96-01, Vol. 1, 1996.
[2] L. Breiman, J. Friedman, C.J. Stone, R.A. Olshen, Classification and regression trees, Chapman & Hall/CRC, New York, 1984.
[3] J. Chen, Q. Jin, H. Wang, S. Zhao, A Risk Assessment Model of Flood Based on Information Diffusion Method and BP Neural Network, 2012.
[4] J.-S. Chou, K.-H. Yang, M.-Y. Cheng, W.-T. Tu, Identification and assessment of heavy rainfall–induced disaster potentials in Taipei City, Natural Hazards 66 (2) (2013) 167-190.
[5] Columbia University and The World Bank produce new report, Natural disaster hotspots: A global risk analysis, New York, 2005.
[6] Council of Agriculture. Executive Yuan, Soil and Water Conservation Bureau, 2010.
[7] S. Džeroski, J.S. Institute, S. Ljubljana, Towards a general framework for data mining., Knowledge Discovery in Inductive Databases, Vol. 4747, 2007, pp. 259-300.
[8] FEMA, Earthquake Loss Estimation Methodology- HAZUS97, Technical Manual, Vol. 1, 1997.
[9] M. Gad-el-Hak, Large-Scale Disasters, Cambridge University Press, 2008.
[10] D. Guha-Sapir, F. Vos, R. Below, Annual Disaster Statistical Review 2011, Centre for Research on the Epidemiology of Disasters Institute of Health and Society (IRSS)-Universite catholique de Louvain, Belgium, 2012.
[11] M. Hashemi, AliAsgharAlesheikh, A GIS-based earthquake damage assessment and settlement methodology, Soil Dynamics and Earthquake Engineering 31 (2011) 1607-1617.
[12] S.S. Haykin, Neural networks: a comprehensive foundation, Prentice Hall, 1999.
[13] S. Ikeda, An Integrated Risk Analysis Framework for Emerging Disaster Risks: Toward a better risk management of flood disaster in urban communities, in: S. Ikeda, T. Fukuzono, T. Sato (Eds.), A better integrated management of disaster risks: Toward resilient society to emerging disaster risks in mega-cities, Japan: Terrapub and Nied, 2006, pp. 1–21.
[14] E.U. Kucuksille, R. Selbaş, A. Şencan, Data mining techniques for thermophysical properties of refrigerants, Energy Conversion and Management 50 (2) (2009) 399-412.
[15] C.A. K., Dynamics of Structures, 3rd Ed., Prentice Hall 2007.
[16] R. Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection, Proceedings of the 14th international joint conference on Artificial intelligence, Vol. 2, Morgan Kaufmann Publishers Inc., Montreal, Quebec, Canada, 1995, pp. 1137-1143.
[17] J.-S. Lai, F. Tsai, Verification and Risk Assessment for Landslides in the Shimen Reservoir Watershed of Taiwan Using Spatial Analysis and Data Mining, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012XXII ISPRS Congress, Vol. Volume XXXIX-B2, Melbourne, Australia, 2012.
[18] T.Y. Li, Y. Chen, M. Yang, X.W. Mu, Data mining model based on improved fuzzy k-means algorithm and neural network algorithm, Dalian Haishi Daxue Xuebao/Journal of Dalian Maritime University 34 (4) (2008) 37-40, 44.
[19] G.F. Lin, Upgrading potential inundation maps of Tamsui River, Taipei city, Taipei county, Taoyuan county, and Keelung city, Water Resources Agency, Ministry of Economic Affairs, 2010.
[20] D. Liu, Y. Yuan, S. Liao, Artificial neural network vs. nonlinear regression for gold content estimation in pyrometallurgy, Expert Systems with Applications 36 (7) (2009) 10397-10400.
[21] W.-Y. Loh, Y.-S. Shih, Split Selection Methods for Classification Trees, Statistica Sinica 7 (1997) 815-840.
[22] M. Manske, Tropical Cyclones, 1945–2006. Data from the Joint Typhoon Warning Center and the U.S. National Ocean, 2011.
[23] R.E. Neapolitan, Learning Bayesian Networks, Northeastern Illinois University, Chicago, Illinois, 2003.
[24] T.T. Nguyen, M. Coulier, A preliminary analysis of disaster and poverty data in Quang Binh province, Viet Nam, Ministry of Agriculture and Rural Development and the United Nations Development Programme, 2012.
[25] T. Orenstein, Z. Kohavi, I. Pomeranz, An optimal algorithm for cycle breaking in directed graphs, Journal of Electronic Testing 7 (1-2) (1995) 71-81.
[26] S.-H. Peng, M.-J. Shieh, S.-Y. Fan, Potential Hazard Map for Disaster Prevention Using GIS-Based Linear Combination Approach and Analytic Hierarchy Method, Journal of Geographic Information System 4 (2012) 403-411.
[27] B.D. Pitt, D.S. Kirschen, Application of data mining techniques to load profiling, IEEE Power Industry Computer Applications Conference (1999) 131-136.
[28] P. Refaeilzadeh, L. Tang, H. Liu, Encyclopedia of Database Systems, 2009.
[29] R.J. Roiger, M.W. Geatz, 資料探勘 Data Mining -A Tutorial-Based Primer, 臺灣培生教育出版：臺灣東華發行, 臺北市, 2003.
[30] S.L. Salzberg, On comparing classifiers: Pitfalls to avoid and a recommended approach, Data Mining and Knowledge Discovery 1 (3) (1997) 317-328.
[31] B. Samanta, G.L. Bird, M. Kuijpers, R.A. Zimmerman, G.P. Jarvik, G. Wernovsky, R.R. Clancy, D.J. Licht, J.W. Gaynor, C. Nataraj, Prediction of periventricular leukomalacia. Part I: Selection of hemodynamic features using logistic regression and decision tree algorithms, Artificial Intelligence in Medicine 46 (3) (2009) 201-215.
[32] L.J. Scheetz, J. Zhang, J. Kolassa, Classification tree modeling to identify severe and moderate vehicular injuries in young and middle-aged adults, Artificial Intelligence in Medicine 45 (1) (2009) 1-10.
[33] G. Shmueli, N.R. Patel, P.C. Bruce, Data Mining for Business Intelligence, New Jersey, 2007.
[34] SPSS, Clementine 12.0 Algorithms Guide SPSS, 2007.
[35] Taipei City Disaster Prevention and Rescue Information, Disaster Prevention and Protection Plan, 2013.
[36] G.K.F. Tso, K.K.W. Yau, Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks, Energy 32 (9) (2007) 1761-1768.
[37] United States Geological Survey, Pacific Ring of Fire, 2004.
[38] D.L. Wells, K.J. Coppersmith, New Empirical Relationships among Magnitude, Reupture Length, Rupture Width, Rupture Area, and Surface Displacement, Bulletin of the Seismological Society of America 84 (1994) 974-1002.
[39] Y.-M. Wu, J.-H. Chang, C.-C. Chen, Near realtime prediction of PGV map and preliminary damage by using seismic rapid reporting system., Central Weather Bureau-Seismological Center, 2002.
[40] A. Yezioro, B. Dong, F. Leite, An applied artificial intelligence approach towards assessing building performance simulation tools, Energy and Buildings 40 (4) (2008) 612-620.
[41] L. Zheng, C. Shen, L. Tang, T. Li, S. Luis, S.-C. Chen, Applying Data Mining Techniques to Address Disaster Information Management Challenges on Mobile Devices, San Diego, California, USA., 2011.
[42] 丁一賢, 陳牧言, 資料探勘, 滄海書局, 臺中市, 2005.
[43] 丁亞中, 網格式GIS製圖模式建置之探討-以陽明山國家公園主題製圖為例, 第一屆數位地球國際研討會, Vol. 論文集C1-3 2003.
[44] 中央地質調查所, 山腳斷層條帶地質圖(北段), 2012.
[45] 中央地質調查所, 山腳斷層條帶地質圖(南段), 2012.
[46] 內政部營建署, 建築物耐震設計規範, 2011.
[47] 何明錦, 李威儀, 都市計畫防災規劃手冊彙編, 內政部建築研究所, 2000.
[48] 李振銘, 周瑞生, 鄭明淵, 林昌賢, 臺北市防救災地圖之規劃與製作, 100年臺北市深耕防災深耕計畫研討會, 2011.
[49] 周瑞生, 台北市災害防救深耕計畫(第1期)總結報告, in: 國立台灣科技大學生態與防災工程研究中心 (Ed.), 臺北市政府消防局, 2010.
[50] 周瑞生, 台北市災害防救深耕計畫(第2期)總結報告, in: 國立台灣科技大學生態與防災工程研究中心 (Ed.), 臺北市政府消防局, 2011.
[51] 周瑞生, 台北市災害防救深耕計畫(第3期)總結報告, in: 國立台灣科技大學生態與防災工程研究中心 (Ed.), 臺北市政府消防局, 2012.
[52] 香港規劃師學會汶川大地震關注組公共設施小組, 防減地震災害規劃與學校避難場所, Planning and Development 25 (2010).
[53] 國家災害防救科技中心, 颱洪災害規模研究計劃, 2011.
[54] 張云濤, 龔玲, 資料探勘原理與技術, 五南圖書出版股份有限公司, 2007.
[55] 許晃雄, 吳宜昭, 周佳, 陳正達, 陳永明, 盧孟明, 臺灣氣候變遷科學報告, 國家災害防救科技中心, 2011.
[56] 楊國鑫, 周瑞生, 鄭明淵, 涂莞庭, 雷泰雄, 蔡茂岳, 臺北市颱洪與坡地災害潛勢界定與風險分析, 營建管理季刊 一百年春季號 (86) (2011) 59-73.
[57] 經濟部中央地質調查所, 2010台灣活動斷層分布圖, 2011.
[58] 經濟部水利署, 水災危險潛勢區域疏散避難標準作業程序, 中華民國99年5月5日經授水字第09920221710號函修正 2010.
[59] 經濟部水利署, 臺北市淹水潛勢圖, 2010.
[60] 經濟部水利署水利防災中心, 縣市政府抽水機運用作業流程, 2011.
[61] 葉錦勳, 地理資訊系統在地震災害潛勢分析的損失評估之應用, 國家地震工程研究中心, 1999.
[62] 葉錦勳, 地震危害度分析與震災境況模擬技術整合研究(I), 國家地震工程研究中心, 2006.
[63] 葉錦勳, 地震災害境況模擬方法與應用軟體整合研究, 國家地震工程研究中心, 2002.
[64] 葉錦勳, 臺灣地震損失評估系統─TELES, 國家地震工程研究中心, 2003.
[65] 葉錦勳, 簡文郁, 地震危害度分析與震災境況模擬技術整合研究(II), 國家地震工程研究中心, 2007.
[66] 葉錦勳, 簡文郁, 林主潔, 周光武, 陳緯蒼, 張毓文, 住宅地震保險風險評估模型技術手冊, 國家地震工程研究中心, 2010.
[67] 廖述賢, 溫志皓, 資料探勘理論與應用-以IBM SPSS Moderler為範例, 博碩文化股份有限公司, 2011.
[68] 廖述賢, 溫志皓, 資料採礦與商業智慧 Data Mining and Business Intelligence, 霜葉書廊, 臺北市, 2009.
[69] 廖述賢、溫志皓, 資料採礦與商業智慧, 雙葉書廊 (2009).
[70] 臺北市各區公所, 98年區務統計要覽, 2009.
[71] 臺北市各區公所, 99年為民服務白皮書, 2010.
[72] 臺北市政府工務局水利工程處, 歷史易發生積水之地區參考, 2012.
[73] 臺北市政府民政局, 臺北市各區最新月份人口數及戶數, 2012.
[74] 臺北市政府災害防救委員會, 台北市各行政區颱洪災害潛勢紀要(92年度), 2003.
[75] 臺北市政府消防局, 臺北市防災作業手冊, 2013.
[76] 臺北市政府教育局, 臺北市各類防災任務學校一覽表, 2011.
[77] 劉家增等, 101年度防災避難收容學校國際交流參訪, 臺北市政府教育局, 2012.
[78] 鄭明淵, 周瑞生, 楊亦東, 蔡明修, 蔡幸致, 極端氣候下都市複合性災害潛勢評估與防災作業之研究-以臺北市為例(2/3), 國科會研究計畫報告, 2012.
[79] 鍾弘遠, 陳高德, 臺北市邊坡管理經驗, 2003.
[80] 簡文郁, 張毓文, 溫國樑, 羅俊雄, 台北盆地地盤效應分析, 結構工程 17 (3) (2002).