颱風、暴雨期間，實務單位採用警戒水位做為預警之變量，但傳統預報模式卻採用流量為變量，再經由率定曲線轉換為水位。然而率定曲線在高流量存在較大之不確定性及誤差，為免除流量與水位間的轉換手續及其不確定性因素，本研究以蘭陽溪流域為研究區域，建立蘭陽大橋之即時河川水位預報模式。

　　本文引用一新興機器學習方法「支撐向量機」來建構預報模式，支撐向量機發展自統計學習理論，基於結構風險最小化法則來優選模式，具有避免模式過度學習之特性，於各領域已有廣泛且良好的應用，本研究首先引用支撐向量機理論應用於即時水位預報，期能有助於洪水預報領域之研究與進展。

　　關於模式變量之選擇，本研究採用相應水位法針對河川上、下游水位關係進行探討，並考慮雨量之影響，據以提供預報模式建立之基礎；而變量之階數則基於水文反應時間之觀念來決定。關於支撐向量機之參數推估，為克服傳統上採用試誤法之缺點，本文採用兩階段格網搜尋法來進行系統化且徹底之參數優選。對於較長前置時間之水位預報，本研究考慮輸入變量之不同條件組合，建立兩種模式架構之水位預報模式，對蘭陽大橋進行前置時間一至六小時之即時水位預報，結果證實兩種模式架構均有良好的預報效能；並經與灰色水位預報模式比較，證實支撐向量機所建立之水位預報模式有較佳之預報能力。

　In practice, the river stage is the variable for issuing a flood warning during the period of typhoon or storm. However, the river discharge is commonly chosen as a variable in flood forecasting models. The forecasted discharge is then transformed into river stage using a rating curve, which may involve errors and uncertainties in high stages. Hence, the purpose of this study is to construct a real-time flood stage forecasting model at Lan-Yang Bridge in Lan-Yang Creek basin.

　The support vector machine (SVM), a novel and potential artificial intelligence method developed from the statistical learning theory, notionally minimizes the expected risk of a learning machine and thus hypothetically overcomes the problem of over-fitting. Hence the SVM was adopted in this work to establish a flood stage forecasting model and investigate its applicability in real-time stage forecasting. First, the relations between the water stage and input variables were investigated in order to provide prior information on modeling the forecasting model. The orders of input variables were then investigated based on the hydrological concept of time of response. After having decided the input variables, this study applied a two-step grid search method to search the optimal values of parameters in the proposed learning machine. Two kinds of model structures were proposed to perform one- to six-hour-ahead stage forecasts in Lan-Yang Bridge, Lan-Yang Creek. The proposed forecasting model, using the theory of SVM, demonstrated good forecasting results from validation events. The forecasting results of the proposed model were further compared with those of the grey stage forecasting model, and it revealed that the proposed SVM stage forecasting model outperforms the grey stage forecasting model.

王景南，2003，「多類支向機之研究」，元智大學資訊管理研究所碩士論文。
吳南靖、蔡丁貴、簡振和，2002，「集水區降雨－出口點河川水位預報模式之建立」，第十三屆水利工程研討會。
李柏毅，2003，「Support Vector Machine技術應用於中文文件自動分類之探討」，國立高雄應用科技大學電機工程研究所碩士論文。
長江水利委員會，1993，「水文預報方法(第二版)」，水力水電出版社，北京。
林淑真、李宗仰，1996，「自我聯合模式於感潮河段之水位預報」，土木水利，第22卷，第4期，第3-16頁。
夏軍，1989，「水文系統DHGM模型識別與實時灰色預測」，灰色系統論文集。
莊文南，1993，「微分水文灰色模式之研究與應用」，國立臺灣大學農業工程研究所碩士論文。
陳憲宗，1998，「灰色預測在逕流預報之應用」，國立成功大學水利及海洋工程研究所碩士論文。
陳昶憲、陳建宏，1999，「類神經模糊邏輯法應用於洪水位預報」，中國土木水利工程學刊，第11卷，第2期，第317-326頁。
郭修瑞，2004，「使用特徵選擇演算法暨支援向量機在胃部組織學分類上的研究與應用」，國立成功大學電機工程研究所碩士論文。
蘇聯水文氣象委員會，1989，「水文預報指南」(中譯本：張瑞芳等譯，中國水利水電出版社，北京，1998出版)。
Box, G. E. P. and G. M. Jenkins (1976). Time Series Analysis Forecasting and Control, Holden-Day, San Francisco, U.S.A.
Cannas, B., A. Montisci, A. Fanni, L. See, and G. M. Sechi (2004). “Comparing Artificial Neural Networks and Support Vector Machines for Modelling Rainfall-Runoff.” In: Proceedings of the 6th International Conference on Hydroinformatics, S. Y. Liong, K. K. Phoon, and V. Babovic, eds., (Singapore, 21–24 June 2004), World Scientific Publishing Co., Singapore.
Chang, C. C. and C. J. Lin (2002). “Training ν -Support Vector Regression: Theory and Algorithms.” Neural Computation, 14(8), 1959-1977.
Chang, F. J. and Y. C. Chen (2003). “Estuary Water-Stage Forecasting by Using Radial Basis Function Neural Network.” Journal of Hydrology, 270, 158-166.
Cherkassky, V. and Y. Ma (2004). “Practical selection of SVM parameters and noise estimation for SVM regression.” Neural Networks, 17, 113-126.
Choy, K. Y. and C. W. Chan (2003). “Modelling of River Discharges and Rainfall Using Radial Basis Function Networks Based on Support Vector Regression.” International Journal of Systems Science, 34(14-15), 763-773.
Dibike, Y. B., S. Velickov, D. Solomatine, and M. B. Abbott (2001). “Model Induction with Support Vector Machines: Introduction and Applications.” Journal of Computing in Civil Engineering, 15(3), 208-216.
Dumais, S. T. (1998). “Using SVMs for Text Categorization.” In: IEEE Intelligent Systems, Trends and Controversies, M. A. Hearst, ed., 13(4).
Fletcher, R. (1987). Practical Methods of Optimization, John Wiley and Sons, New York.
Han, D. and I. Cluckie (2004). “Support Vector Machines Identification for Runoff Modelling.” In: Proceedings of the 6th International Conference on Hydroinformatics, S. Y. Liong, K. K. Phoon, and V. Babovic, eds., (Singapore, 21–24 June 2004), World Scientific Publishing Co., Singapore.
Hsu, C. W., C. C. Chang, and C. J. Lin (2003). “A Practical Guide to Support Vector Classification.” Technical report, Department of Computer Science and Information Engineering, National Taiwan University, Available at: http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf
Joachims, T. (1998). “Text Categorization with Support Vector Machines.” In: Proceedings of the 10th European Conference on Machine Learning (ECML'98), Chemnitz, Germany, 137-142.
Kelly, K. S. and R. Krzysztofowicz (2000). “Precipitation Uncertainty Processor for Probabilistic River Stage Forecasting.” Water Resources Research, 36(9), 2643-2653.
Krzysztofowicz, R. and K. S. Kelly (2000). “Hydrologic Uncertainty Processor for Probabilistic River Stage Forecasting.” Water Resources Research, 36(11), 3265-3277.
Krzysztofowicz, R. and H. D. Herr (2001). “Hydrologic Uncertainty Processor for Probabilistic River Stage Forecasting: Precipitation-dependent Model.” Journal of Hydrology, 249, 46-68.
Krzysztofowicz, R. (2001). “Integrator of Uncertainties for Probabilistic River Stage Forecasting: Precipitation-dependent Model.” Journal of Hydrology, 249, 69-85.
Krzysztofowicz, R. (2002). “Bayesian System for Probabilistic River Stage Forecasting.” Journal of Hydrology, 268, 16-40.
Lin, C. J. and co-workers (2004). LIBSVM Software (Version 2.71, released on November 20, 2004), Available at: http://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html
Liong, S. Y., W. H. Lim, and G. N. Paudyal (2000). “River Stage Forecasting in Bangladesh: Neural Network Approach.” Journal of Computing in Civil Engineering, 14(1), 1-8.
Liong, S. Y. and C. Sivapragasam (2002). “Flood Stage Forecasting with Support Vector Machines.” Journal of the American Water Resources Association, 38(1), 173-186.
Mattera, D. and S. Haykin (1999). “Support Vector Machines for Dynamic Reconstruction of a Chaotic System.” In: Advances in Kernel Methods: Support Vector Machine, B. Schölkopf, J. Burges, and A. Smola, eds., MIT Press, Cambridge, MA.
Mukherjee, S., E. Osuna, and F. Girosi (1997). ‘‘Nonlinear Prediction of Chaotic Time Series Using Support Vector Machine.’’ In: Proceedings of the 1997 IEEE Workshop on Neural Networks for Signal Processing, New York, 511-519.
Muller, K. R., A. Smola, G. Ratsch, B. Scholkopf, J. Kohlmorgen, and V. Vapnik (1997). ‘‘Predicting Time Series with Support Vector Machines.’’ In: Proceedings of the International Conference on Artificial Neural Networks, Springer-Verlag, Berlin, 999-1004.
Osuna, E., R. Freund, and F. Girosi (1997). ‘‘An Improved Training Algorithm for Support Vector Machines.’’ In: Proceedings of the 1997 IEEE Workshop on Neural Networks for Signal Processing, New York, 276-285.
Osuna, E. (1998). “Using SVMs for Face Detection.” In: IEEE Intelligent Systems, Trends and Controversies, M. A. Hearst, ed., 13(4).
See, L. and S. Openshaw (1999). “Applying Soft Computing Approaches to River Level Forecasting.” Hydrological Sciences Journal, 44(5), 763-778.
See, L. and S. Openshaw (2000). “A Hybrid Multi-Model Approach to River Level Forecasting.” Hydrological Sciences Journal, 45(4), 523-536.
Seibert, J. (2001). “On the Need for Benchmarks in Hydrological Modeling.” Hydrological Processes, 15, 1063-1064.
Sivapragasam, C. and S.Y. Liong (2002). “Flow Region Specific Model for Flow Forecasting.” In: Hydroinformatics 2002: Proceedings of the 5th International Conference on Hydroinformatics, (Cardiff, U.K., 1–5 July 2002), IWA Publishing, London, U.K., 653-658.
Sivapragasam, C. and S. Y. Liong (2004). “Identifying Optimal Training Data Set － A New Approach.” In: Proceedings of the 6th International Conference on Hydroinformatics, S. Y. Liong, K. K. Phoon, and V. Babovic, eds., (Singapore, 21–24 June 2004), World Scientific Publishing Co., Singapore.
Suykens, J. A. K., T. Van Gestel, J. De Brabanter, B. De Moor, and J. Vandewalle (2002). Least Squares Support Vector Machines, World Scientific Publishing, Singapore, 42-44.
Thirumalaiah, K. and M. C. Deo (1998). “River Stage Forecasting Using Artificial Neural Networks.” Journal of Hydrologic Engineering, 3(1), 26-32.
Vapnik, V. N. (1995). The Nature of Statistical Learning Theory, Springer-Verlag, New York.
Vapnik, V. N., S. Golowich, and A. Smola (1997). “Support Vector Method for Function Approximation, Regression Estimation, and Signal Processing.” In: Neural Information Processing Systems, M. Mozer, M. Jordan, and T. Petsche, eds., MIT Press, Cambridge, MA, 169-184.
Vapnik, V. N. (1998). Statistical Learning Theory, Wiley, New York.
Vojinovic, Z. and V. Kecman (2004). “Contaminant Transport Modelling with Support Vector Machine Model – An Alternative to Classical Advection-Dispersion Equation.” In: Proceedings of the 6th International Conference on Hydroinformatics, S. Y. Liong, K. K. Phoon, and V. Babovic, eds., (Singapore, 21–24 June 2004), World Scientific Publishing Co., Singapore.
Yu, X., S.Y. Liong, and V. Babovic (2002). “Hydrologic Forecasting with Support Vector Machine Combined with Chaos-Inspired Approach.” In: Hydroinformatics 2002: Proceedings of the 5th International Conference on Hydroinformatics, (Cardiff, U.K., 1–5 July 2002), IWA Publishing, London, U.K., 764-769.
Yu, X. and S. Y. Liong (2004). “Forecasting of Chaotic Hydrological Time Series with Ridge Linear Regression in Feature Space.” In: Proceedings of the 6th International Conference on Hydroinformatics, S. Y. Liong, K. K. Phoon, and V. Babovic, eds., (Singapore, 21–24 June 2004), World Scientific Publishing Co., Singapore.