臺灣博碩士論文加值系統

颱洪往往導致大量泥砂進入水庫造成淤積，為使水庫能永續經營必須有效清除淤積。目前異重流排砂為中大型水庫主要排砂策略，若能預先知道泥砂濃度，在適當時機啟動排砂設施便能增加排砂量並減少水資源的浪費。目前現有的水庫出流泥砂濃度預報模式，在濃度轉折處和峰值會低估。因此，本研究提出庫出流泥砂濃度預報模式，可準確預報水庫出流泥砂濃度，特別是修正了濃度轉折處和峰值誤差，提供決策者操作出水工之依據，以提升排砂效率。
本研究結合自組織映射輸出圖(self-organizing feature map，SOM)、支援向量機(support vector machine，SVM)和時序列分析(autoregressive model，AR)建立水庫出流泥砂濃度預報模式，命名為 SOSVM-AR。主要架構分為三階段：分類、預報和即時修正。分類時以SOM模式分析並萃取高價值資訊的資料，經資料再處理後，以SVM預報水庫出流泥砂濃度。最後使用AR，對預報結果作即時修正，進一步增加模式準確度。
本研究選用石門水庫為研究區域，蒐集2012至2016年共六場颱風事件的入流量、出流量、入流濃度、出流濃度和時域反射法實測斷面濃度資料。經過相關係數分析篩選有效輸入項後，預報未來在t+1至t+3小時泥砂濃度，並將結果與單純使用SVM和未使用AR修正的SOSVM比較。結果顯示，在t+1至t+3時刻SOSVM-AR預報泥砂濃度尖峰值最準確，其次為SOSVM和SVM，尤其在t+3時刻最為明顯。均方根誤差、平均絕對誤差、相關係數、效率係數等四個評鑑指標指出SOSVM-AR預報結果皆優於SOSVM和SVM。未來可使用本研究提出之SOSVM-AR預報水庫出流泥砂濃度，作為決策者排砂操作的參考。

Reservoir sedimentation is a serious problem in Taiwan. Therefore, reducing sediment deposition in reservoirs is an essential issue. Various strategies have been used to reduce sedimentation. Venting turbidity currents through reservoir outlets can be an efficient strategy. An accurate forecasted outflow sediment concentration is necessary for accessing and increasing the venting efficiency.
In this study, an outflow sediment concentration forecasting model (SOSVM-AR), integrating self-organizing map (SOM), support vector machine (SVM), and autoregressive model (AR), is proposed to yield 1- to 3-h lead time forecasts. First, self-organizing map (SOM) is adopted to extract valuable data which has salient features. Second, the original training data and the reprocessed data are employed to train SVM. Finally, AR is used to real-time correct the forecasts.
An application to the Shihmen reservoir is presented to demonstrate the accuracy of the proposed model. Six typhoons events from 2012 to 2016 are collected to train and test the proposed model. The original SVM and the SOSVM, integrating SOM with SVM, were constructed to highlight how adding the extracted reprocessed data and real-time error correction improves the estimating performance. The results show that the proposed model outperforms over other models, especially for the peak sediment concentration. In conclusion, the proposed model can be used as a reference to reservoir sedimentation management.

口試委員會審定書 i
致謝 ii
中文摘要 iii
Abstract iv
目錄 v
圖目錄 vii
表目錄 ix
第一章 緒論 1
1.1 研究動機 1
1.2 文獻回顧 2
1.3 論文架構 4
第二章 研究區域與資料 5
2.1研究區域 5
2.2異重流現象 7
2.3研究資料 8
2.3.1 濃度資料 8
2.3.2 流量資料 9
第三章 研究方法 16
3.1 自組織映射圖(SOM) 16
3.2 支援向量機(SVM) 20
3.3 自迴歸模式(AR) 25
3.4 網格搜尋法 26
3.5 交替驗證 27
3.6 評鑑指標 28
3.7 排砂效率計算 30
第四章 模式建立 31
4.1 研究流程 31
4.2 分類階段 32
4.3 預報階段 33
4.4 即時修正階段 34
第五章 結果與討論 35
5.1 分類階段 35
5.1.1 難預報點 35
5.1.2 分類因子篩選 37
5.1.3 分類結果 42
5.2 預報階段 43
5.2.1 預報因子篩選 43
5.2.2 預報結果 43
5.3 即時修正階段 50
5.3.1 參數率定 50
5.3.2 即時修正結果 50
5.4 排砂效率 61
第六章 結論與建議 68
6.1 結論 68
6.2 建議 69
參考文獻 70

1.Chamoun S, De Cesare G, Schleiss AJ (2016) Experimental investigation on turbidity current venting under restrained outflow discharges. River Flow Proceedings, Saint Louis, USA
2.Akiyama J, Stefan HG (1984) Plunging flow into a reservoir-theory. J Hydraul Eng 110:484–499
3.Annandale GW (2005) Reservoir sedimentation. Elsevier Science, USA
4.Buehler J, Siegenthaler C (1986) Self-preserving solutions for turbidity currents. Acta Mechanica 63:217–233.
5.Cesare GD, Boillat J-L, Schleiss AJ (2006) Circulation in Stratified Lakes due to Flood-Induced Turbidity Currents. Journal of Environmental Engineering 132:1508–1517
6.Cortez P, Rocha M, Neves J Time Series Forecasting by Evolutionary Neural Networks.
7.Coulibaly P, Haché M, Fortin V, Bobée B (2005) Improving Daily Reservoir Inflow Forecasts with Model Combination. Journal of Hydrologic Engineering 10:91–99.
8.Hebbert B, Imberger J, Loh I, Patterson J (1979) Collie River Underflow into Wellington Reservoir. Journal of Hydraulics Divsion 105:533–545
9.Heednacram A (2014) Suspended Sediment Forecast of Khlong Bang Yai, Phuket. International Journal of Engineering and Technology 338–345.
10.Huang J (2011) Adaptive autoregressive deinterlacing method. Optical Engineering 50:057001.
11.Jothiprakash V, Magar R (2012) Multi-time-step ahead daily and hourly intermittent reservoir inflow prediction by artificial intelligent techniques using lumped and distributed data. Journal of Hydrology 450-451:293–307.
12.Kalra A, Ahmad S (2009) Using oceanic-atmospheric oscillations for long lead time streamflow forecasting.
13.Kohonen T, (2006) Self-organizing Neural Projections. Neural Networks 19(6-7): 723-733.
14.Kohonen T, (1987) The Self-organizing Map. Neurocomputing 21(1-3): 1-6.
15.Lin G-F, Chen G-R, Huang P-Y, Chou Y-C (2009) Support vector machine-based models for hourly reservoir inflow forecasting during typhoon-warning periods. Journal of Hydrology 372:17–29.
16.Lin G-F, Chen L-H (2004) A non-linear rainfall-runoff model using radial basis function network. Journal of Hydrology 289:1–8.
17.Lin G-F, Chen L-H (2004) A spatial interpolation method based on radial basis function networks incorporating a semivariogram model. Journal of Hydrology 288:288–298.
18.Lin G-F, Wang C-M (2007) A nonlinear rainfall–runoff model embedded with an automated calibration method – Part 1: The Model . Journal of Hydrology 341:186–195.
19.Lin G-F, Wang C-M (2007) A nonlinear rainfall–runoff model embedded with an automated calibration method – Part 2: The automated calibration method. Journal of Hydrology 341:196–206.
20.Lin G-F, Wu M-C (2011) An RBF network with a two-step learning algorithm for developing a reservoir inflow forecasting model. Journal of Hydrology 405:439–450.
21.Liong S-Y, Sivapragasam C (2002) Flood Stage Forecasting With Support Vector Machines. Journal of the American Water Resources Association 38:173–186.
22.Mohammadi K, Eslami H, Kahawita R (2006) Parameter estimation of an ARMA model for river flow forecasting using goal programming. Journal of Hydrology 331:293–299.
23.Moradkhani H, Hsu K-L, Gupta HV, Sorooshian S (2004) Improved streamflow forecasting using self-organizing radial basis function artificial neural networks. Journal of Hydrology 295:246–262.
24.Rashidi S, Vafakhah M, Lafdani EK, Javadi MR (2016) Evaluating the support vector machine for suspended sediment load forecasting based on gamma test.
25.Savage SB, Brimberg J (1975) Analysis Of Plunging Phenomena In Water Reservoirs. Journal of Hydraulic Research 13:187–205
26.Singh B, Shah CR (1971) Plunging phenomenon of density currents in reservoirs. LaHouille Blanche. 26(1):59–64
27.Srinivasulu S, Jain A (2006) A comparative analysis of training methods for artificial neural network rainfall–runoff models. Applied Soft Computing 6:295–306. doi: 10.1016/j.asoc.2005.02.002
28.Sudheer K-P, Jain S-K (2003) Radial Basis Function Neural Network for Modeling Rating Curves. Journal of Hydrologic Engineering 8(3)
29.Tabatabaei SM, Khozeymehnezhad H, Akbarpuor A, VarjavandP (2017) Investigating Effects of Obstacles Arrangement on the Velocity of Density Currents in Experimental Conditions. Journal of Science and Engineering. 4 (1):53-64
30.Üneş F, Ağiralioğlu N (2017) Numerical Investigation of Temporal Variation of Density Flow and Parameters. Journal of Applied Fluid Mechanics 10:81–94.
31.Wan XY, Wang GQ, Yi P, Bao WM (2010) Similarity-based optimal operation of water and sediment in a sediment-laden reservoir. Water Resour Manag 24(15):4381–4402
32.Wang Z, Xia J, Deng S, et al (2017) One-dimensional morphodynamic model coupling open-channel flow and turbidity current in reservoir. Journal of Hydrology and Hydromechanics
33.Wu M-C, Lin G-F, Lin H-Y (2012) Improving the forecasts of extreme streamflow by support vector regression with the data extracted by self-organizing map. Hydrological Processes 28:386–397.
34.Wu S-J, Lien H-C, Chang C-H, Shen J-C (2011) Real-time correction of water stage forecast during rainstorm events using combination of forecast errors. Stochastic Environmental Research and Risk Assessment 26:519–531
35.Xiong L, Oconnor KM (2002) Comparison of four updating models for real-time river flow forecasting. Hydrological Sciences Journal 47:621–639.
36.Yu P-S, Chen S-T, Chang I-F (2006) Real-Time Flood Stage Forecasting Using Support Vector Regression. Practical Hydroinformatics Water Science and Technology Library 359–373.
37.Yule G-U (1927) On a method of investigating periodicities in disturbed series, with special reference to Wolfer''s sunspot numbers. Phil. Trans. Roy. Soc. London, Ser. A 226:267–298.
38.李豐佐，2013，水庫異重流排砂效率及運移行為之數值模擬與模型試驗，國立臺灣大學生物環境系統工程學博士論文。
39.俞維昇，1990，水庫高濃度異重流的運動行為，中國土木水利工程學會。
40.俞維昇，1991，水庫沉滓運動特性之研究，國立臺灣大學土木工程學博士論文。
41.經濟部水利署，2011，氣候變遷下水庫排砂對策研究總報告
42.經濟部水利署，2014，曾文永久河道放水道改建防淤設施工程射流閘門操作及維護手冊。