| 研究生: |
周世凱 Chou, Shih-kai |
|---|---|
| 論文名稱: |
應用類神經模式推估未設測站之自然流態 Application of Artificial Neural Networks for Estimating Ungauged Natural Flow Regime |
| 指導教授: |
孫建平
Suen, Jian-Ping |
| 學位類別: |
碩士 Master |
| 系所名稱: |
工學院 - 水利及海洋工程學系 Department of Hydraulic & Ocean Engineering |
| 論文出版年: | 2008 |
| 畢業學年度: | 96 |
| 語文別: | 中文 |
| 論文頁數: | 97 |
| 中文關鍵詞: | 自然流態 、未設測站 、類神經網路 、水文改變指標 |
| 外文關鍵詞: | Artificial neural network, Indicator of hydrologic alteration, Ungauged station, Natural flow regime |
| 相關次數: | 點閱:132 下載:1 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
台灣地區河川的生態環境已受相當程度的改變,為了人類需求大多數的河川都具有人工結構物用以調節水資源,這些結構物將會導致河川中最重要的流水型態產生改變,而自然流態的變化卻是能夠架構完整的河川生態系統,雖然河川保育觀念的提昇,但工程上常使用的生態流量管理法大部份屬於固定流量管理,這種單調性的環境變化對於生態環境會導致物種的多樣性降低並影響生態系統的穩定性等,所以河川保育的觀念應該不只著重於棲息地的復育,對於河川水流的流態變化也是重要的考量。
本研究欲推估未設測站的自然流態,設計選取全台42個上游未受人為控制且流量紀錄約20年的流量測站,採用可以量化河川的自然流態的31個水文改變指標(Indicator of Hydrologic Alteration,IHA)作為依變數,並使用水文改變指標作為分類變數進行流態均一區的劃分,再利用地理資訊系統取得地文及雨量參數作為自變數。推估模式的建立將利用可模擬描述非線性系統的類神經網路,採用具有一隱藏層的倒傳遞類神經網路作為本研究的推估模式。
從研究結果顯示台灣地區流量測站具有三類別的流態特性,而各組水文改變指標與集水區地文及雨量參數因子具有不同的相關特性。在類神經模式的水文改變指標推估值誤差結果顯示,各組指標的誤差百分比平均落在8到21%,且相關係數平均達到0.7以上呈現高度相關,表示本研究設計的類神經模式具有準確推估流量測站之自然流態的能力。
最後以多元迴歸模式進行指標推估比較,其結果顯示大部份的指標推估誤差表現上,類神經網路模式具有較優異的表現,顯示類神經網路推估模式能夠有效的描述模擬複雜的水文系統。
Maintaining the integrity of the river ecosystem must rely on natural flow regimes. In the past, the ecological streamflow management often used the minima flow approach, but many studies have shown that flow regulation is one of the most critical factors that cause the ecological environment of the river basin deterioration. The variability of the flow regimes strongly affects important habitat physical factors, such as flow rate, water depth and river erosion and deposition changes.
This study uses an artificial neural network approach that could simulate complex nonlinear model. The back-propagation neural network (BPN) with one hidden layer is used for estimating ungauged natural flow regime. A set of 42 gauging stations with no artificially upstream flow control mechanism and about 20 years streamflow record of each station has been selected for this study. Geographic Information System is used to obtain the physiographic characteristics and climate characteristics for model inputs. In order to quantify the natural river flow regime, the 31 Indicators of Hydrologic Alteration (IHA) are used as model outputs. Results show that the range of the each group’s mean absolute percentage error is 8~21% and the correlation coefficient of test samples is up to 0.7.
At last, a multiple regression model is used to compare with ANN model. The results show that the neural network model reveals much better performance in most estimating errors of indicators estimation than the regression model does. It suggests that the neural network model could effectively simulate the complex hydrological system.
Alczar J., A. Palau, and C. V. Garca., “A neural net model for environmental flow estimation at the Ebro River Basin, Spain.”, Journal of Hydrology 349, 44– 55., 2008
Allen J. D., “Stream Ecology: Structure and Function of Running Waters.” Chapman and Hall, London., 1995
Bovee K.D., “A guide to stream habitat analysis using the instream flow incremental methodology.” Instream Flow Information Paper no. 12. FWS OBSERVATION 82/86. Washington D.C., USA., 1982
Burn, D.H., “Cluster analysis as applied to regional flood frequency.” Journal of Water Resources Planning and Management, 115(5), 567-582., 1989
Connell J. H., “Diversity in tropical Rainforests and Coral reefs.” Science, 199:1302-1310., 1978
Fisher R. A., “The use of multiple measurements in taxonomic problems.” Annals Eugen. 7:179-188., 1936
Gwo Fong Lin, Ming Chang Wu, “A SOM-based approach to estimating design hyetographs of ungauged sites.” Journal of Hydrology. 339:3-4:216-226., 2007
Haines A. T., Finlayson B.L., McMahon T.A., “A global classification of river regimes.” Applied Geography. 8, 255-272., 1988
Hopfield J. J., “Neural Networks and Physical Systems with Emergent Collective Computational Abilities.” Proceeding of the National Academy of Scientists. 79:2554-2558., 1982
Hopfield J. J., Tank D., “Neural Computations of Decisions in Optimization Problems.” Biological Cybernetics. 51:141-152., 1985
Hosking J. R. M., Wallis, J. R., “Regional Frequency Analysis: An Approach Based on L-moments.”, Cambridge University Press, New York., 1997
Lenard MJ, Alam P, Madey GR., “The application of neural networks and a qualitative response model to the auditor’s going concern uncertainty decision.” Decision Sci 26(2):209–227., 1995
MacArthur R. H., “Fluctuations of animal populations, and measure of community stability.” Ecology 35:533-536, 1955
MacArthur R. H., and E. O. Wilson., “The theory of island biodiversity.” Princeton: Princeton University Press, Princeton, New Jersey, USA., 1967
Marks J. C., R. Parnell, C. Carter, E. C. Dinger, G. A. Haden., “Interactions between geomorphology and ecosystem processes in travertine streams: Implications for decommissioning a dam on Fossil Creek, Arizona.”, Geomorphology: 77 299–307., 2006
McCulloch W. S. and Pitts W., “A logical Calculus of Ideas Immanent in Nervous Activity.”, Bulletin of Mathematical Biophysics. 5:115-133, 1943
Minsky M. L., Papert S. A., “Perceptrons” Cambridge. MA: MIT Press., 1969
Nathan R. J., McMahon T. A., “Identification of homogeneous regions for the purpose of regionalization.” Journal of Hydrology, 121, 217-238., 1990
Orth D. J., “Ecological considerations in the development and application of instream flow-habitat models”, Regulated Rivers: Research and Management., 1987
Piramuthu S., Shaw M., Gentry J.., “A classification approach using multi-layered neural networks.” Decis Support Syst 11(5):509–525, 1994
Poff N. L., J. D. Allan, M.B. Bain, J. R. Karr, K. L. Prestegaard, B. D. Richter, R. E. Sparks, J. C. Stromberg., “The natural flow regime.” Bioscience 47, pp.769-784., 1997
Poff N. L., Tokar S., Johnson P., “Stream hydrological and ecological responses to climate change assessed with an artificial neural network.” Limnology and oceanography, 41(5), 857-863., 1996
Punj G. N., R. Staelin., “A Model of Consumer Information Search Behavior for New Automobiles.” Journal of Consumer Research, 9(4), 368-380., 1983
Richter B. D., J. V. Baumgartner, J. Powell, and D. P. Braun, “A Method for Assessing Hydrologic Alteration within Ecosystems.” Conservation Biology, 10(4): 1163-1174., 1996
Richter B. D., Baumgartner J. V., Wigington R., and Braun D. P., “How Much Water Does A River Need.”, Freshwater Biology,.37(1):231-249., 1997
Richter B. D., J. V. Baumgartner, D. P. Braun., and J. Powell., “A Spatial Assessment of Hydrologic Alteration Within A River Network.”, Regulated Rivers: Research & Management 14: 329-340., 1998
Rosenblatt F., “A Probabilistic Model for Information Storage and Organization in the Brain.” Psych. Rev. 65:386-408., 1958
Rumelhart D. E., McClelland J. L., “Parallel Distributed Processing: Exploration in the Microstructure of Cognition.” Vol. 1. Cambridge, MA: MIT Press., 1986
Sanborn S. C. and B. P. Bledsoe, “Predicting streamflow regime metrics for ungauged streams in Colorado, Washington, and Oregon.” Journal of Hydrology, 325, 241-261., 2006
Sharma S., “Applied multivariate techniques” ,NY :John Wiley & Sons, Inc., 1996
Suen, J.P. and Eheart, J.W., “Reservoir management to balance ecosystem and human needs: incorporating the paradigm of the ecological flow regime.”,Water resources research,42(3) :W03417., 2006
Tennant D.L., “Instream flow regimens for fish, wildlife, recreation and related environmental resources.” American Fisheries Society, Bethesda, Maryland, USA. Instream Flow Needs, pp. 359–373., 1976
Wang F., “The use of artificial neural networks in a geographical information system for agricultural land suitability assessment.” Environ Plann A 26(2):265–284., 1994
Ward, J. H., “Hierarchical grouping to optimize an objective function.” Journal of the American Statistical Association, 58, 236-244., 1963
朱錦紅、柯文雄、許晃雄,「臺灣降水變化研究回顧:氣候分區、降水與東亞大氣環流之關聯」,全球變遷通訊雜誌第三十六期,2002。
汪靜明,「臺灣河川的生態保育」,科學月刊22(12):930-937,1991。
易任、徐國麟,「主成份分析與集分析應用於淡水河流域空間降雨的研究」,第五屆水利工程研討會論文,第112-137頁,1990。
易任,「臺灣全區降雨時空分佈之研究:主成份分析與群集分析」,行政院國家科學委員會專題研究計劃成果報告,1993。
林國峰、王俊明、高士傑,「區域性設計雨型之建立及應用」,台大工程學刊92期,第1-9頁,2004
邱皓政,「量化研究與統計分析:SPSS中文視窗版資料分析範例解析」,五南出版社,2002。
徐天寶、彭靜、李翀,「河流生態水文指標體系及其應用研究」,第十一屆海峽兩岸水利科技交流研討會,2007。
孫建平,「類神經網路及其應用於降雨及逕流過程之研究」,國立台灣大學農業工程研究所碩士論文,1996。
張斐章、黃浩倫、張麗秋,「回饋式類神經網路於河川流量推估之應用」,中國農業工程學報, 47(2):32-39,2001。
陳柏蒼、陳昶憲,「未設測站流量推估-利用類神經網路建構模式」,第七屆海峽兩岸水利科技交流研討會,2002。
陳堯風、林信初,「威脅河川之因素」,American Rivers,2002。
游保杉、楊道昌、陳嘉榮,「立霧溪流域年平均流量與地文因子關係之研究」,台灣水利,第41 卷,第3 期,第68-76頁,1993。
游保杉、楊道昌,「未量測集水區降雨─逕流模式之率定方法」,土木水利,第26 卷,第2 期,第16–23 頁,1999。
葉怡成,「類神經網路模式應用與實作」,儒林圖書有限公司,1999。
溫博文,「台灣中部河川生態棲地分佈特性集時空變化之研究」,國立中央大學土木工程研究所博士論文,2005。
蕭政宗、吳富春,「集集攔河堰最佳引水與河川生態流量之研究」,第十四屆水利工程研討會,第C1-C8頁,2004。
蕭政宗、吳富春,「變異範圍法RVA應用於河川生態流量之規劃」,第二屆生態工程學術研討會,第33-58頁,2005。
羅積玉,「多元統計分析方法與應用」,科技圖書股份有限公司,1980。