進階搜尋


 
系統識別號 U0026-2508201416034300
論文名稱(中文) 應用個體生態矩陣及類神經網路模擬溪流棲息地之概況
論文名稱(英文) Using Fish Autecology Matrix & Artificial Neural Networks to Simulate Instream Fish Habitat Conditions
校院名稱 成功大學
系所名稱(中) 水利及海洋工程學系
系所名稱(英) Department of Hydraulics & Ocean Engineering
學年度 102
學期 2
出版年 103
研究生(中文) 張桓旋
研究生(英文) Huan-Hsuan Chang
學號 N86014021
學位類別 碩士
語文別 中文
論文頁數 84頁
口試委員 指導教授-孫建平
口試委員-蕭政宗
口試委員-游景雲
口試委員-邱郁文
中文關鍵字 魚類個體生態矩陣  類神經網路模式  模糊控制  棲息地模式 
英文關鍵字 autecology matrix  artificial neural networks  fuzzy control  habitat model 
學科別分類
中文摘要 近年來生態意識抬頭,以生態為基礎、安全為導向的生態工法被廣泛利用,以減少對自然環境造成傷害、落實生物多樣性保育及永續發展。其中魚類偏好之棲息地環境常為溪流棲息地保護與復育的重要一環。棲息地環境會隨水深、流速、溶氧、水質等物理化學因子不同而異,除物理及化學因子外,亦會隨魚類的互動關係如消費層級、魚類食性、對水質的偏好等而有所不同。本研究模式同時探討物理環境因子與生物因子與棲息地環境的關聯性,並找出與棲息地環境相單位棲息地相關的重要因子。
本研究目標在於發展溪流棲息地模擬模式,以後堀溪及五溝水為研究案例,結合過往魚類採樣及生態調查結果,調查的尺度為微棲息地尺度(單位棲息地)。運用魚類個體生態矩陣分析魚類資料以了解魚類對個環境因子的需求。另將單位棲息地調查結果之水深及流速利用模糊控制理論(fuzzy control)進行分類,分成淺灘、淺湍瀨、深潭、深湍瀨四類型。結合上述兩者擴大棲息地尺度以便往後本模式可以適用於大型的棲息地採樣資料。不同組合的大型棲息地魚類群落並不相同,偏好棲息地環境也有所差異,為了解大型棲息地魚類群落與各棲息地環境的關係,分別利用線性迴歸(linear regression, LR)與類神經網路(artificial neural networks, ANNs),建立棲息地模擬模式,推測大型棲息地中各棲息地類型比例、平均水深及平均流速,以及找出影響其數值的相關環境因子,並且比較線性迴歸模式及類神經網路模式的優劣。
透過本研究魚類與棲息地關係模式的應用,可提供河川管理者依不同的魚種選擇適合的棲息地類型與生態復育設計的參考依據,以達到維護生態保護的目標。
英文摘要 Recently, more and more people realize the importance of Ecology. For river restoration, ecological engineering projects that providing more suitable habitats for fish community are being designed. To sustain fish population and maintain biodiversity, understanding the relationship between fish community and physical habitat of rivers plays an important role.
This study proposes a simplified method to estimate the mesohabitat composition that would favor members of a given set of fish species. Sampling data were collected form HouKu River and WuGouShui River, Taiwan. Using an autecology matrix to identify the critical environmental factors for fish and fuzzy control theory which including depth and velocity as inputs to classify habitats as shallow pool, shallow riffle, deep pool, and deep riffle. Linear regression (LR) and artificial neural networks (ANNs) were used to run the fish habitat models which are based on fish data, abiotic data and an autecology matrix. The result shows that ANNs is an appropriate tool for modeling the relationship between fish and habitat. The models results constitute a reference condition that can be used to guide stream restoration and ecological engineering decisions aimed at maintaining the natural ecological integrity and diversity of rivers.
論文目次 摘要 I
Extended Abstract II
謝誌 III
目錄 VIII
表目錄 X
圖目錄 XII
第一章 前言 1
1-1 研究動機與目的 1
1-2 論文架構 2
第二章 文獻回顧 4
2-1 魚類與棲息地的關係 4
2-2 溪流棲息地分類標準 5
2-3 類神經網路 8
2-4 溪流棲息地模擬 9
第三章 研究方法與理論 11
3-1 魚類個體生態矩陣 11
3-1-1 魚類個體生態矩陣架構 11
3-1-2 魚類個體生態矩陣之建立 14
3-2 模糊控制系統 17
3-2-1 傳統集合與模糊集合 17
3-2-2 模糊推論系統 19
3-3 類神經網路 22
3-3-1 類神經網路的基本架構 23
3-3-2 倒傳遞類神經網路 25
第四章 研究案例 28
4-1 研究區域概述 28
4-1-1 研究區域河川環境特性 28
4-1-2 資料之建置 30
4-2 溪流棲息地模擬架構建立 31
4-2-1 魚類個體生態矩陣分析 32
4-2-2 運用模糊控制理論於棲息地分類 35
4-2-3 大型棲息地模擬 40
4-3 棲息地環境推估模式 41
4-3-1 迴歸模式架構 42
4-3-2 類神經模式架構 43
4-3-3 模式評鑑指標 44
第五章 結果與討論 46
5-1 單位棲息地分類 46
5-2 魚類環境需求矩陣 52
5-3 棲息地環境推估模式結果與分析 55
5-3-1 迴歸模式推估結果與分析 55
5-3-2 類神經模式推估結果與分析 62
5-3-3 迴歸模式與類神經模式成果比較 68
5-4 運用模式做歷史資料推估 74
第六章 結論與建議 77
6-1 結論 77
6-2 建議 78
參考文獻 79
參考文獻 Azzellino, A., & Vismara, R. Pool quality index: New method to define minimum flow requirements of high-gradient, low-order streams. Journal of Environmental Engineering, 127(11), 1003-1013, (2001).
Bockelmann, B. N., Fenrich, E. K., Lin, B., & Falconer, R. A. Development of an ecohydraulics model for stream & river restoration. Ecological Engineering, 22(4–5), 227-235, (2004).
Brosse, S., Guegan, J. F., Tourenq, J.-N., & Lek, S. The use of artificial neural networks to assess fish abundance & spatial occupancy in the littoral zone of a mesotrophic lake. Ecological Modelling, 120(2–3), 299-311, (1999).
Brown, L. Fish Communities & their associations with environmental variables, lower San Joaquin River drainage, California. Environmental Biology of Fishes, 57(3), 251-269, (2000).
Chameau, J. L., & Santamarina, J. C. Membership functions I: Comparing methods of measurement. International Journal of Approximate Reasoning, 1(3), 287-301, (1987).
Dedecker, A. P., Goethals, P. L. M., Gabriels, W., & De Pauw, N. Optimization of Artificial Neural Network (ANN) model design for prediction of macroinvertebrates in the Zwalm river basin (Fl&ers, Belgium). Ecological Modelling, 174(1–2), 161-173, (2004).
Fretwell, S.D., Population in changing environments., Princeton University Press, Princeton, NJ, (1972).
Guisan, A., & Zimmermann, N. E. Predictive habitat distribution models in ecology. Ecological Modelling, 135(2–3), 147-186, (2000).
Hughes, R. M., & Gammon, J. R. Longitudinal changes in fish assemblages & water quality in the Willamette River, Oregon. Transactions of the American Fisheries Society, 116(2), 196-209, (1987).
Lamouroux, N., Capra, H., & Pouilly, M. Predicting habitat suitability for lotic fish: linking statistical hydraulic models with multivariate habitat use models. Regulated Rivers: Research & Management, 14(1), 1-11, (1998).
Lamouroux, N., & Capra, H. Simple predictions of instream habitat model outputs for target fish populations. Freshwater Biology, 47(8), 1543-1556, (2002).
Lek, S., Delacoste, M., Baran, P., Dimopoulos, I., Lauga, J., & Aulagnier, S. Application of neural networks to modelling nonlinear relationships in ecology. Ecological Modelling, 90(1), 39-52, (1996).
Lek, S., & Guégan, J. F. Artificial neural networks as a tool in ecological modelling, an introduction. Ecological Modelling, 120(2–3), 65-73, (1999).
Lévêque, C. Biodiversity dynamics & conservation: the freshwater fish of tropical Africa: Cambridge University Press, (1997).
Liang, Q., & Mendel, J. M. Interval type-2 fuzzy logic systems: theory & design. Fuzzy Systems, IEEE Transactions on, 8(5), 535-550, (2000).
Mattingly, H. T., & Galat, D. L. Distributional patterns of the threatened Niangua darter, Etheostoma nianguae, at three spatial scales, with implications for species conservation. Journal Information, (2002).
Moir, H. J., Gibbins, C. N., Soulsby, C., & Webb, J. Linking channel geomorphic characteristics to spatial patterns of spawning activity & discharge use by Atlantic salmon (Salmo salar L.). Geomorphology, 60(1–2), 21-35, (2004).
Morán-López, R., Pérez-Bote, J. L., Da Silva Rubio, E., & Corbacho Amado, C. Summer habitat relationships of barbels in south-west Spain. Journal of Fish Biology, 67(1), 66-82, (2005).
Moyle, P. B., & Baltz, D. M. Microhabitat use by an assemblage of California stream fishes: developing criteria for instream flow determinations. Transactions of the American Fisheries Society, 114(5), 695-704, (1985).
Moyle, P. B., & Vondracek, B. Persistence & structure of the fish assemblage in a Small California Stream. Ecology, 66(1), 1-13, (1985).
Mueller Jr, R., & Pyron, M. Fish assemblages & substrates in the Middle Wabash River, USA. Copeia, 2010(1), 47-53, (2010).
Munakata, T., & Jani, Y. Fuzzy systems: an overview. Communications of the ACM, 37(3), 68-76, (1994).
Nicolas, D., Le Loc'h, F., Désaunay, Y., Hamon, D., Blanchet, A., & Le Pape, O. Relationships between benthic macrofauna & habitat suitability for juvenile common sole (Solea solea, L.) in the Vilaine estuary (Bay of Biscay, France) nursery ground. Estuarine, Coastal & Shelf Science, 73(3–4), 639-650, (2007).
Olaya-Marín, E. J., Martínez-Capel, F., Soares Costa, R. M., & Alcaraz-Hernández, J. D. Modelling native fish richness to evaluate the effects of hydromorphological changes & river restoration (Júcar River Basin, Spain). Science of The Total Environment, 440, 95-105, (2012).
Özesmi, S. L., & Özesmi, U. An artificial neural network approach to spatial habitat modelling with interspecific interaction. Ecological Modelling, 116(1), 15-31, (1999).
Park, Y. S., Verdonschot, P. F., Chon, T.-S., & Lek, S. Patterning & predicting aquatic macroinvertebrate diversities using artificial neural network. Water research, 37(8), 1749-1758, (2003).
Schwartz, J. S., & Herricks, E. E. Fish use of ecohydraulic-based mesohabitat units in a low-gradient Illinois stream: implications for stream restoration. Aquatic Conservation: Marine and Freshwater Ecosystems, 18(6), 852-866, (2008)
Suen, J. P., & Herricks, E. Investigating the causes of fish community change in the Dahan River (Taiwan) using an autecology matrix. Hydrobiologia, 568(1), 317-330, (2006).
Suen, J. P., & Su, W. C. Reconstructing riverine mesohabitat unit composition using fish community data & an autecology matrix. Journal of Fish Biology, 77(4), 972-984, (2010).
Sutela, T., Vehanen, T., & Jounela, P. Response of fish assemblages to water quality in boreal rivers. Hydrobiologia, 641(1), 1-10, (2010).
Vadas R.L., & Orth D.J., Use of physical variables to discriminate visually determined mesohabitat types in North American Stream, River, 6, 3 143-159, (1998).
Vadas Jr, R. L., & Orth, D. J. Formulation of habitat suitability models for stream fish guilds: do the st&ard methods work? Transactions of the American Fisheries Society, 130(2), 217-235, (2001).
Van Liefferinge, C., Seeuws, P., Meire, P., & Verheyen, R. F. Microhabitat use & preferences of the endangered Cottus gobio in the River Voer, Belgium. Journal of Fish Biology, 67(4), 897-909, (2005).
Wu, X., Fini, P., Keller, S., Tarsa, E., Heying, B., Mishra, U., Speck, J. Morphological & structural transitions in GaN films grown on sapphire by metal-organic chemical vapor deposition. Japanese journal of applied physics part 2 letters, 35, 1648-1651, (1996).
Yamazaki, Y., Haramoto, S., & Fukasawa, T. Habitat uses of freshwater fishes on the scale of reach system provided in small streams. Environmental Biology of Fishes, 75(3), 333-341, (2006).
Yi, Y., Wang, Z., & Yang, Z. Two-dimensional habitat modeling of Chinese sturgeon spawning sites. Ecological Modelling, 221(5), 864-875, (2010).
Yu, S. L., & Edward, J. P. Use of froude number to determine habitat selection by fish, Rivers, 6, 1, 10-18, (1997).
Yu, S. L., & Lee, T. W. Habitat segregation by fishes in western Taiwan rivers. Journal of Applied Ichthyology, 21(6), 531-534, (2005).
Zadeh, L. A. Fuzzy sets. Information & Control, 8(3), 338-353, (1965).

王進德,「類神經網路與模糊控制理論入門與應用」,全華圖書公司,(2007)。
台灣自來水股份有限公司第六區管理處,「南化水庫防淤隧道工程對下游河道影響評估期末報告」,巨廷工程顧問股份有限公司,(2014)。
吳富春、王琪芳,「流況及地質粒徑之改變對河川物理棲息地之影響」,第十一屆水利工程研討會論文集(下冊),第47-50頁,(2000)。
吳富春、胡通哲、李國昇、李德旺,「應用棲息地模式估算台灣河川之生態流量」,第九屆水利工程研討會,第21-28頁,(1998)。
呂映昇,「物理環境因子與魚類棲息地喜好度之關係-多變量分析之應用」, 國立成功大學水利及海洋工程研究所碩士論文,(2009)。
汪靜明,「大甲溪水資源環境教育」,經濟部水資源局,第15-30頁,(2000)。
汪靜明,「大甲溪魚類棲息地改善之三年生態評估研究」,經濟部水資源局,(1999)。
汪靜明,「台灣溪流生態保育」,行政院農業委員會林務局,第66-70頁,(2003)。
沈世傑,「台灣魚類誌」,國立台灣大學動物學系,(1993)。
林馳源,「伏流水對地表逕流水質與魚類影響之研究」,國立成功大學水利及海洋工程研究所碩士論文,(2013)。
邵廣昭、林沛立,「溪池釣的魚-淡水魚及河口的魚」,渡假出版社有限公司,第234頁,(1998)。
邵廣昭、陳靜怡,「魚類圖鑑」,遠流出版事業股份有限公司,第431頁,(2003)。
孫建平、曹先紹、E. E. Herricks,「魚類生態矩陣之建立及其於生態工程之應用」,台灣水利第53卷第2期,第86-93頁,(2005)。
張斐章、張麗秋,「類神經網路導論:理論與應用」,滄海書局,第2-47頁,(2010)。
陳義雄、方力行,「台灣淡水及河口魚類誌」,國立海研生物博物館籌備處,(1999)。
葉明峰,「河川魚類適合度曲線調查技術」,河川生態基準流量評估技術研討會,講題 第1-15頁,(2002)。
葉明峰、張世倉、林斯正,「台灣櫻花鉤吻鮭域外流放棲息地之評估,特有生物研究」5(2),第15-32頁,(2003)。
葉柏緯,「伏流水對魚類棲息地之影響─以五溝水湧泉濕地為例」,國立成功大學水利及海洋工程研究所碩士論文,(2014)。
詹見平、陳瓊如,「和魚兒做朋友」,人人出版股份有限公司,(2002)。
趙傳睿,「以微棲息地偏好度及適合度結合River2D模擬枯水期魚類棲息地」,國立成功大學水利及海洋工程研究所碩士論文,(2011)。
韓僑權、方力行,台南縣河川湖泊魚類誌,台南縣政府,(1997)。
蘇瑋哲,「魚類個體生態矩陣於溪流棲息地模擬之應用」,國立成功大學水利及海洋工程研究所碩士論文,(2008)。
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2017-09-09起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2017-09-09起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw