臺灣博碩士論文加值系統

台灣水庫多位於地勢陡峭之山區，當颱風豪雨過後，水庫集水區總會有土壤沖蝕或土石崩塌之情形，導致人為活動產生之污染物及營養鹽隨著降雨逕流和泥砂沖刷一起進入水庫庫區內造成水質惡化，可能讓水庫呈現優養化之狀態造成水庫庫容減少並縮短水庫的壽命。本研究以翡翠水庫為例，利用CE-QUAL-W2水理水質模式模擬水庫內營養鹽及藻類生長情形，最後利用類神經網路(artificial neural network, ANN)取代複雜的CE-QUAL-W2水庫模式，較簡便地推估水庫營養鹽產量及藻類生長情形，作為水庫管理單位之參考。建立之類神經網路有總磷、溶氧及葉綠素a模式，研究結果顯示總磷、葉綠素a及溶氧模式之MAE分別為2.60μg/L 、1.18μg/L及0.59mg/L，且大致接可掌握到水庫水質的變動趨勢。可見類神經網路具備取代傳統水庫水質模式的潛力。

Eutrophication has been one of the major water quality problems in lakes and reservoirs in many parts of the world. However, most of the reservoir water quality simulation models require users be well-trained and experienced, so the users need to spend a significant amount of time to get familiar with the parameters, coefficients, grids, and input data of the models. The purpose of thesis is to develop an artificial neural network (ANN) which is much easier for users to predict the water qualities, such as total phosphorus (TP), dissolved oxygen (DO) and chlorophyll-a (Chl-a), in the reservoirs.
In this study, CE-QUAL-W2 (W2) model was used to simulate water quality of Feitsui Reservoir, the studied case of this work. W2 model simulation was performed by using the monitored hydraulic data of Feitsui Reservoir in 2011 as the basis of calibration for the model’s parameters, and used the measurement in 2010 for the verification of the model’s prediction. Due to the lack of monitored water quality data of Feitsui Reservoir, the simulated data by W2 were used to build up an ANN model to predict the water quality of Feitsui reservoir. ANN was trained and verified with W2 simulated data in 2011 and 2010, respectively. The mean absolute errors (MAE) of ANN’s predictions of TP, DO and Chl-a were 2.60μg/L, 0.59mg/L and 1.18μg/L, respectively. Furthermore, the predictions of ANN are able to forecast the trends of water quality variations. The results indicate that ANN has the potential to replace the traditional reservoir water quality simulation models.

摘要 i
Abstract ii
表目錄 vii
圖目錄 viii
第一章 前言 1
1.1. 研究緣起 1
1.2. 研究目的 2
1.3. 研究方法與流程 2
第二章 文獻回顧 4
2.1. 水庫優養化 4
2.2. 水質模式之相關研究 4
2.3. 類神經網路之相關研究 6
第三章 研究方法 8
3.1. 研究區域 8
3.1.1. 水庫介紹 8
3.1.2. 水文與氣象 9
3.1.3. 水質監測 11
3.2. CE-QUAL-W2水理水質模式 13
3.2.1. CE-QUAL-W2模式簡介 13
3.2.2. W2模式理論背景 14
3.2.2.1. 水理模式基本控制方程式 14
3.2.2.2. 水質傳輸模式 17
3.2.2.3. 熱交換模式 18
3.2.2.4. 水力擴散模式 20
3.2.2.5. 生化反應模式 21
3.3. 類神經網路 35
3.3.1. 類神經網路簡介 35
3.3.2. 倒傳遞類神經網路架構 36
3.3.2.1. 人工神經元功能 37
3.3.2.2. 層功能 39
3.3.2.3. 網路功能 40
3.3.3. 倒傳遞類神經網路演算法 40
3.4.1. W2水庫網格的劃分 46
3.4.2. W2模式之輸入資料 49
3.4.3. 模式輸入檔 50
3.5. 類神經網路水質預測模式 51
3.5.1. ANN模式架構 51
3.6. 模式效能評估 55
第四章 結果與討論 57
4.1. CE-QUAL-W2模擬結果 57
4.1.1. W2水理模擬結果 58
4..1.1.1. W2水位模擬結果 58
4.1.1.2. W2水溫模擬結果 60
4.1.2. 水質模擬結果 68
4.2. 類神經網路預測結果 76
4.2.1. 總磷模式 77
4.2.2. 溶氧模式 78
4.2.3. 葉綠素a模式 80
第五章 結論與建議 82
5.1. 結論 82
5.2. 建議 82
參考文獻 83

中文文獻
中央氣象局，http://www.cwb.gov.tw/V7/index.htm。
經濟部水利署，http://www.wra.gov.tw/。
臺北翡翠水庫管理局，http://www.feitsui.gov.tw/。
吳建宏，「德基水庫二維水理與水質模式之模擬」，碩士論文，台灣大學土木工程學研究所，1987。
余岱璟，「石門水庫水質模擬與水理探討」，碩士論文，中央大學土木工程學研究所，2002。
李光敦，「水文學」，五南圖書出版公司出版，2002。
李麗華，「類神經網路」，上課教材，中興大學資訊管理學系，2007。
林信宏，「應用類神經網路於集水區與水庫之水質預測分析」，碩士論文，台灣大學土木工程學研究所，2008。
唐太山，「曾文水庫二維水理水質之模擬與風險分析」，碩士論文，台灣大學土木工程學研究所，2001。


陳鴻傑，「曾文水庫集水區污染物傳輸及水庫水質模擬」，碩士論文，台灣大學土木工程學研究所，2003。
陳怡靜，「水文變化、生物地質化學作用及集水區人為活動對水庫磷質量平衡及藻類消長之影響-以台灣亞熱帶深水水庫為例」，博士論文，台灣大學環境工程學研究所，2004。
莊鎮維，「以CE-QUAL-W2模式模擬分析新山水庫優養化之原因」，碩士論文，台灣大學環境工程學研究所，2012。
張怡塘、陳奕宏、王怡諭，「環境微生物」，中華民國環境工程學會編印，第335-363頁，1999。
章瑜蓓，「二維水質模式之參數校正分析」，碩士論文，中央大學土木工程學研究所，2004。
郭振泰、吳建民、何政儒、陳樹群，「德基水庫熱分層及優養之模擬」，中華民國環境工程學會第三屆環境規劃與管理研討會論文集，1982。
郭振泰、陳樹群，「鳳山水庫優養之探討與模擬(一)、(二)」，省環保處及環保署委託，台灣大學土木工程學研究所執行，1989~1990。
黃宇齊，「翡翠水庫及水庫集水區水文暨水質模擬與其不確定性」，碩士論文，臺北科技大學土木與防災研究所，2010。
葉怡成，「類神經網路-模式應用與實作」，儒林圖書公司，台北，1994。
葉怡成，「應用類神經網路」，儒林圖書公司，台北，1997。
楊詠傑，「以高斯軌跡煙流模式及類神經網路評估南投竹山地區臭氧減量策略」，碩士論文，中興大學環境工程學研究所，2009。
趙美英，「德基水庫二維水理水質之模擬與風險分析」，碩士論文，台灣大學土木工程學研究所，2001。
謝文雄，「水庫水位激烈變化下之水理水質模擬」，碩士論文，中央大學土木工程學研究所，2003。
臺北翡翠水庫管理局，「翡翠水庫操作年報」，2010~2011。
西文文獻
Afshar, A., & Saadatpour, M. (2009). Reservoir eutrophication modeling, sensitivity analysis, and assessment: application to Karkheh Reservoir, Iran. Environmental Engineering Science, 26(7), 1227-1238.
Buchak, E.M., & Edinger, J.E. (1982). User Guide for LARM2: A Longitudinal-Vertical, Time-Varying Hydrodynamic Reservoir Model. Instruction Report E-82-3, U.S. Army Engineer Waterways Experiment Station, Hydraulics Laboratory.
Brion, G. M., NEELAKANTA, T., & Lingireddy, S. (2001). Using neural networks to predict peak Cryptosporidium concentrations. Journal-American Water Works Association, 93(1), 99-105.


Chen, C. W. & Orlob, G. T. (1975). Ecological Simulation of Aquatic Environmental. Chapter 12 in: Systems Analysis and Simulation in Ecology, Vol.3, B.C. Patten, Academic Press, New York.
Chapra, S.C. (1977). Total Phosphorus Model for the Great Lakes. Journal of the Environmental Engineering Division, 103, 147-161.
Chapra, S. C. (1997). Surface water-quality modeling (Vol. 1). New York: McGraw-Hill.
Chung, S., & Oh, J. (2006). Calibration of CE-QUAL-W2 for a monomictic reservoir in a monsoon climate area. Water Science & Technology, 54(11-12), 29-37.
Chine, W. H., Wang, T. S., Chen, L., & Kou, C. H. (2009). Artificial Neural Networks for Water Quality Prediction in a Reservoir. In Computer Science and Engineering, 2009. WCSE''09. Second International Workshop on(Vol. 1, pp. 516-519). IEEE.
Cole, T.M., & Wells, S.A. (2010). CE-QUAL-W2: A Two-Dimensional, Laterally Averaged, Hydrodynamic and Water Quality Model, User Manual, Version 3.7, Waterways Experiment Station, U.S. Army Corps of Engineers.
French, M., & Recknagel, F. (1994). Modeling of algal blooms in freshwaters using artificial neural networks. Computer Techniques in Environmental Studies V, vol.2: environment systems, Computational Mechanics Publications, Boston, 87-94.
Garvey, E., Tabiason, J.E., Hayes, M., Wolfram, E., Reckhow, D.A. & Male, J.W. (1988). Coliform Transport in a Pristine Reservoir: Modeling and Field Studies. Water Science and Technology, Vol.37, No.2, 137-144.
Gunduz, O., Soyupak, S., & Yurteri, C. (1998). Development of water quality management strategies for the proposed Isikli Reservoir. Water science and technology, 37(2), 369-376.
Hebb, D. O. (1949). The organization of behavior: A Neuropsychological Theory. Wiley, New York.
Hsu, H. H., Chen, L., Kou, C. H., Yeh, H. C., & Wang, T. S. (2009). Applying Multi-temporal Satellite Imageries to Estimate Chlorophyll-a Concentration in Feitsui Reservoir Using ANNs. In Artificial Intelligence, JCAI''09. International Joint Conference on IEEE.
Kuo, J. T., Hsieh, M. H., Lung, W. S., & She, N. (2002). Using artificial neural network for reservoir eutrophication prediction. Ecological Modelling, Vol.200, 171-177.
Kuo, J. T., Lung, W. S., Yang, C. P., Liu, W. C., Yang, M. D., & Tang, T. S. (2006). Eutrophication modelling of reservoirs in Taiwan. Environmental Modelling & Software, 21(6), 829-844.
Kuo, J. T., Wang, Y. Y., & Lung, W. S. (2006). A Hybrid Neural‐Genetic Algorithm for Reservoir Water Quality Management. Water Research. Vol.40, 1367‐1376.
Kuo, J. T., Hsieh, M. H., Lung, W. S., & She, N. (2007). Using artificial neural network for reservoir eutrophication prediction. Ecological modelling, 200(1), 171-177.
Lung, W. S. (2001). Water quality modeling for wasteload allocations and TMDLs. Wiley. com.
Liu, W. C., Chen, W. B., & Kimura, N. (2009). Impact of phosphorus load reduction on water quality in a stratified reservoir-eutrophication modeling study. Environmental monitoring and assessment, 159(1-4), 393-406.
McCulloch, W. S. & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, vol. 5, 115-133.
Martin, J.L. (1988). Application of Two Dimension Water Quality Model. Journal of Environmental Engineering, ASCE, Vol.114, No.2, 317-335.
Riely, G.A., Stomnel, H. & Bumpus, D.F. (1949). Quantitative Ecology of the Plankton of the Western North Atlantic. Bulletin Bingham Oceanogr. Collection, Vol.12, No.3, 1-169.
Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, vol.65, 386-408.
Reckhow, K.H., & Chapra, S.C. (1983). Engineering Approaches for Lake Management: Empirical Models for Lake Trophic State Evaluation. ANN ARBOR SCI.
Ritchie, J. C., Cooper, C. M., & Schiebe, F. R. (1990). The relationship of MSS and TM digital data with suspended sediments, chlorophyll, and temperature in Moon Lake, Mississippi. Remote Sensing of environment, 33(2), 137-148.
Recknagel, F., French, M., Harkonen, P., & Yabubka, K. I. (1997). Artificial neural network approach for modeling and prediction of algal blooms. Ecological Modelling, Vol.96, 11-28.
Streeter, H. W., & Phelps, E. B. (1925). A study of the pollution and purification of the Ohio River, III. Factors concerned in the phenomena of oxidation and reaeration. Public Health Bulletin, 146.
Steel, J.H. (1965). Notes on Some Theoretical Problem in Production Ecology. University of California Press Berkeley and Los Angeles, California and University of California Press, Ltd. London, England.
Schindler, J.E. (1971). Food Quality and Zooplankton Nutrition. Journal of Animal Ecology, 40, 589-595.
Schindler, D.W., Kling, H., Schmidt, R.V., Prokopowich, J., Frost, V.E., Reid, R.A., & Capel, M. (1973). Eutrophication of Lake 227 by Addition of Phosphate and Nitrate: the Second, Third, and Fourth Years of Enrichment, 1970, 1971, and 1972. Journal of the Fisheries Research Board of Canada,30, 1415-1440.
Stein, S. M., Goulet, N., Kammer, T., Waye, D. & Saffarinia, K. (1998). Occoquan Water Supply Protection Tool. Water Resources Engineering 98, ASCE, Vol. 2, pp. 1159-1164.
Thomann, R. V., & Mueller, J. A. (1987). Principles of surface water quality modeling and control. Harper & Row, Publishers.
Vollenweider, R.A. (1968). Scientific Fundamentals of the Eutrophication of Lakes and Flowing Waters, with Particular Reference to Nitrogen and Phosphorus as Factors in Eutrophication. Tech. Rept. OECD, DAS/CSI/68.27.

Vollenweider, R.A. (1975). Advances in Defining Critical Loading Levels for Phosphorus in Lake Eutrophication. Mem. Inst. Ital. Idrobiol. 33, 53-83.
Wang, T. S., Tan, C. H., Chen, L., & Tsai, Y. C. (2008). Applying Artificial Neural Networks and Remote Sensing to Estimate Chlorophyll-a Concentration in Water Body. In Intelligent Information Technology Application, 2008. IITA''08. Second International Symposium on (Vol. 1, pp. 540-544). IEEE.
Yabunaka, K. I., Hosomi M., & Murakami, A. (1997). Novel application of a back-propagation artificial neural network model formulated to predict algal bloom. Water Science and Technology, Vol.36, No.5, 89-97.
Yang, C. P., Hsieh, C. Y., Wang, Y. M., & Hsiao, W. P. (2011). Using artificial neural network for reservoir water quality analysis in Taiwan. In Consumer Electronics, Communications and Networks (CECNet), 2011 International Conference on (pp. 1883-1886). IEEE.