Responsive image
博碩士論文 etd-0302110-160617 詳細資訊
Title page for etd-0302110-160617
論文名稱
Title
類神經網路應用於颱風暴潮之預測
Apply Neural Network Techniques for Storm Surge Prediction
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
97
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2009-12-29
繳交日期
Date of Submission
2010-03-02
關鍵字
Keywords
類神經、颱風、暴潮
Neural Network, Typhoon, Surge
統計
Statistics
本論文已被瀏覽 5760 次,被下載 1945
The thesis/dissertation has been browsed 5760 times, has been downloaded 1945 times.
中文摘要
台灣地區夏、秋兩季常受到颱風侵襲,而颱風所帶來氣壓變化及強風吹拂會導致海水面的異常升降,易造成沿海海岸嚴重災害,因此提高颱風暴潮預測準確度可降低颱風對於沿海地區影響風險。本文採用具非線性及監督學習能力之倒傳遞類神經網路,根據Horikawa(1987)所提出最大暴潮偏差經驗公式得知影響暴潮之因子,因地理位置不同導致暴潮大小有所差異,故將因子對暴潮偏差作相關分析,篩選影響當地暴潮偏差主要因子作為輸入參數,建立颱風暴潮偏差之預測模式,並比較兩者差異。
首先收集並整理大鵬灣及高雄港測站潮位及氣象資料(風速、風向及氣壓),利用調和分析取得二者暴潮偏差變化,發現為內灣地形的大鵬灣暴潮變化大於開放灣域的高雄港,分別將二者所收集的風速、風向、氣壓差資料對其暴潮偏差作相關性分析。大鵬灣風速及風向對暴潮偏差相關性高達0.6702及0.58,氣壓差為0.3626;高雄港風速對暴潮偏差相關性達0.3723,而風向為-0.1559,氣壓差為-0.0337,皆低於0.3。將風向、風速及氣壓差作為輸入參數,比較其兩者差異。
利用大鵬灣資料測試選出當輸入參數為2∼4個時最佳的網路架構,將風速、風向及氣壓差分別當作輸入參數設定三個案例,預測結果為三者皆輸入訓練時為最佳。設計不同路徑颱風及相同路徑颱風訓練案例測試其差異,預測結果為以不同路徑颱風訓練最佳。分別以調和分析及經驗模態分解法的暴潮偏差作訓練,後者預測結果為佳。最後設計高雄港岸例輸入風速為訓練參數,其預測結果較大鵬灣差。
Abstract
Taiwan is often threaten by typhoon during summer and autumn. The surges brought by theses typhoons not only cause human lives in danger, but also cause severe floods in coastal area. Storm surge prediction remains still a complex coastal engineering problem to solve since lots of parameters may affect the predictions. The purpose of this study is to predict storm surges using an Artificial Neural Network (ANN). A non-linear hidden-layer forward feeding neural network using back-propagation learning algorithms was developed. The study included a detailed analysis the factors may affect the predictions. The factors were obtained from the formulation of storm surge discrepancies after Horikawa (1987). Storm surge behaviors may vary from different geographical locations and weather conditions. A correlation analysis of the parameters was carried out first to pick up those factors shown high correlations as input parameters for establishing the typhoon surge predictions.
The applications started with collecting tide and meteorological data (wind speed, wind direction and pressure) of Dapeng Bay and Kaohsiung harbor. A harmonic analysis was utilized to identify surge deviations. The surge deviation recorded at Dapeng Bay was found higher then Kaohsiung harbor for the same typhoon events. Correlation analysis has shown positive correlations between wind field, both wind speed and direction, and the associated storm surge deviations at Dapeng Bay. Correlation coefficients (CC) 0.6702 and 0.58 were found respectively. The variation of atmospheric pressure during typhoons is found with positive correlation too (i.e. CC=0.3626). Whereas the analysis has shown that the surges at Kaohsiung harbor were only sensitive to wind speed (CC=0.3723), while the correlation coefficients of the wind direction (CC=-0.1559) and atmospheric pressure (CC= -0.0337) are low. The wind direction, wind speed and atmospheric pressure variation were then used as input parameters for the training and predictions.
An optimum network structure was defined using the Dapeng Bay data. The best results were obtained by using wind speed, wind direction and pressure variation as input parameters. The ANN model can predict the surge deviation better if the empirical mode decomposition (EMD) method was used for training.
目次 Table of Contents
目錄
中文摘要 Ⅰ
英文摘要 Ⅱ
目錄 Ⅳ
表目錄 Ⅵ
圖目錄 Ⅶ
第一章 緒論 1
1-1 研究動機 1
1-2 文獻回顧 1
1-3 研究目的 5
1-4 研究架構 6
第二章 研究方法 7
2-1 暴潮理論 7
2-2 調和分析 10
2-3 類神經網路 14
2-3-1 倒傳遞類神經網路演算法 16
2-3-2 轉換函數 21
2-3-3 學習速率及慣性因子 22
第三章 資料處理及分析 27
3-1 地理位置及資料來源 27
3-2 資料分析 29
第四章 模式建立及驗證 55
4-1 網路模式建構及最佳化 55
4-2 結果分析 58
4-2-1 效能評鑑指標 58
4-2-2 結果分析 59
第五章 結論與建議 75
5-1 結論 75
5-2 建議 77
參考文獻 78

參考文獻 References
參考文獻
1. 楊春生 (1974) 「台灣北岸暴潮推算之研究」,台南水工試驗所土木水利學術彙刊,第49-63頁。
2. 黃壽銘 (1975) 「花蓮暴潮推算之研究」,國立台灣大學海洋研究所碩士論文。
3. 魏靖松 (1976) 「暴潮統計分析及數值推算」,國立成功大學水利及海洋研究所碩士論文。
4. 王俊、馬亞平 (1980) 「台灣地區暴潮現象之研究(第一報)」,第四屆海洋工程研討會論文集,第569-584頁。
5. 李賢文 (1984) 「沿海窪地與海水堆升之研究 (1)-台灣周圍海域颱風暴潮數值模擬式」,防災科技研究報告。
6. 邵建林、張憲國 (1992) 「選擇性堆積有限元素法應用於暴潮傳遞之解析」,第十四屆海洋工程研討會論文集,第148-164頁。
7. 薛曙生 (1995) 「台灣西南海岸地區颱風氣候特性與頻率以及外傘頂洲海岸地區暴潮洪水研究」,第十七屆海洋工程研討會論文集,第1617-1627頁。
8. 李賢文、陳志堅 (1996) 「台灣東北海域潮流預測數值模式」,台灣海洋學刊第三十五期第一號,第65-88頁。
9. 徐月娟、曾淑芬、陳進益、蔡恆雄 (1998) 「台灣地區八十三年至八十六年颱風暴潮特性之初步研究」,交通部中央氣象局學報,第42卷,第3期,第230-247頁。
10. 劉文俊 (1999) 「台灣的潮汐」,萬森興業有限公司。
11. 莊文傑、江中權 (2000) 「台灣四周海域海流數值模擬研究」,MOT-IOT-IHMT-NA8916基本研究報告,交通部運輸研究所港灣技術研究中心。
12. 李芳承 (2001) 「台灣北部與東部海岸之暴潮模擬」,國立海洋大學河海工程學系碩士論文。
13. 李宗霖、S. Rajasekaran、徐月娟、楊宗儒 (2003) 「序列學習神經網路在颱風期間之潮位預測」,第25屆海洋工程研討會論文集,第275-279頁。
14. 郭金棟 (2004) 海岸保護,科技圖書公司,第24頁。
15. 王啟明 (2004) 「類神經網路應用於颱風暴潮之預測」,國立成功大學水利及海洋工程研究所碩士論文。
16. 于嘉順、徐月娟、尤皓正、江朕榮、朱啟豪 (2005) 「台灣海域風暴潮模式之發展與應用」,2005台灣海洋年-海洋資訊應用研討會論文彙編,中央氣象局,台北,第125-130頁。
17. 蔡清標、黃貴麟、游智宇 (2006) 「類神經網路在淡水河口暴潮位預測之應用」, 第28屆海洋工程研討會論文集,第265-270頁。
18. 施文豪 (2007) 「類神經網路在颱風暴潮預測之研究」,立德管理學院資源環境學系研究所碩士論文。
19. 游智宇 (2007) 「以類神經網路預測淡水河口暴潮偏差之研究」,國立中興大學土木工學系研究所碩士論文。
20. Bernoulli, D. (1740) “Trait’e sur le flux et reflux de la mer.” Paris.
21. Chang, F.J. and Chen, Y.C. (2003) “Estuary water-stage forecasting by using radial basis function neural network.” Journal of Hydrology, Vol. 207, pp. 158–166.
22. Darwin, G.H. (1982) “On an apparatus for facilitating the reduction of tidal observations,” Proc. Roy. Soc(London), Ser.A252, pp.346-376.
23. Deo, M.C. and Sridhar, N.C. (1999) “Real time wave forecasting using neural networks,” Ocean Engineering, Vol.26, pp.191-203.
24. Doodson, A.T. (1928) “The analysis of tidal observations.” Philosophical Trans. Roy. Soc. , London, Ser. A 227, pp.223-279.
25. Doodson, A.T. (1957) “The analysis and prediction of tides in shallow water.” Int. Hydrographic Rev., Monte-Carlo, Monaco., 33, pp.85-126.
26. Fan, C.W. and Kao, S.J. (2008) “Effects of climate events driven hydrodynamics on dissolved oxygen in a subtropical deep reservoir in Taiwan.” Science of The Total Environment 393, pp. 326-332.
27. Horikawa (1978) Coastal Engineering, Tokyo University Press, pp.153-177.
28. Hopfield, J. (1982) Neural networks and physical systems with emergent collective computational properties, Proceedings of the National Academy of Sciences of the USA, Vol.79, pp2554-2588.
29. Haykin, S. (1999) NEURAL NETWORKS A comprehensive foundation, second edition, Prentice-Hall, New Jersey.
30. Lee, J.H.W., Wong, K.T.M., Huang, Y. and Jayawardena, A.W. (1991) “A real time early warning and modeling system for red tides in Hong Kong.” Hong Kong Research Grants Council Central Allocation Group Research Project.
31. Lee, T.L., Tsai, C.P., Jeng, D.S. and Shieh, R.J. (2002) “Neural Network for the prediction and supplement of tidal record in Taichung Harbor, Taiwan.” Advances in Engineering Softwares, Vol. 33, No. 6, PP.329-338, 2002.
32. Lee, T.L. (2004) “Back-propagation neural network for long-term tidal predictions.” Ocean Engineering, Vol. 31, No.9, pp.225-238.
33. Lee, T.L., Rajasekaran S. and Hsu, Y.J. (2004) “Tidal Level Forecasting during Typhoon Surge using Functional Network.” The ninth conference on artificial intelligence and applications, (on the CD Rom#54).
34. Lee, T.L., (2006), “Neural Network Prediction of a Storm Surge.” Ocean Engineering, Vol. 30, pp.85-103.
35. Marzenna, S. (2003) ”Forecast of storm surge by means of artificial neural network.” Journal of Sea Research, Vol. 49, pp.317-322.
36. Newton, I. (1687) Principia mathematica, London.
37. Recknagel, F.,French, M., Harkonen, P. and Yabunaka, K.I. (1997) “Artificial neural network approach for modeling and prediction of algal blooms.” Ecological Modelling 96, pp. 11-28.
38. Rumelhart, D.E., and J.L. McClelland, eds., (1986) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, Cambridge, MA: MIT Press.
39. Schmid, B.H. and Koskiaho, J. (2006) “Artificial neural network modeling of dissolved oxygen in a wetland pond: the case of Hovi, Finland.” Journal of Hydrologic Engineering, Vol.11, No. 2, pp. 188-192.
40. Serre, S. (2003) “Tidal-level forecasting and filtering by neural network model.” Costal Engineering Journal, Vol. 45, pp.119-137.
41. Tsai, C.P. and Lee, T.L. (1999) “Back-propagation neural network in tidal-level forecasting.” Journal of Waterway, Port, Coastal and Ocean Engineering, ASCE, Vol. 125, No. 4, pp.195-202.
42. Tsai, C.P., Lee, T.L., Yang, T.J., Hsu, Y.J. (2005) “Back-propagation neural networks for prediction of storm surge.” Structural and Environmental Engineering, Civil-comp Press, Vol.11, pp.589-596.
43. Walter, M., Recknagel, F., Carpenter, C., and Bormans, M. (2001) “Predicting eutrophication effects in the Burrinjuck Reservoir (Australia) by means of the deterministic model SALMO and the recurrent neural network model ANNA,” Ecological Modelling 146, pp.97-113.
44. Yu, C.S., Z.W. Song, D. Roose and J. Berlamont (1992), “Implementation of tidal flow equations on distributed parallel computers.” Proc. Of the Int. Conf. on Parallel Computing and Transputers Application (PACTA ’92), Barcelona, pp. 21-25.
45. Yu, C.S., H.Y. Chang, S.C. Tcheng and K.K. Huang (2000), “Modeling tidal flow currents in the Taiwan Strait on parallel computers.” Proceedings of the High Performance Computing Symposium – HPC 2000, Adrian Tentner (ed), SCS, Washington D.C., April 16-20, 2000, pp. 308-312.
電子全文 Fulltext
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
論文使用權限 Thesis access permission:校內外都一年後公開 withheld
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus: 已公開 available


紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code