| 研究生: |
林崇瑋 Lin, Chung-Wei |
|---|---|
| 論文名稱: |
應用類神經網路推估雲林、嘉義地區之地層下陷 Estimate the Land Subsidence in Yunlin and Chia-I with Neural Network |
| 指導教授: |
李振誥
Lee, Cheng-Haw |
| 學位類別: |
碩士 Master |
| 系所名稱: |
工學院 - 資源工程學系 Department of Resources Engineering |
| 論文出版年: | 2010 |
| 畢業學年度: | 98 |
| 語文別: | 中文 |
| 論文頁數: | 67 |
| 中文關鍵詞: | 雲林 、嘉義 、類神經網路 、地層下陷 |
| 外文關鍵詞: | Yunlin, Chia-I, Neural Network, Land Subsidence |
| 相關次數: | 點閱:93 下載:3 |
| 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 |
在台灣西部沿海地區,由於缺乏地下水管理及永續利用之觀念,使得地下水長期被不當超抽而引發嚴重的地層下陷問題。本研究主要目的首先利用類神經網路模擬出地下水位、雨量及地層下陷變化量之間的對映關係,以求得一適合雲林嘉義地區之類神經網路架構,再預測雲林嘉義地區於2010年至2030年的未來地層下陷變化量,最後與灰預測理論之預測結果進行比較。
本研究首先利用兩種類神經網路的模式進行比較(倒傳遞類神經網路與Elman類神經網路),選定輸入訓練因子,在進行類神經網路訓練中發現,以雨量之影響權重較大,其次為地下水水位,而雨量及地下水水位推估地層下陷量之類神經網路,以倒傳遞類神經網路所推估之結果誤差值較小,而Elman類神經網路誤差較大。在推估地層下陷結果中顯示,嘉義地區之地層下陷速率較雲林地區下陷速率大。
在全球氣候變遷情況下(2010年至2030年雨量),在嘉義及雲林地區應用倒傳遞類神經網路預測地層下陷量,每月地層下陷量皆大於現有觀測值之每月地層下陷量,地層下陷之速率最大成長5倍,最小成長1.2倍。與灰預測比較預測結果顯示,類神經網路之預測成果較灰預測之預測成果大1.6至7.6倍。
Due to lack of management and sustainable utilization viewpoint, groundwater has long been overdrawn improperly that caused serious land subsidence in western coast area of Taiwan. The main purpose of this study is first to apply Neural Network software to simulate the relations among groundwater level, rainfall and the variation of land subsidence for getting the Neural Network structure in the land subsidence area in Yunlin and Chia-I county, Taiwan. Two Neural Network models, Back-propagation Neural Network and Elman Neural Network were performed. Two Neural Network models, Back-propagation Neural Network and Elman Neural Network were performed. And then predict the variation of land subsidence in Yunlin and Chia-I area considering the situations of global climate change during 2010~2030. Finally, Gray system theory and Back-propagation Neural Network models were performed to compare in order to understand the model suitability
Results indicated that after deciding training factors, the weight of rainfall is more effective than groundwater level. The deviation of land subsidence is more accurate from Back-propagation Neural Network model with the rainfall and groundwater surface factors than those from Elman Neural Network model. Results also showed the land subsidence rate is quicker in Chia-I area than that in Yunlin area
Under considering rainfall data from 2010 to 2030 in global climate change situation, the expected results of land subsidence for each month in Yunlin and Chia-I area were larger than measured results as Back-propagation Neural Network model was applied. It also indicated that ratio between expected and measured subsidence per month may grow from a minimum value of two times to a maximum value of five times. By compared results using Gray system theory model and Back-propagation Neural Network model, the prediction result with Neural Network is larger 1.6 to 7.6 times than that with Gray system theory.
1. Banerjee,P., Prasad, R. K., Singh, V. S., 2008. Forecasting of groundwater level in hard rock region using artificial neural network. Environ Earth Sci.
2. Bowden, G.. J., Maier, H.R. and Dandy. G.. C, 2002, Optimal division of data for neural network models in water resources applications, Water Resources Research, Vol. 38, No2, pp.1029-1040.
3. Chang, F.J., L.C. Chang, and H.L. Huang, 2002. Real-time recurrent learning neural network for stream-flow forecasting. Hydrological Processes 16(13): 2577-2588.
4. Coulibaly, P., Anctil, F. and Bobée, B., 2000. Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. Journal of Hydrology 230, 244-257.
5. Dawson, C.W. and Wilby, R., 1998. An artificial neural network approach to rainfall-runoff modelling. Hydrolog. Sci. J., 43, 47– 66.
6. Gong, N., Denoeux, T.,Bertrand-Krajewski, J.L., 1996. Neural networks for solid transport modelling in sewer systems during storm events, Water Science and Technology Vol 33 No 9 pp 85–92.
7. Govindaraju, R.S., Ramachandra Rao, A., 2000. Artificial Neural Networks in Hydrology. Kluwer Academic Publishing, The Netherlands.
8. Ioannis N. daliakopoulos, Paulin Coulibaly, Ioannis K. Tsanis, 2005. Groundwater level forecasting using artificial neural networks. Journal of Hydrology 309,229-240.
9. Kim, K.D., Lee, S., Oh, H.J., 2009. Prediction of ground subsidence in Samcheok City, Korea using artificial neural networks and GIS. Environ Geol 58:61-70.
10. Lallahem, S., Mania, J., Hani, A., Najjar, Y., 2005. On the use of neural networks to evaluate groundwater level in fractured media. Journal of Hydrology 307:92-111.
11. Luk, K.C, Ball, J.E. and Sharma, A., 2000. A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting. Journal of Hydrology, 227, 56-65.
12. Maier, H.R., Dandy, G.C., 1998. Understanding the behavior and optimizing the performance of back-propagation neural networks: an empirical study. Environ. Modeling Software 13, 179-191.
13. Maier, H.R., Dandy, G.C., 2000. Neural networks for the prediction and forecasting of water resources variables: a review of modeling issues and applications. Environ. Modeling oftware 15, 101-124.
14. Nayak, P.C., Satyaji, U.R., Sudheer, K.P., 2006. Groundwater level forecasting in shallow aquifer using artificial neural network approach. Water Resour Manage 20:77-90.
15. Toth, E., Brath , A., Montanari , A., 2000. Comparison of short-term rainfall prediction models for real-time flood forecasting. J. Hydrol., 239: 132-147.
16. Waltham A.C, 1989. Ground subsidence. Blackie & Son Ltd. New York, pp 49-97.
17. Wang, C.H., Kuo, C.H., Peng, T.R., Chen, W.F., Liu, T.K., Chiang, C.J., Liu, W.C. and Hung, J.J., 2001. Isotope Characteristics of Taiwan Groundwaters. Western Pacific Earth Sciences, 1(4):415-428.
18. Wimrie, C.E., Durucan, S., and Korre, A., 2000. River flow prediction using artificial neural networks: generalization beyond the calibration range, Journal of Hydrology, Vol.233, pp.138-153.
19. Zhang, G., Patuwo, B.E., Hu, M.Y., 1998. Forecasting with artificial neural networks: the state of the art. Int. J. Forecasting 14, 35-62.
20. 王如意、潘宗毅、宋文元,2004,「遞迴式類神經網路之系統識別及其於降雨-逕流模擬之應用」,台灣水利,第52巻第4期,pp.1~14。
21. 李友平、張國強、劉萬里,2001,「台灣地區之地下水資源現況」,第四屆地下水資源與水源保護研討會,屏東,第201~210頁。
22. 吳漢雄、鄧聚龍、溫坤禮,1996,「灰色分析入門」,高立圖書有限公司。
23. 洪益發、梁昇,2001,「以類神經網路預測河川短期距流量」,中華水土保持學報,32(3):215-225。
24. 孫建平,1996,「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。
25. 孫建平、張斐章,1995,「倒傳遞類神經網路演算法於時雨量預測之研究」, 八十四年度農業工程研討會,台北,209-223。
26. 許盈松、周湘俊、陳昶憲、張國強,2004.09,類神經網路方法分析流量率定曲線之研究,台灣水利,第52卷,第三期, P.P.104-118。
27. 陳永祥、程惟國、李國煜、張斐章,2010,演化式類神經網路應用於蒸發量推估之研究,臺灣水利第58卷第1期。
28. 陳文福、江崇榮,1999,「濁水溪扇州及鄰近地區之沉積物分布與沉積環境」,地質第十八卷第二期,經濟部中央地質調查所。
29. 陳柏蒼,2002,「未設測站流量推估-利用類神經網路建構模式」,私立逢甲大學土木及水利工程所碩士論文。
30. 陳柏蒼、陳昶憲(2002),「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,pp.543-550。
31. 陳昶憲,吳青俊,鍾侑達,2004,「遞迴式類神經模式於日流量預測之應用」,中華水土保持學報, 35(3): 187-195。
32. 陳昶憲、鍾侑達、方唯鈞、劉錦蕙,2005,「結合類神經之模糊推理邏輯建置-以日流量預測模式為例」,臺灣水利季刊,第五十三卷,第三期,P.P41-55。
33. 陳莉、簡大為,2001,逕流量推估之研究,臺灣水利第49卷第4期。
34. 陳肇夏、何信昌、謝凱旋、羅偉、林偉雄、張徽正、黃鑑水、林啟文、陳政恆、楊昭男、李元希,2000,「台灣地質圖」,經濟部中央地質調查所。
35. 梁晉銘、張斐章、陳彥璋,2000,「預分類型類神經-模糊推論模式於水文系統之研究」,第十一屆水利工程研討會論文集,第L-107-L-112頁,台北。
36. 郭益銘、劉振宇,2000,「雲林沿海地區地下水質變化分析:(II)倒轉遞類神經網路法」,台灣水利,第48卷,第1期。
37. 郭勝豐、程澄元、劉振宇,2006,「倒傳遞神經網路應用於嘉南灌區作物蒸發散量之推估」,中國農業工程學報,第52卷,第1期,pp.24-34。
38. 張斐章、胡湘帆、黃源義,1998,「反傳遞模糊類神經網路於流量推估之應用」,中國農業工程學報,第44 卷,第2 期,pp.26-38。
39. 張斐章、胡湘帆、蕭錫清、張長圖,2000,「模糊類神經網路於水庫即時入流量預測之應用」, 台電工程月刊,第618期,pp 7-19。
40. 張斐章、黃源義、梁晉銘、孫建平,1996,「類神經網路在水文歷程之研析」,第二屆海峽兩岸水利科技交流研討會,台北,253-266。
41. 張斐章、張麗秋,2005,「類神經網路」,東華書局。
42. 彭宗仁、劉聰桂,1992,「地下水的碳十四定年及其應用」,地質,第十二卷,第二期,第 212-217 頁。
43. 詹仕堅、孫志鴻、徐美玲、李建堂,2004,「以集水區地文特徵為基礎的類神經網路洪水推估研究」,中華水土保持學報,35(1): 1-16。
44. 葉一隆, 2001,「斜率灰色模式與一維地下水流分析」,國立台灣大學農業工程學研究所博士論文。
45. 葉怡成,1995,「類神經網路─模式應用與實作」,儒林圖書有限公司。
46. 鄧聚龍,1997,「灰色控制系統」,華中理工大學出版社。
47. 鄭子璉,1996,「分佈型類神經網路降雨逕流模式之研究」,國立成功大學水利及海洋工程研究所,碩士論文。
48. 劉聰桂,1996,「由碳十四定年與氚示蹤探討濁水溪沖積扇地下水的流速與補注」,地下水資源與水質保護研討會,1-23頁。
49. 蘇中鈺,2009「雲林地層下陷易淹區水資源調配運用與管理之研究」,國立成功大學資源工程研究所碩士論文。