查詢結果分析
相關文獻
- 結合類神經網路之動力波模式--蘭陽溪洪水預報為例
- 高解析降雨資料應用於河川洪水位預報
- 結合河川洪流演算與類神經網路模式於不同前導時間之洪水位預報分析
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
- 類神經網路(Neural Networks)的種類及其在影像處理上的應用
- C++Fuzzy類神經網路物件導向發展系統之建立
- 臺灣汽保費率之估計--對數線性費率模式與類神經網路之比較
頁籤選單縮合
| 題 名 | 結合類神經網路之動力波模式--蘭陽溪洪水預報為例=Dynamic Wave Models Coupled with ANN for Stage Prediction--A Case Study of Flood Forecast in Lanyang River |
|---|---|
| 作 者 | 許銘熙; 林洙宏; 傅金城; 陳信中; | 書刊名 | 農業工程學報 |
| 卷 期 | 56:3 2010.09[民99.09] |
| 頁 次 | 頁12-31 |
| 分類號 | 443.42 |
| 關鍵詞 | 運動波; 動力波; 類神經網路; 洪水位預報; Unsteady river routing model; Artificial neural network; Flood river stage forecasting; |
| 語 文 | 中文(Chinese) |
| 中文摘要 | 蘭陽溪流域平均年雨量達3,256公釐,是颱風侵襲次數最頻繁地區。天然地形造成河川坡陡流急,經常導致嚴重水患。經由即時數值模擬預測未來的河川洪水位之變化,可適時提出預警以降低洪災。在洪水預報模式中,本研究以迪聖凡納方程式為基礎,除了傳統的動力波模式外,還利用預報初始值修正、參數修正與結合類神經網路之動力波模式等。將即時監測水位或預報水位等資料進行回饋演算,以改善模式預報精度,使預報值更接近觀測值。文中以敏督利、南瑪都兩場颱洪事件進行模式測試,進而比較各個模式之預報精度。結果顯示結合類神經網路之動力波模式,可有效提升蘭陽溪流域颱洪期間預報未來1~3小時之河川水位準確度。 |
| 英文摘要 | The Lanyang river basin, the most frequent typhoon tracks in Taiwan, reaches 3,256 mm of the mean annual precipitation. The heavy rainfall combining with short river course usually results in severe damage. The numerical model is a useful tool on the river stage forecasts for the flood damage mitigation. This study develops a flood river stage forecasting model which integrates the ANN model river stage prediction at gauged stations and the unsteady flow routing model in rivers. The parameters of the flood routing model are updated by using the optimization technique which minimized the stage difference between the ANN model and river flood routing model. Two typhoon events were simulated to confirm the accuracy of the forecasting model. The present model can provide a satisfactory and reliable river stages forecasting for one to three-hours lead times following a storm for the Lanyang river basin. |
本系統中英文摘要資訊取自各篇刊載內容。