查詢結果分析
來源資料
相關文獻
- 類神經網路應用於颱風暴潮之預測
- 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
- 運用類神經網路於股價指數之套利--以日經225指數為例
- 使用類神經網路預估碳化鎢材料放電加工性能
頁籤選單縮合
題名 | 類神經網路應用於颱風暴潮之預測=Application of Artificial Neural Networks to Typhoon-Surge Forecasting |
---|---|
作 者 | 詹錢登; 曾志民; 王志賢; 王啟明; | 書刊名 | 海洋工程學刊 |
卷期 | 6:1 民95.04 |
頁次 | 頁1-24 |
分類號 | 328.55 |
關鍵詞 | 颱風暴潮; 類神經網路; 暴潮預測; Typhoon surge; Artificial neural network; Typhoon-surge forecasting; |
語文 | 中文(Chinese) |
中文摘要 | 本文應用倒傳遞類神經網路建立颱風暴潮預測模式,利用過去颱風特性資料與潮位測站氣象資料,推估未來颱風期間該潮位測站之颱風暴潮。依照不同輸入因子,考量四種類神經颱風暴潮預測模式,以梗枋潮位站過去12場颱風暴潮實測資料進行模式訓練,以4場颱風暴潮實測資料進行模式驗證,用以評選較佳之模式。本文提出以綜合評鑑指標來評估模式預測結果之好壞,並將預測結果區分為A (較好)、B (好)、C (普通)、D (差)及E (較差)等五級。結果顯示:Model D的預測結果較好。Model D是由t 時刻及t-1時刻颱風資料、潮位站氣象資料及暴潮偏差等18個輸入因子,推估t+1時刻以後之暴潮偏差。本文並應用Model D於台東成功潮位測站及嘉義東石潮位測站,先用此兩站之暴潮資料分別進行模式訓練,然後再進行颱風暴潮預測,結果顯示台東成功潮位測站暴潮預測結果優於嘉義東石潮位測站之暴潮預測結果。 |
英文摘要 | A typhoon-surge forecasting model was developed with the application of the back-propagation neural network (BPN) in the present paper. The data including the typhoon’s characteristics, meteorological conditions at (or near) the tidal observation station, and typhoon-surge height at the previous time were used as the input data to the model for the forecasting of typhoon surges in the next few hours. Based on the different composition of input factors, four models were tested and compared. Sixteen sets of typhoon- surge data at Geng-fang Tidal Station were collected, twelve of them were used in model’s calibration while the other four were used in model’s verification. A general evaluation index that is a composition of four performance indexes was proposed for the evaluation of model’s overall performance in typhoon-surge forecasting. The result of model’s forecast was classified into five grades: A (excellent), B (good), C (fair), D (poor) and E (bad), according to the value of the general evaluation index. The result shows that the Model D that has 18 input factors has better performance in typhoon-surge forecasting. The Model D was also applied to typhoon-surge forecasting at Cheng-kung Tidal Station and Tung-shih Tidal Station. Results indicate that the typhoon-surge forecast at Cheng-kung Tidal Station in eastern Taiwan has better performance, compared with the typhoon-surge forecast at Tung-shih Tidal Station in western Taiwan. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。