https://scholars.lib.ntu.edu.tw/handle/123456789/87632
標題: | 應用類神經網路推估溪流之生物多樣性 A Study of Artificial Neural Networks for Estimating Riverine Biodiversity |
作者: | 蔡文柄 張斐章 Tsai, Wen-Ping Chang, Fi-John |
關鍵字: | 自組特徵輻狀基底類神經網路;臺灣生態水文指標系統;生物多樣性;Self-organizing radial basis neural networks;Taiwan ecohydrology index system;Bio-diversity | 公開日期: | 十二月-2009 | 卷: | 57 | 期: | 4 | 起(迄)頁: | 1-13 | 來源出版物: | 臺灣水利 | 摘要: | 河川流量管理為一兼顧人類使用需求及河川生態系統需求之理念,將生態觀念融入河川流量經營管理之中,以達到人類與河川生態系統共存的理想。本研究建立自組特徵輻狀基底類神經網路架構,透過此模式對流量資料進行型態判別分類並利用台灣生態水文指標系統推估溪流生態中魚類的生物多樣性。共選取全台灣河川中未受人為控制、流量資料長度大於二十年且其上下游10公里內有魚類調查資料之流量站作為研究測站,模式於訓練階段的科岐異度實際值與網路推估值之相關係數高達0.82,而測試階段的實際值與推估值表現上,相關係數仍然有0.66,顯示模式除有對流量資料進型態判別分類的能力外,也能準確推估生物多樣性。 Steam flow management is the idea that combines the concept of ecology and provides the demand for both human and river ecosystem. This study were built Self-Organizing Radial Basis Neural Networks. By this model, it can categorize the stream flow data and be estimated the diversities of fish families in river ecosystem by using the index of Taiwan Ecohydrology Index System. In this research, the stream flow data which are only collected with records more than 20 years and without anthropogenic control would be tested. The output of the model showed a high authenticity of the prediction (r > 0.82 and 0.66 for training and testing process, respectively) for the diversities. The result shows that this model not only can categorize the stream flow data but also can estimate the bio-diverstity efficiently and precisely. |
URI: | http://ntur.lib.ntu.edu.tw//handle/246246/258221 |
顯示於: | 生物環境系統工程學系 |
檔案 | 描述 | 大小 | 格式 | |
---|---|---|---|---|
應用類神經網路推估溪流之生物多樣性.pdf | 2.35 MB | Adobe PDF | 檢視/開啟 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。