查詢結果分析
來源資料
頁籤選單縮合
題 名 | 區域頻率分析均一性區域劃分之研究=Study on Identification of Homogeneous Regions for Regional Frequency Analysis |
---|---|
作 者 | 陳儒賢; 陳清田; 洪毓婷; | 書刊名 | 臺灣水利 |
卷 期 | 58:2=230 2010.06[民99.06] |
頁 次 | 頁81-94 |
分類號 | 328.63 |
關鍵詞 | 區域頻率分析; 均一性區域; 主成分分析; 自組織映射圖網路; Regional frequency analysis; Homogeneous region; Principal component analysis; |
語 文 | 中文(Chinese) |
中文摘要 | 本研究分別應用K均值法、華德法及自組織映射圖 (self-organizingmap;簡稱SOM) 網路於區域頻率分析時之均一性區域劃分上。首先,本研究選用台灣地區127個雨量測站,將年最大一日雨量之平均值、標準差、變異係數與測站之UTM座標及測站高程,共計六個輸入因子,以K均值法及華德法進行群集分析,其所得之三個分群,再分別以不一致估量與異質性估量作評估,結果顯示分群效果並不佳。若以SOM網路進行分群,經由二維映射圖所得之十個均一性區域,經由不一致估量與異質性估量作評估,結果亦顯示分群效果不佳。為了消弭因子間之相關性,本研究先利用主成分分析(principalcomponentanalysis;簡稱PCA),針對127個雨量站共20年之年最大一日雨量資料進行主成分分析,總共擷取9個主要成分,再加上雨量測站之3個地文因子,共計12個因子作為SOM網路之輸入項。由SOM所得之二維映射圖可知,全台雨量測站可被劃分成17群,經由不一致估量與異質性估量之結果顯示,這17群所構成之均一性區域均通過測試。綜觀上述結果可知,PCA結合SOM網路不但可以消弭因子間之相關性,且其所劃分之均一性區域較其他方法更適合用於區域頻率分析,因此建議可將PCA結合SOM網路之方法應用於區域頻率分析之均一性區域劃分上。 |
英文摘要 | In this paper, the K-means method, Ward's method and self-organizing map (SOM) are applied to identify the homogeneous regions for regional frequency analysis. First, the annual maximum daily rainfall records from 127 gauges in Taiwan are available. Based on the mean, standard deviation and coefficient of variation of annual maximum daily rainfall, and the geographic characters of the gauges, including gauge latitude, gauge longitude and elevation, the K-means method and Ward's method are used to group the rain gauges into specific clusters. The 127 rain gauges are grouped into three clusters. The discordancy measure and heterogeneity test indicates that the three regions are not sufficiently homogeneous. In order to reduce the number of variables that are linearly formulated by the original data, principal component analysis (PCA) is applied to obtain the principal components. It is found that the first nine principal components explain over 80% of the information. Based on the transformed data resulting from PCA and the geographic characters of the gauges, the SOM is used to group the rain gauges into specific clusters. The 127 rain gauges are grouped into 17 clusters. The discordancy test and the heterogeneity test indicate that the 17 regions are sufficiently homogeneous. The approach based on the combination of PCA and SOM reduces future data collection costs. In addition, the results show that the SOM can identify the homogeneous regions more accurately as compared to the K-means method and Ward's method. Therefore, the proposed approach is recommended as an alternative to the identification of homogeneous regions for regional frequency analysis. |
本系統中英文摘要資訊取自各篇刊載內容。