摘要 為了有效率地管理土地資源，遙測影像已成為不可或缺的土地利用監測工具。營建署目前正進行台灣地區每三到四個月多光譜衛星影像全國性土地利用之變遷偵測，偵測出的變遷區域，其空間分佈與其他空間資料間，可能隱含一些資訊，有助於增進土地利用變遷偵測之效率。 資料挖掘(Data Mining)，又稱作知識發現，其意義在於：發掘隱藏在大量資料中的知識。有關資料挖掘的各種技術與應用近年來蓬勃發展，同時也被廣泛地使用在發現大量空間資料中潛在的知識。本論文利用空間資料挖掘的方法，結合已取得之變遷位置與空間資料圖層(道路圖、建地圖、數值地形模型……等)，挖掘變遷發生地點與物件之空間關係中所隱藏的知識。採用的是資料挖掘中的監督式分類法，萃取出土地利用變遷以及空間資料間的相關規則，並根據這些規則建立變遷發生機率的空間分佈模型。此模型有助於評估全台各地發生地表變遷的潛勢，進而可針對變遷機率較高之區域進行優先處理。 As the dynamics of economic development and complication of land use, the limited land resource has suffered from a large amount of mismanagement in Taiwan. To prevent the land from being illegally used, a national land use/land cover change detection system has been worked out by National Central university and the government. In the system, national scale change detection is operated every 3~ 4 months. It is worthy to know that the spatial relations between the changed regions and other spatial objects may hide some valuable information that will help improve the change detection effectively. Spatial data mining, which is also considered as geographical knowledge discovery, is a branch of data mining that has attracted attention in the recent research. It puts emphasis on extracting interesting, implicit knowledge such as the spatial pattern or other significant mode not explicitly stored in the spatial databases. The main idea of the research is to utilize spatial data mining techniques to find some interesting knowledge hidden in the land change spots. The extracted knowledge will be use to perform spatial prediction that could make the land use monitoring task more efficient.
